Skocz do pozycji: 1.

Tytuł:

Towards ensuring software interoperability between deep learning frameworks

Autorzy:

Lee, Youn Kyu
Park, Seong Hee
Lim, Min Young
Lee, Soo-Hyun
Jeong, Jongwook

Powiązania:

https://bibliotekanauki.pl/articles/23944833.pdf

Data publikacji:

2023

Wydawca:

Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych

Tematy:

deep learning
interoperability
validation
verification
deep learning framework
model conversion

Opis:

With the widespread of systems incorporating multiple deep learning models, ensuring interoperability between target models has become essential. However, due to the unreliable performance of existing model conversion solutions, it is still challenging to ensure interoperability between the models developed on different deep learning frameworks. In this paper, we propose a systematic method for verifying interoperability between pre- and post-conversion deep learning models based on the validation and verification approach. Our proposed method ensures interoperability by conducting a series of systematic verifications from multiple perspectives. The case study confirmed that our method successfully discovered the interoperability issues that have been reported in deep learning model conversions.

Źródło:

Journal of Artificial Intelligence and Soft Computing Research; 2023, 13, 4; 215--228
2083-2567
2449-6499

Pojawia się w:

Journal of Artificial Intelligence and Soft Computing Research

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 2.

Tytuł:

Improving accuracy of detecting dangerous objects with deep learning
Poprawa skuteczności wykrycia niebezpiecznych obiektów przy użyciu technik deep learning

Autorzy:

Zacniewski, A.

Powiązania:

https://bibliotekanauki.pl/articles/315763.pdf

Data publikacji:

2016

Wydawca:

Instytut Naukowo-Wydawniczy "SPATIUM"

Tematy:

detecting dangerous objects
deep learning
detekcja niebezpiecznych obiektów
technika deep learning

Opis:

In this article, the problem of detecting dangerous objects with deep learning is presented. Convolutional Neural Networks are created with Python language ecosystem (Theano and Keras libraries), and then trained with different number of layers and different parameters. Accuracy of detection dangerous objects for artificial Neural Network with smaller number of layers is computed and obtained result is improved with deep learning. CIFAR-10 dataset is used due to useful classes included.
W artykule przedstawiono problem detekcji niebezpiecznych obiektów przy użyciu technik deep learning. Konwolucyjne sieci neuronowe tworzone są przy pomocy bibliotek języka Python takich jak Keras i Theano, a następnie trenowane są przy różnej liczbie warstw i z różnymi parametrami. Skuteczność detekcji niebezpiecznych obiektów dla małej liczby warstw sztucznej sieci neuronowej jest obliczana, a uzyskany wynik jest ulepszany przy użyciu technik deep learning. Zbiór danych CIFAR-10 został wykorzystany w badaniach z powodu dużej użyteczności występujących w nim klas.

Źródło:

Autobusy : technika, eksploatacja, systemy transportowe; 2016, 17, 12; 513-516
1509-5878
2450-7725

Pojawia się w:

Autobusy : technika, eksploatacja, systemy transportowe

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 3.

Tytuł:

Deep reinforcement learning overview of the state of the art

Autorzy:

Fenjiro, Y.
Benbrahim, H.

Powiązania:

https://bibliotekanauki.pl/articles/384788.pdf

Data publikacji:

2018

Wydawca:

Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów

Tematy:

reinforcement learning
deep learning
convolutional network
recurrent network
deep reinforcement learning

Opis:

Artificial intelligence has made big steps forward with reinforcement learning (RL) in the last century, and with the advent of deep learning (DL) in the 90s, especially, the breakthrough of convolutional networks in computer vision field. The adoption of DL neural networks in RL, in the first decade of the 21 century, led to an end-toend framework allowing a great advance in human-level agents and autonomous systems, called deep reinforcement learning (DRL). In this paper, we will go through the development Timeline of RL and DL technologies, describing the main improvements made in both fields. Then, we will dive into DRL and have an overview of the state-ofthe- art of this new and promising field, by browsing a set of algorithms (Value optimization, Policy optimization and Actor-Critic), then, giving an outline of current challenges and real-world applications, along with the hardware and frameworks used. In the end, we will discuss some potential research directions in the field of deep RL, for which we have great expectations that will lead to a real human level of intelligence.

Źródło:

Journal of Automation Mobile Robotics and Intelligent Systems; 2018, 12, 3; 20-39
1897-8649
2080-2145

Pojawia się w:

Journal of Automation Mobile Robotics and Intelligent Systems

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 4.

Tytuł:

A novel deep neural network that uses space-time features for tracking and recognizing a moving object

Autorzy:

Chang, O.
Constante, P.
Gordon, A.
Singaña, M.

Powiązania:

https://bibliotekanauki.pl/articles/91702.pdf

Data publikacji:

2017

Wydawca:

Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych

Tematy:

deep architectures
deep learning
artificial vision

Opis:

This work proposes a deep neural net (DNN) that accomplishes the reliable visual recognition of a chosen object captured with a webcam and moving in a 3D space. Autoencoding and substitutional reality are used to train a shallow net until it achieves zero tracking error in a discrete ambient. This trained individual is set to work in a real world closed loop system where images coming from a webcam produce displacement information for a moving region of interest (ROI) inside the own image. This loop gives rise to an emergent tracking behavior which creates a self-maintain flow of compressed space-time data. Next, short term memory elements are set to play a key role by creating new representations in terms of a space-time matrix. The obtained representations are delivery as input to a second shallow network which acts as ”recognizer”. A noise balanced learning method is used to fast train the recognizer with real-world images, giving rise to a simple and yet powerful robotic eye, with a slender neural processor that vigorously tracks and recognizes the chosen object. The system has been tested with real images in real time.

Źródło:

Journal of Artificial Intelligence and Soft Computing Research; 2017, 7, 2; 125-136
2083-2567
2449-6499

Pojawia się w:

Journal of Artificial Intelligence and Soft Computing Research

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 5.

Tytuł:

Interferogram blind denoising using deep residual learning for phase-shifting interferometry

Autorzy:

Xu, Xiaoqing
Xie, Ming
Chen, Song
Ji, Ying
Wang, Yawei

Powiązania:

https://bibliotekanauki.pl/articles/2060681.pdf

Data publikacji:

2022

Wydawca:

Politechnika Wrocławska. Oficyna Wydawnicza Politechniki Wrocławskiej

Tematy:

interferogram denoising
deep learning
interferometry

Opis:

The interferogram containing the noises often affects the accuracy of phase retrieval, leading to the degradation of the phase imaging quality. To address this issue, a new interferogram blind denoising (IBD) method based on deep residual learning is proposed. In the presence of unknown noise levels, during the training, the deep residual convolutional neural networks (DRCNN) in the IBD approach is able to remove the latent clean interferogram implicitly, and then gradually establish the residual mapping relation in the pixel-level between the interferogram and the noises. With a well-trained DRCNN model, this algorithm can deal not only with the single-frame interferogram efficiently but also with the multi-frame phase-shifted interferograms collaboratively, while effectively retaining interferogram features related to phase retrieval. Simulation and experimental results demonstrate the feasibility and applicability of the proposed IBD method.

Źródło:

Optica Applicata; 2022, 52, 1; 101--116
0078-5466
1899-7015

Pojawia się w:

Optica Applicata

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 6.

Tytuł:

Word prediction in computational historical linguistics

Autorzy:

Dekker, Peter
Zuidema, Willem

Powiązania:

https://bibliotekanauki.pl/articles/1818886.pdf

Data publikacji:

2020

Wydawca:

Polska Akademia Nauk. Instytut Podstaw Informatyki PAN

Tematy:

computational historical linguistics
machine learning
deep learning

Opis:

In this paper, we investigate how the prediction paradigm from machine learning and Natural Language Processing (NLP) can be put to use in computational historical linguistics. We propose word prediction as an intermediate task, where the forms of unseen words in some target language are predicted from the forms of the corresponding words in a source language. Word prediction allows us to develop algorithms for phylogenetic tree reconstruction, sound correspondence identification and cognate detection, in ways close to attested methods for linguistic reconstruction. We will discuss different factors, such as data representation and the choice of machine learning model, that have to be taken into account when applying prediction methods in historical linguistics. We present our own implementations and evaluate them on different tasks in historical linguistics.

Źródło:

Journal of Language Modelling; 2020, 8, 2; 295--336
2299-856X
2299-8470

Pojawia się w:

Journal of Language Modelling

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 7.

Tytuł:

Word prediction in computational historical linguistics

Autorzy:

Dekker, Peter
Zuidema, Willem

Powiązania:

https://bibliotekanauki.pl/articles/1818890.pdf

Data publikacji:

2020

Wydawca:

Polska Akademia Nauk. Instytut Podstaw Informatyki PAN

Tematy:

computational historical linguistics
machine learning
deep learning

Opis:

In this paper, we investigate how the prediction paradigm from machine learning and Natural Language Processing (NLP) can be put to use in computational historical linguistics. We propose word prediction as an intermediate task, where the forms of unseen words in some target language are predicted from the forms of the corresponding words in a source language. Word prediction allows us to develop algorithms for phylogenetic tree reconstruction, sound correspondence identification and cognate detection, in ways close to attested methods for linguistic reconstruction. We will discuss different factors, such as data representation and the choice of machine learning model, that have to be taken into account when applying prediction methods in historical linguistics. We present our own implementations and evaluate them on different tasks in historical linguistics.

Źródło:

Journal of Language Modelling; 2020, 8, 2; 295--336
2299-856X
2299-8470

Pojawia się w:

Journal of Language Modelling

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 8.

Tytuł:

Development of a neural network structure for identifying begin-end points in the assembly process

Autorzy:

Kutschenreiter-Praszkiewicz, Izabela

Powiązania:

https://bibliotekanauki.pl/articles/24084694.pdf

Data publikacji:

2023

Wydawca:

Wrocławska Rada Federacji Stowarzyszeń Naukowo-Technicznych

Tematy:

deep learning
assembly
begin-end point

Opis:

The paper presents an approach to video-based assembly analysis using machine learning. A neural network is one of the machine learning methods that is widely studied in many engineering fields. The purpose of this paper is to develop a deep neural network structure for identifying begin-end points for a selected component assembly process. A neural network structure that effectively identifies begin-end points is proposed and an example from industry is presented. The proposed approach can prove useful in the assembly process analysis.

Źródło:

Journal of Machine Engineering; 2023, 23, 2; 100-109
1895-7595
2391-8071

Pojawia się w:

Journal of Machine Engineering

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 9.

Tytuł:

Phase retrieval without phase unwrapping for white blood cells in deep-learning phase-shifting digital holography

Autorzy:

Jin, Shuyang
Xu, Xiaoqing
Chen, Jili
Ni, Yudan

Powiązania:

https://bibliotekanauki.pl/articles/2202768.pdf

Data publikacji:

2023

Wydawca:

Politechnika Wrocławska. Oficyna Wydawnicza Politechniki Wrocławskiej

Tematy:

digital holography
phase retrieval
deep learning

Opis:

Phase retrieval and phase unwrapping are the two important problems for enabling quantitative phase imaging of cells in phase-shifting digital holography. To simultaneously cope with these two problems, a deep-learning phase-shifting digital holography method is proposed in this paper. The proposed method can establish the continuous mapping function of the interferogram to the ground-truth phase using the end-to-end convolutional neural network. With a well-trained deep convolutional neural network, this method can retrieve the phase from one-frame blindly phase-shifted interferogram, without phase unwrapping. The feasibility and applicability of the proposed method are verified by the simulation experiments of the microsphere and white blood cells, respectively. This method will pave the way to the quantitative phase imaging of biological cells with complex substructures.

Źródło:

Optica Applicata; 2023, 53, 1; 127--140
0078-5466
1899-7015

Pojawia się w:

Optica Applicata

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 10.

Tytuł:

Real-time face mask detection in mass gatherings to reduce Covid-19 spread

Autorzy:

Soner, Swapnil
Litoriya, Ratnesh
Khatri, Ravi
Hussain, Ali Asgar
Pagrey, Shreyas
Kushwaha, Sunil Kumar

Powiązania:

https://bibliotekanauki.pl/articles/27314233.pdf

Data publikacji:

2023

Wydawca:

Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów

Tematy:

Covid
machine learning
face mask detection
Deep Learning

Opis:

The Covid 19 (coronavirus) pandemic has become one of the most lethal health crises worldwide. This virus gets transmitted from a person by respiratory droplets when they sneeze or when they speak. According to leading and well‐known scientists, wearing face masks and maintain‐ ing six feet of social distance are the most substantial protections to limit the virus’s spread. In the proposed model we have used the Convolutional Neural Network (CNN) algorithm of Deep Learning (DL) to ensure efficient real‐time mask detection. We have divided the system into two parts—1. Train Face Mask Detector 2. Apply Face Mask Detector—for better understanding. This is a real‐ time application that is used to discover or detect the person who is wearing a mask at the proper position or not, with the help of camera detection. The system has achieved an accuracy of 99% after being trained with the dataset, which contains around 1376 images of width and height 224×224 and also gives the alarm beep message after the detection of no mask or improper mask usage in a public place.

Źródło:

Journal of Automation Mobile Robotics and Intelligent Systems; 2023, 17, 1; 51--58
1897-8649
2080-2145

Pojawia się w:

Journal of Automation Mobile Robotics and Intelligent Systems

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 11.

Tytuł:

Navigation strategy for mobile robot based on computer vision and YOLOv5 network in the unknown environment

Autorzy:

Bui, Thanh-Lam
Tran, Ngoc-Tien

Powiązania:

https://bibliotekanauki.pl/articles/30148249.pdf

Data publikacji:

2023

Wydawca:

Polskie Towarzystwo Promocji Wiedzy

Tematy:

mobile robot
navigation
deep learning
computer vision

Opis:

The capacity to navigate effectively in complex environments is a crucial prerequisite for mobile robots. In this study, the YOLOv5 model is utilized to identify objects to aid the mobile robot in determining movement conditions. However, the limitation of deep learning models being trained on insufficient data, leading to inaccurate recognition in unforeseen scenarios, is addressed by introducing an innovative computer vision technology that detects lanes in real-time. Combining the deep learning model with computer vision technology, the robot can identify different types of objects, allowing it to estimate distance and adjust speed accordingly. Additionally, the paper investigates the recognition reliability in varying light intensities. When the light illumination increases from 300 lux to 1000 lux, the reliability of the recognition model on different objects also improves, from about 75% to 98%, respectively. The findings of this study offer promising directions for future breakthroughs in mobile robot navigation.

Źródło:

Applied Computer Science; 2023, 19, 2; 82-95
1895-3735
2353-6977

Pojawia się w:

Applied Computer Science

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 12.

Tytuł:

A CNN Approach to Central Retinal Vein Occlusion Detection

Autorzy:

Bala, Jayanthi Rajee
Sindha, Mohamed Mansoor Roomi
Sahayam, Jency
Govindharaj, Praveena
Rakesh, Karthika Priya

Powiązania:

https://bibliotekanauki.pl/articles/27311911.pdf

Data publikacji:

2023

Wydawca:

Polska Akademia Nauk. Czasopisma i Monografie PAN

Tematy:

Blood vessels
segmentation
Features
CRVO
deep learning

Opis:

In the field of medicine there is a need for the automatic detection of retinal disorders. Blindness in older persons is primarily caused by Central Retinal Vein Occlusion (CRVO). It results in rapid, irreversible eyesight loss, therefore, it is essential to identify and address CRVO as soon as feasible. Hemorrhages, which can differ in size, pigment, and shape from dot-shaped to flame hemorrhages, are one of the earliest symptoms of CRVO. The early signs of CRVO are, hemorrhages, however, so mild that ophthalmologists must dynamically observe such indicators in the retina image known as the fundus image, which is a challenging and time-consuming task. It is also difficult to segment hemorrhages since the blood vessels and hemorrhages (HE) have the same color properties also there is no particular shape for hemorrhages and it scatters all over the fundus image. A challenging study is needed to extract the characteristics of vein deformability and dilatation. Furthermore, the quality of the captured image affects the efficacy of feature Identification analysis. In this paper, a deep learning approach for CRVO extraction is proposed.

Źródło:

International Journal of Electronics and Telecommunications; 2023, 69, 3; 565--570
2300-1933

Pojawia się w:

International Journal of Electronics and Telecommunications

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 13.

Tytuł:

A novel approach of voterank-based knowledge graph for improvement of multi-attributes influence nodes on social networks

Autorzy:

Pham, Hai Van
Duong, Pham Van
Tran, Dinh Tuan
Lee, Joo-Ho

Powiązania:

https://bibliotekanauki.pl/articles/23944825.pdf

Data publikacji:

2023

Wydawca:

Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych

Tematy:

video surveillance
deep learning
moving object detection

Opis:

Recently, measuring users and community influences on social media networks play significant roles in science and engineering. To address the problems, many researchers have investigated measuring users with these influences by dealing with huge data sets. However, it is hard to enhance the performances of these studies with multiple attributes together with these influences on social networks. This paper has presented a novel model for measuring users with these influences on a social network. In this model, the suggested algorithm combines Knowledge Graph and the learning techniques based on the vote rank mechanism to reflect user interaction activities on the social network. To validate the proposed method, the proposed method has been tested through homogeneous graph with the building knowledge graph based on user interactions together with influences in realtime. Experimental results of the proposed model using six open public data show that the proposed algorithm is an effectiveness in identifying influential nodes.

Źródło:

Journal of Artificial Intelligence and Soft Computing Research; 2023, 13, 3; 165--180
2083-2567
2449-6499

Pojawia się w:

Journal of Artificial Intelligence and Soft Computing Research

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 14.

Tytuł:

A Brief Review of Recent Developments in the Integration of Deep Learning with GIS

Autorzy:

Mohan, Shyama
Giridhar, M.V.S.S

Powiązania:

https://bibliotekanauki.pl/articles/2055781.pdf

Data publikacji:

2022

Wydawca:

Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH

Tematy:

deep learning
GIS
integration
classification
remote sensing

Opis:

The interaction of Deep Learning (DL) methods with Geographical Information System (GIS) provides the opportunity to obtain new insights into environmental processes through the spatial, temporal and spectral resolutions as well as data integration. The two technologies may be connected to form a dynamic system that is incredibly well adapted to the evaluation of environmental conditions through the interrelationships of texture, size, pattern, and process. This perspective has acquired popularity in multiple disciplines. GIS is significantly dependant on processors, particularly for 3D calculations, map rendering, and route calculation whereas DL can process huge amounts of data. DL has received a lot of attention recently as a technology with a plethora of promising results. Furthermore, the growing use of DL methods in a variety of disciplines, including GIS, is evident. This study tries to provide a brief overview of the use of DL methods in GIS. This paper introduces the essential DL concepts relevant to GIS, the majority of which have been published in recent years. This research explores remote sensing applications and technologies in areas such as mapping, hydrological modelling, disaster management, and transportation route planning. Finally, conclusions on contemporary framework methodologies and suggestions for further studies are provided.

Źródło:

Geomatics and Environmental Engineering; 2022, 16, 2; 21--38
1898-1135

Pojawia się w:

Geomatics and Environmental Engineering

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 15.

Tytuł:

Characterization of symbolic rules embedded in deep DIMLP networks : a challenge to transparency of deep learning

Autorzy:

Bologna, G.
Hayashi, Y.

Powiązania:

https://bibliotekanauki.pl/articles/91545.pdf

Data publikacji:

2017

Wydawca:

Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych

Tematy:

ensemble
Deep Learning
rule extraction
feature detectors

Opis:

Rule extraction from neural networks is a fervent research topic. In the last 20 years many authors presented a number of techniques showing how to extract symbolic rules from Multi Layer Perceptrons (MLPs). Nevertheless, very few were related to ensembles of neural networks and even less for networks trained by deep learning. On several datasets we performed rule extraction from ensembles of Discretized Interpretable Multi Layer Perceptrons (DIMLP), and DIMLPs trained by deep learning. The results obtained on the Thyroid dataset and the Wisconsin Breast Cancer dataset show that the predictive accuracy of the extracted rules compare very favorably with respect to state of the art results. Finally, in the last classification problem on digit recognition, generated rules from the MNIST dataset can be viewed as discriminatory features in particular digit areas. Qualitatively, with respect to rule complexity in terms of number of generated rules and number of antecedents per rule, deep DIMLPs and DIMLPs trained by arcing give similar results on a binary classification problem involving digits 5 and 8. On the whole MNIST problem we showed that it is possible to determine the feature detectors created by neural networks and also that the complexity of the extracted rulesets can be well balanced between accuracy and interpretability.

Źródło:

Journal of Artificial Intelligence and Soft Computing Research; 2017, 7, 4; 265-286
2083-2567
2449-6499

Pojawia się w:

Journal of Artificial Intelligence and Soft Computing Research

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 16.

Tytuł:

Deep learning based road recognition for intelligent suspension systems

Autorzy:

Sun, Jinwei
Cong, Jingyu

Powiązania:

https://bibliotekanauki.pl/articles/2055054.pdf

Data publikacji:

2021

Wydawca:

Polskie Towarzystwo Mechaniki Teoretycznej i Stosowanej

Tematy:

intelligent suspension system
deep learning
road recognition

Opis:

This paper presents a deep learning-based road recognition strategy for advanced suspension systems. A four-quarter suspension model with a magnetorheological (MR) damper is developed, and four typical road images with corresponding roughness data are collected. A back-propagation neural network based autoencoder and Convolutional Neural Networks (CNN) are utilized to form the deep learning structure. By utilizing the multi-object genetic algorithm, the optimal parameters can be obtained, and the control current can be adaptively adjusted. Simulation results indicate that the designed structure can identify the road type accurately, and the recognition-based control strategy can improve the suspension performance effectively.

Źródło:

Journal of Theoretical and Applied Mechanics; 2021, 59, 3; 493--508
1429-2955

Pojawia się w:

Journal of Theoretical and Applied Mechanics

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 17.

Tytuł:

Detrimental Starfish Detection on Embedded System: A Case Study of YOLOv5 Deep Learning Algorithm and TensorFlow Lite framework

Autorzy:

Toan, Nguyen Quoc

Powiązania:

https://bibliotekanauki.pl/articles/2086221.pdf

Data publikacji:

2022

Wydawca:

Politechnika Lubelska. Instytut Informatyki

Tematy:

deep learning
computer vision
YOLO
embedded system

Opis:

There is a great range of spectacular coral reefs in the ocean world. Unfortunately, they are in jeopardy, due to an overabundance of one specific starfish called the coral-eating crown-of-thorns starfish (or COTS). This article provides research to deliver innovation in COTS control. Using a deep learning model based on the You Only Look Once version 5 (YOLOv5) deep learning algorithm on an embedded device for COTS detection. It aids professionals in optimizing their time, resources, and enhances efficiency for the preservation of coral reefs worldwide. As a result, the performance over the algorithm was outstanding with Precision: 0.93 - Recall: 0.77 - F1score: 0.84.

Źródło:

Journal of Computer Sciences Institute; 2022, 23; 105--111
2544-0764

Pojawia się w:

Journal of Computer Sciences Institute

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 18.

Tytuł:

Moving object detection for complex scenes by merging BG modeling and deep learning method

Autorzy:

Lin, Chih-Yang
Huang, Han-Yi
Lin, Wei-Yang
Ng, Hui-Fuang
Muchtar, Kahlil
Nurdin, Nadhila

Powiązania:

https://bibliotekanauki.pl/articles/23944823.pdf

Data publikacji:

2023

Wydawca:

Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych

Tematy:

video surveillance
deep learning
moving object detection

Opis:

In recent years, many studies have attempted to use deep learning for moving object detection. Some research also combines object detection methods with traditional background modeling. However, this approach may run into some problems with parameter settings and weight imbalances. In order to solve the aforementioned problems, this paper proposes a new way to combine ViBe and Faster-RCNN for moving object detection. To be more specific, our approach is to confine the candidate boxes to only retain the area containing moving objects through traditional background modeling. Furthermore, in order to make the detection able to more accurately filter out the static object, the probability of each region proposal then being retained. In this paper, we compare four famous methods, namely GMM and ViBe for the traditional methods, and DeepBS and SFEN for the deep learning-based methods. The result of the experiment shows that the proposed method has the best overall performance score among all methods. The proposed method is also robust to the dynamic background and environmental changes and is able to separate stationary objects from moving objects. Especially the overall F-measure with the CDNET 2014 dataset (like in the dynamic background and intermittent object motion cases) was 0,8572.

Źródło:

Journal of Artificial Intelligence and Soft Computing Research; 2023, 13, 3; 151--163
2083-2567
2449-6499

Pojawia się w:

Journal of Artificial Intelligence and Soft Computing Research

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 19.

Tytuł:

Exploring convolutional auto-encoders for representation learning on networks

Autorzy:

Nerurkar, Pranav Ajeet
Chandane, Madhav
Bhirud, Sunil

Powiązania:

https://bibliotekanauki.pl/articles/305489.pdf

Data publikacji:

2019

Wydawca:

Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH

Tematy:

network representation learning
deep learning
graph convolutional neural networks

Opis:

A multitude of important real-world or synthetic systems possess network structures. Extending learning techniques such as neural networks to process such non-Euclidean data is therefore an important direction for machine learning re- search. However, this domain has received comparatively low levels of attention until very recently. There is no straight-forward application of machine learning to network data, as machine learning tools are designed for i:i:d data, simple Euclidean data, or grids. To address this challenge, the technical focus of this dissertation is on the use of graph neural networks for network representation learning (NRL); i.e., learning the vector representations of nodes in networks. Learning the vector embeddings of graph-structured data is similar to embedding complex data into low-dimensional geometries. After the embedding process is completed, the drawbacks associated with graph-structured data are overcome. The current inquiry proposes two deep-learning auto-encoder-based approaches for generating node embeddings. The drawbacks in such existing auto-encoder approaches as shallow architectures and excessive parameters are tackled in the proposed architectures by using fully convolutional layers. Extensive experiments are performed on publicly available benchmark network datasets to highlight the validity of this approach.

Źródło:

Computer Science; 2019, 20 (3); 273-288
1508-2806
2300-7036

Pojawia się w:

Computer Science

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 20.

Tytuł:

Comparative Experimental Investigation and Application of Five Classic Pre-Trained Deep Convolutional Neural Networks via Transfer Learning for Diagnosis of Breast Cancer

Autorzy:

Nogay, Hidir Selcuk
Akinci, Tahir Cetin Akinci
Yilmaz, Musa

Powiązania:

https://bibliotekanauki.pl/articles/2023314.pdf

Data publikacji:

2021

Wydawca:

Stowarzyszenie Inżynierów i Techników Mechaników Polskich

Tematy:

breast cancer
classification
deep learning
DCNN
transfer learning
diagnosis

Opis:

In this study, for the diagnosis and classification of breast cancer, we used and applied five classical pre-trained deep convolutional neural network models (DCNN) which have proven successful many times in different fields (ResNet-18, AlexNet, GoogleNet and SuffleNet). To make pre-trained DCNN models suitable for the purpose of our study, we updated some layers according to the new situation by using the transfer learning technique. We did not change the weights of all layers used in these five pre-trained DCNN models. Instead, we just gave new weights to the new layers so that new layers adapt faster to emerging new DCNN models. With these five pre-trained DCNN models, we have realized a quadruple classification as "cancer", "normal", "actionable" and "benign", and a binary classification as "actionable + cancer" and "normal + benign". With these two separate classification and diagnosis studies, we have carried out comparative experimental examination and analysis of pre-trained DCNN models for breast cancer diagnosis. In the study, it was concluded that successful results can be achieved with pre-trained DCNN models without extra time-consuming procedures such as feature extraction, and DCNN can perform quite successfully in cancer diagnosis and image comment.

Źródło:

Advances in Science and Technology. Research Journal; 2021, 15, 3; 1-8
2299-8624

Pojawia się w:

Advances in Science and Technology. Research Journal

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 21.

Tytuł:

Performance Analysis of LEACH with Deep Learning in Wireless Sensor Networks

Autorzy:

Prajapati, Hardik K.
Joshi, Rutvij

Powiązania:

https://bibliotekanauki.pl/articles/2200710.pdf

Data publikacji:

2022

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

machine learning
Deep learning
Convolutional Neural Network (CNN)
LEACH

Opis:

Thousands of low-power micro sensors make up Wireless Sensor Networks, and its principal role is to detect and report specified events to a base station. Due to bounded battery power these nodes are having very limited memory and processing capacity. Since battery replacement or recharge in sensor nodes is nearly impossible, power consumption becomes one of the most important design considerations in WSN. So one of the most important requirements in WSN is to increase battery life and network life time. Seeing as data transmission and reception consume the most energy, it’s critical to develop a routing protocol that addresses the WSN’s major problem. When it comes to sending aggregated data to the sink, hierarchical routing is critical. This research concentrates on a cluster head election system that rotates the cluster head role among nodes with greater energy levels than the others.We used a combination of LEACH and deep learning to extend the network life of the WSN in this study. In this proposed method, cluster head selection has been performed by Convolutional Neural Network (CNN). The comparison has been done between the proposed solution and LEACH, which shows the proposed solution increases the network lifetime and throughput.

Źródło:

International Journal of Electronics and Telecommunications; 2022, 68, 4; 799--805
2300-1933

Pojawia się w:

International Journal of Electronics and Telecommunications

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 22.

Tytuł:

A model of continual and deep learning for aspect based in sentiment analysis

Autorzy:

López, Dionis
Artigas-Fuentes, Fernando

Powiązania:

https://bibliotekanauki.pl/articles/27314219.pdf

Data publikacji:

2023

Wydawca:

Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów

Tematy:

continual learning
deep learning
catas
trophic forgetting
sentiment analysis

Opis:

Sentiment analysis is a useful tool in several social and business contexts. Aspect sentiment classification is a subtask in sentiment analysis that gives information about features or aspects of people, entities, products, or services present in reviews. Different deep learning models that have been proposed to solve aspect sen‐ timent classification focus on a specific domain such as restaurant, hotel, or laptop reviews. However, there are few proposals for creating a single model with high performance in multiple domains. The continual learn‐ ing approach with neural networks has been used to solve aspect classification in multiple domains. However, avoiding low, aspect classification performance in contin‐ ual learning is challenging. As a consequence, potential neural network weight shifts in the learning process in different domains or datasets. In this paper, a novel aspect sentiment classification approach is proposed. Our approach combines a trans‐ former deep learning technique with a continual learning algorithm in different domains. The input layer used is the pretrained model Bidirectional Encoder Representations from Transformers. The experiments show the efficacy of our proposal with 78 % F1‐macro. Our results improve other approaches from the state‐of-the-art.

Źródło:

Journal of Automation Mobile Robotics and Intelligent Systems; 2023, 17, 1; 3--12
1897-8649
2080-2145

Pojawia się w:

Journal of Automation Mobile Robotics and Intelligent Systems

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 23.

Tytuł:

Python Machine Learning. Dry Beans Classification Case

Autorzy:

Słowiński, Grzegorz

Powiązania:

https://bibliotekanauki.pl/articles/50091919.pdf

Data publikacji:

2024-09

Wydawca:

Warszawska Wyższa Szkoła Informatyki

Tematy:

machine learning
deep learning
data dimension reduction
activation function

Opis:

A dataset containing over 13k samples of dry beans geometric features was analyzed using machine learning (ML) and deep learning (DL) techniques with the goal to automatically classify the bean species. Performance in terms of accuracy, train and test time was analyzed. First the original dataset was reduced to eliminate redundant features (too strongly correlated and echoing others). Then the dataset was visualized and analyzed with a few shallow learning techniques and simple artificial neural network. Cross validation was used to check the learning process repeatability. Influence of data preparation (dimension reduction) on shallow learning techniques were observed. In case of Multilayer Perceptron 3 activation functions were tried: ReLu, ELU and sigmoid. Random Forest appeared to be the best model for dry beans classification task reaching average accuracy reaching 92.61% with reasonable train and test times.

Źródło:

Zeszyty Naukowe Warszawskiej Wyższej Szkoły Informatyki; 2024, 18, 30; 7-26
1896-396X
2082-8349

Pojawia się w:

Zeszyty Naukowe Warszawskiej Wyższej Szkoły Informatyki

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 24.

Tytuł:

Segmentation of bone structures with the use of deep learning techniques

Autorzy:

Krawczyk, Zuzanna
Starzyński, Jacek

Powiązania:

https://bibliotekanauki.pl/articles/2128158.pdf

Data publikacji:

2021

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

deep learning
semantic segmentation
U-net
FCN
ResNet
computed tomography
technika deep learning
głęboka nauka
segmentacja semantyczna
tomografia komputerowa

Opis:

The paper is focused on automatic segmentation task of bone structures out of CT data series of pelvic region. The authors trained and compared four different models of deep neural networks (FCN, PSPNet, U-net and Segnet) to perform the segmentation task of three following classes: background, patient outline and bones. The mean and class-wise Intersection over Union (IoU), Dice coefficient and pixel accuracy measures were evaluated for each network outcome. In the initial phase all of the networks were trained for 10 epochs. The most exact segmentation results were obtained with the use of U-net model, with mean IoU value equal to 93.2%. The results where further outperformed with the U-net model modification with ResNet50 model used as the encoder, trained by 30 epochs, which obtained following result: mIoU measure – 96.92%, “bone” class IoU – 92.87%, mDice coefficient – 98.41%, mDice coefficient for “bone” – 96.31%, mAccuracy – 99.85% and Accuracy for “bone” class – 99.92%.

Źródło:

Bulletin of the Polish Academy of Sciences. Technical Sciences; 2021, 69, 3; e136751, 1--8
0239-7528

Pojawia się w:

Bulletin of the Polish Academy of Sciences. Technical Sciences

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 25.

Tytuł:

Update on the study of Alzheimer’s disease through artificial intelligence techniques

Autorzy:

Garea-Llano, Eduardo

Powiązania:

https://bibliotekanauki.pl/articles/27314235.pdf

Data publikacji:

2023

Wydawca:

Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów

Tematy:

Alzheimer's disease
detection
progression
artificial intelligence
deep learning

Opis:

Alzheimer’s disease is the most common form of dementia that can cause a brain neurological disorder with progressive memory loss as a result of brain cell damage. Prevention and treatment of disease is a key challenge in today’s aging society. Accurate diagnosis of Alzheimer’s disease plays an important role in patient management, especially in the early stages of the disease, because awareness of risk allows patients to undergo preventive measures even before irreversible brain damage occurs. Over the years, techniques such as statistical modeling or machine learning algorithms have been used to improve understanding of this condition. The objective of the work is the study of the methods of detection and progression of Alzheimer’s disease through artificial intelligence techniques that have been proposed in the last three years. The methodology used was based on the search, selection, review, and analysis of the state of the art and the most current articles published on the subject. The most representative works were analyzed, which allowed proposing a taxonomic classification of the studied methods and on this basis a possible solution strategy was proposed within the framework of the project developed by the Cuban Center for Neurosciences based on the conditions more convenient in terms of cost and effectiveness and the most current trends based on the use of artificial intelligence techniques.

Źródło:

Journal of Automation Mobile Robotics and Intelligent Systems; 2023, 17, 2; 51--60
1897-8649
2080-2145

Pojawia się w:

Journal of Automation Mobile Robotics and Intelligent Systems

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 26.

Tytuł:

Skin Lesion Analysis Toward Melanoma Detection Using Deep Learning Techniques

Autorzy:

Sherif, Fatma
Mohamed, Wael A.
Mohra, A.S.

Powiązania:

https://bibliotekanauki.pl/articles/226719.pdf

Data publikacji:

2019

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

melanoma
skin cancer
convolutional neural network
deep learning

Opis:

In the last few years, a great attention was paid to the deep learning Techniques used for image analysis because of their ability to use machine learning techniques to transform input data into high level presentation. For the sake of accurate diagnosis, the medical field has a steadily growing interest in such technology especially in the diagnosis of melanoma. These deep learning networks work through making coarse segmentation, conventional filters and pooling layers. However, this segmentation of the skin lesions results in image of lower resolution than the original skin image. In this paper, we present deep learning based approaches to solve the problems in skin lesion analysis using a dermoscopic image containing skin tumor. The proposed models are trained and evaluated on standard benchmark datasets from the International Skin Imaging Collaboration (ISIC) 2018 Challenge. The proposed method achieves an accuracy of 96.67% for the validation set. The experimental tests carried out on a clinical dataset show that the classification performance using deep learning-based features performs better than the state-of-the-art techniques.

Źródło:

International Journal of Electronics and Telecommunications; 2019, 65, 4; 597-602
2300-1933

Pojawia się w:

International Journal of Electronics and Telecommunications

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 27.

Tytuł:

Comparative study of CNN and LSTM for opinion mining in long text

Autorzy:

Yousf, Siham
Rhanoui, Maryem
Mounia, Mikram

Powiązania:

https://bibliotekanauki.pl/articles/1837369.pdf

Data publikacji:

2020

Wydawca:

Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów

Tematy:

deep learning
long text opinion mining
CNN
LSTM

Opis:

The digital revolution has encouraged many companies to set up new strategic and operational mechanisms to supervise the flow of information published about them on the Web. Press coverage analysis is a part of sentiment analysis that allows companies to discover the opinion of the media concerning their activities, products and services. It is an important research area, since it involves the opinion of informed public such as journalists, who may influence the opinion of their readers. However, from an implementation perspective, the analysis of the opinion from media coverage encounters many challenges. In fact, unlike social networks, the Media coverage is a set of large textual documents written in natural language. The training base being huge, it is necessary to adopt large-scale processing techniques like Deep Learning to analyze their content. To guide researchers to choose between one of the most commonly used models CNN and LSTM, we compare and apply both models for opinion mining from long text documents using real datasets.

Źródło:

Journal of Automation Mobile Robotics and Intelligent Systems; 2020, 14, 3; 50-55
1897-8649
2080-2145

Pojawia się w:

Journal of Automation Mobile Robotics and Intelligent Systems

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 28.

Tytuł:

Segmentation of bone structures with the use of deep learning techniques

Autorzy:

Krawczyk, Zuzanna
Starzyński, Jacek

Powiązania:

https://bibliotekanauki.pl/articles/2173574.pdf

Data publikacji:

2021

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

deep learning
semantic segmentation
U-net
FCN
ResNet
computed tomography
technika deep learning
głęboka nauka
segmentacja semantyczna
tomografia komputerowa

Opis:

The paper is focused on automatic segmentation task of bone structures out of CT data series of pelvic region. The authors trained and compared four different models of deep neural networks (FCN, PSPNet, U-net and Segnet) to perform the segmentation task of three following classes: background, patient outline and bones. The mean and class-wise Intersection over Union (IoU), Dice coefficient and pixel accuracy measures were evaluated for each network outcome. In the initial phase all of the networks were trained for 10 epochs. The most exact segmentation results were obtained with the use of U-net model, with mean IoU value equal to 93.2%. The results where further outperformed with the U-net model modification with ResNet50 model used as the encoder, trained by 30 epochs, which obtained following result: mIoU measure – 96.92%, “bone” class IoU – 92.87%, mDice coefficient – 98.41%, mDice coefficient for “bone” – 96.31%, mAccuracy – 99.85% and Accuracy for “bone” class – 99.92%.

Źródło:

Bulletin of the Polish Academy of Sciences. Technical Sciences; 2021, 69, 3; art. no. e136751
0239-7528

Pojawia się w:

Bulletin of the Polish Academy of Sciences. Technical Sciences

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 29.

Tytuł:

Towards sustainable and intelligent machining: energy footprint and tool condition monitoring for media-assisted processes

Autorzy:

Dogan, Hakan
Jones, Llyr
Hall, Stephanie
Shokrani, Alborz

Powiązania:

https://bibliotekanauki.pl/articles/24084657.pdf

Data publikacji:

2023

Wydawca:

Wrocławska Rada Federacji Stowarzyszeń Naukowo-Technicznych

Tematy:

machining
deep learning
tool condition monitoring
energy footprint

Opis:

Reducing energy consumption is a necessity towards achieving the goal of net-zero manufacturing. In this paper, the overall energy footprint of machining Ti-6Al-4V using various cooling/lubrication methods is investigated taking the embodied energy of cutting tools and cutting fluids into account. Previous studies concentrated on reducing the energy consumption associated with the machine tool and cutting fluids. However, the investigations in this study show the significance of the embodied energy of cutting tool. New cooling/lubrication methods such as WS2-oil suspension can reduce the energy footprint of machining through extending tool life. Cutting tools are commonly replaced early before reaching their end of useful life to prevent damage to the workpiece, effectively wasting a portion of the embodied energy in cutting tools. A deep learning method is trained and validated to identify when a tool change is required based on sensor signals from a wireless sensory toolholder. The results indicated that the network is capable of classifying over 90% of the tools correctly. This enables capitalising on the entirety of a tool’s useful life before replacing the tool and thus reducing the overall energy footprint of machining processes.

Źródło:

Journal of Machine Engineering; 2023, 23, 2; 16--40
1895-7595
2391-8071

Pojawia się w:

Journal of Machine Engineering

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 30.

Tytuł:

Tomato disease detection model based on densenet and transfer learning

Autorzy:

Bakr, Mahmoud
Abdel-Gaber, Sayed
Nasr, Mona
Hazman, Maryam

Powiązania:

https://bibliotekanauki.pl/articles/2097440.pdf

Data publikacji:

2022

Wydawca:

Polskie Towarzystwo Promocji Wiedzy

Tematy:

leaf disease detection
convolutional neural network
deep learning
transfer learning

Opis:

Plant diseases are a foremost risk to the safety of food. They have the potential to significantly reduce agricultural products quality and quantity. In agriculture sectors, it is the most prominent challenge to recognize plant diseases. In computer vision, the Convolutional Neural Network (CNN) produces good results when solving image classification tasks. For plant disease diagnosis, many deep learning architectures have been applied. This paper introduces a transfer learning based model for detecting tomato leaf diseases. This study proposes a model of DenseNet201 as a transfer learning-based model and CNN classifier. A comparison study between four deep learning models (VGG16, Inception V3, ResNet152V2 and DenseNet201) done in order to determine the best accuracy in using transfer learning in plant disease detection. The used images dataset contains 22930 photos of tomato leaves in 10 different classes, 9 disorders and one healthy class. In our experimental, the results shows that the proposed model achieves the highest training accuracy of 99.84% and validation accuracy of 99.30%.

Źródło:

Applied Computer Science; 2022, 18, 2; 56--70
1895-3735

Pojawia się w:

Applied Computer Science

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 31.

Tytuł:

An automated driving strategy generating method based on WGAIL–DDPG

Autorzy:

Zhang, Mingheng
Wan, Xing
Gang, Longhui
Lv, Xinfei
Wu, Zengwen
Liu, Zhaoyang

Powiązania:

https://bibliotekanauki.pl/articles/2055167.pdf

Data publikacji:

2021

Wydawca:

Uniwersytet Zielonogórski. Oficyna Wydawnicza

Tematy:

automated driving system
deep learning
deep reinforcement learning
imitation learning
deep deterministic policy gradient
system jezdny
uczenie głębokie
uczenie przez naśladowanie

Opis:

Reliability, efficiency and generalization are basic evaluation criteria for a vehicle automated driving system. This paper proposes an automated driving decision-making method based on the Wasserstein generative adversarial imitation learning–deep deterministic policy gradient (WGAIL–DDPG(λ)). Here the exact reward function is designed based on the requirements of a vehicle’s driving performance, i.e., safety, dynamic and ride comfort performance. The model’s training efficiency is improved through the proposed imitation learning strategy, and a gain regulator is designed to smooth the transition from imitation to reinforcement phases. Test results show that the proposed decision-making model can generate actions quickly and accurately according to the surrounding environment. Meanwhile, the imitation learning strategy based on expert experience and the gain regulator can effectively improve the training efficiency for the reinforcement learning model. Additionally, an extended test also proves its good adaptability for different driving conditions.

Źródło:

International Journal of Applied Mathematics and Computer Science; 2021, 31, 3; 461--470
1641-876X
2083-8492

Pojawia się w:

International Journal of Applied Mathematics and Computer Science

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 32.

Tytuł:

Deep learning (pogłębianie procesu uczenia się) z perspektywy analizy potrzeb studentów języka angielskiego jako obcego
Deep Learning from the Perspective of Needs Analysis of Students of English as a Foreign Language

Autorzy:

Papaja, Katarzyna
Świątek, Artur
Mielnik, Kamil

Powiązania:

https://bibliotekanauki.pl/articles/1398073.pdf

Data publikacji:

2019-12-31

Wydawca:

Ateneum - Akademia Nauk Stosowanych w Gdańsku

Tematy:

Deep Learning
process
teacher
student
foreign language
personalisation
transformation
deep learning
pogłębione uczenie się
proces
nauczyciel
uczeń
język obcy
personalizacja
transformacja

Opis:

Although the term Deep Learning does not seem to be a new term in language learning, it attracted relatively little attention until just a few years ago. Different fields of study show that Deep Learning leverages a sophisticated process to learn multiple levels of abstraction from the data; however, in languages, the term has been widely accepted as the key concept in the transformation and personalisation of the learning process. In this paper, we take the definition of Deep Learning, and we corroborate the theories by use of the study which aims to assess the needs of students in the context of language exercises, resources as well as tools and modern technological solutions. A proper understanding of Deep Learning is necessary to examine the potential benefits for students and the broadly defined society. Therefore, the essence of the research is to obtain the answers to what is important in the education of modern foreign languages and also what the teacher’s role is. A quantitative study was conducted on 441 students of English Philology. The results of the needs analysis of foreign language students allow for a greater understanding of their expectations towards themselves and their teachers; additionally, to answer the question about what kind of education recipients they are and whether they are active participants in the whole educational process.
Choć termin pogłębionego procesu uczenia się (deep learning) nie wydaje się być terminem nowym w nauczaniu języków, do niedawna przyciągnął stosunkowo niewiele uwagi naukowców. W wielu językach jednak termin ten został powszechnie zaakceptowany jako kluczowa koncepcja transformacji i personalizacji procesu uczenia się. W niniejszym artykule prezentujemy definicję deep learning i potwierdzamy teorię poprzez badanie, którego celem jest ocena potrzeb uczniów w kontekście ćwiczeń językowych, zasobów, a także narzędzi i nowoczesnych rozwiązań technologicznych. Prawidłowe zrozumienie pogłębionego uczenia się jest konieczne, aby zbadać potencjalne korzyści wynikające z niego dla studentów i szeroko rozumianego społeczeństwa. Dlatego też istotą prowadzonych badań jest uzyskanie odpowiedzi na pytanie, co jest ważne w dydaktyce współczesnych języków obcych, a także jaka jest rola nauczyciela w tym zakresie. Wyniki analiz potrzeb uczniów języków obcych pozwalają uzyskać wiedzę na temat ich oczekiwań wobec siebie samych oraz wobec nauczycieli, a także odpowiedzieć na pytanie, jakiego rodzaju odbiorcami edukacji są młodzi uczący się i czy aktywnie partycypują w globalnym procesie kształcenia.

Źródło:

Forum Filologiczne Ateneum; 2019, 7, 1; 301-320
2353-2912
2719-8537

Pojawia się w:

Forum Filologiczne Ateneum

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 33.

Tytuł:

Effectiveness of Unsupervised Training in Deep Learning Neural Networks

Autorzy:

Rusiecki, Andrzej
Kordos, Mirosław

Powiązania:

https://bibliotekanauki.pl/articles/1373690.pdf

Data publikacji:

2015

Wydawca:

Uniwersytet Jagielloński. Wydawnictwo Uniwersytetu Jagiellońskiego

Tematy:

neural networks
deep learning
restricted Boltzmann Machine
contrastive divergence

Opis:

Deep learning is a field of research attracting nowadays much attention, mainly because deep architectures help in obtaining outstanding results on many vision, speech and natural language processing – related tasks. To make deep learning effective, very often an unsupervised pretraining phase is applied. In this article, we present experimental study evaluating usefulness of such approach, testing on several benchmarks and different percentages of labeled data, how Contrastive Divergence (CD), one of the most popular pretraining methods, influences network generalization.

Źródło:

Schedae Informaticae; 2015, 24; 41-51
0860-0295
2083-8476

Pojawia się w:

Schedae Informaticae

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 34.

Tytuł:

THE DE BONO LAMS SEQUENCE SERIES: TEMPLATE DESIGNS AS KNOWLEDGE-MOBILISING STRATEGY FOR 21ST CENTURY HIGHER EDUCATION

Autorzy:

Dobozy, Eva

Powiązania:

https://bibliotekanauki.pl/articles/941236.pdf

Data publikacji:

2012

Wydawca:

Uniwersytet Marii Curie-Skłodowskiej w Lublinie. IATEFL Poland Computer Special Interest Group

Tematy:

de Bono LAMS sequence series
student-producers
deep learning

Opis:

In this paper, the five interlocking de Bono LAMS sequences are introduced as a new form of generic template designs. This transdisciplinary knowledge-mobilising strategy is based on Edward de Bono’s attention-directing ideas and thinking skills, commonly known as the CoRT tools. The development of the de Bono LAMS sequence series is an important milestone, signifying the current paradigmatic shift in higher education from a student-consumer paradigm to a student-producer paradigm. Surpassing surface and shallow knowledge stages requires the use of multidisciplinary and generic knowledge in new and unfamiliar situations. The LAMS templates as ‘knowledge-in-practice’ models assist disciplinary specialists generate learning designs that make apparent to students that knowledge is always partial, incomplete and coloured by epistemological beliefs and cultural practices.

Źródło:

Teaching English with Technology; 2012, 12, 2; 88-102
1642-1027

Pojawia się w:

Teaching English with Technology

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 35.

Tytuł:

Application of deep learning neural networks for the diagnosis of electrical damage to the induction motor using the axial flux

Autorzy:

Skowron, M.

Powiązania:

https://bibliotekanauki.pl/articles/201768.pdf

Data publikacji:

2020

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

induction motor
axial flux
deep learning
convolutional neural networks

Opis:

In industrial drive systems, one of the widest group of machines are induction motors. During normal operation, these machines are exposed to various types of damages, resulting in high economic losses. Electrical circuits damages are more than half of all damages appearing in induction motors. In connection with the above, the task of early detection of machine defects becomes a priority in modern drive systems. The article presents the possibility of using deep neural networks to detect stator and rotor damages. The opportunity of detecting shorted turns and the broken rotor bars with the use of an axial flux signal is presented.

Źródło:

Bulletin of the Polish Academy of Sciences. Technical Sciences; 2020, 68, 5; 1031-1038
0239-7528

Pojawia się w:

Bulletin of the Polish Academy of Sciences. Technical Sciences

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 36.

Tytuł:

A hybrid geometallurgical study using coupled Historical Data (HD) and Deep Learning (DL) techniques on a copper ore mine

Autorzy:

Gholami, Alireza
Asgari, Kaveh
Khoshdast, Hamid
Hassanzadeh, Ahmad

Powiązania:

https://bibliotekanauki.pl/articles/2146884.pdf

Data publikacji:

2022

Wydawca:

Politechnika Wrocławska. Oficyna Wydawnicza Politechniki Wrocławskiej

Tematy:

hybrid geometallurgy
historical data
deep learning
copper ore
flotation

Opis:

This research work introduces a novel hybrid geometallurgical approach to develop a deep and comprehensive relationship between geological and mining characteristics with metallurgical parameters in a mineral processing plant. This technique involves statistically screening mineralogical and operational parameters using the Historical Data (HD) method. Further, it creates an intelligent bridge between effective parameters and metallurgical responses by the Deep Learning (DL) simulation method. In the HD method, the time and cost of common approaches in geometallurgical studies were minimized through the use of available archived data. Then, the generated DL-based predictive model was enabled to accurately forecast the process behavior in the mineral processing units. The efficiency of the proposed method for a copper ore sample was practically evaluated. For this purpose, six representative samples from different active mining zone were collected and used for flotation tests organized using a randomizing code. The experimental results were then statistically analyzed using HD method to assess the significance of mineralogical and operational parameters, including the proportions of effective minerals, particle size, collector and frother concentration, solid content and pH. Based on the HD analysis, the metallurgical responses including the copper grade and recovery, copper kinetics constant and iron grade in concentrate were modeled with an accuracy of about 90%. Next, the geometallurgical model of the process was developed using the long short-term memory neural network (LSTM) algorithm. The results showed that the studied metallurgical responses could be predicted with more than 95% accuracy. The results of this study showed that the hybrid geometallurgy approach can be used as a promising tool to achieve a reliable relationship between the mining and mineral processing sectors, and sustainable and predictable production.

Źródło:

Physicochemical Problems of Mineral Processing; 2022, 58, 3; art. no. 147841
1643-1049
2084-4735

Pojawia się w:

Physicochemical Problems of Mineral Processing

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 37.

Tytuł:

Deep learning in pharmacology: opportunities and threats

Autorzy:

Kocić, Ivan
Kocić, Milan
Rusiecka, Izabela
Kocić, Adam
Kocić, Eliza

Powiązania:

https://bibliotekanauki.pl/articles/25728738.pdf

Data publikacji:

2022-09-06

Wydawca:

Gdański Uniwersytet Medyczny

Tematy:

machine learning
pharmacology
deep learning
artificial intelligence
drug research and development

Opis:

Introduction This review aims to present briefly the new horizon opened to pharmacology by the deep learning (DL) technology, but also to underline the most important threats and limitations of this method. Material and Methods We searched multiple databases for articles published before May 2021 according to the preferred reported item related to deep learning and drug research. Out of the 267 articles retrieved, we included 50 in the final review. Results DL and other different types of artificial intelligence have recently entered all spheres of science, taking an increasingly central position in the decision-making processes, also in pharmacology. Hence, there is a need for better understanding of these technologies. The basic differences between AI (artificial intelligence), DL and ML (machine learning) are explained. Additionally, the authors try to highlight the role of deep learning methods in drug research and development as well as in improving the safety of pharmacotherapy. Finally, future directions of DL in pharmacology were outlined as well as possible misuses of it. Conclusions DL is a promising and powerful tool for comprehensive analysis of big data related to all fields of pharmacology, however it has to be used carefully.

Źródło:

European Journal of Translational and Clinical Medicine; 2022, 5, 2; 88-94
2657-3148
2657-3156

Pojawia się w:

European Journal of Translational and Clinical Medicine

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 38.

Tytuł:

Pre-trained deep neural network using sparse autoencoders and scattering wavelet transform for musical genre recognition

Autorzy:

Kleć, M.
Korzinek, D.

Powiązania:

https://bibliotekanauki.pl/articles/952940.pdf

Data publikacji:

2015

Wydawca:

Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH

Tematy:

Sparse Autoencoders
deep learning
genre recognition
Scattering Wavelet Transform

Opis:

Research described in this paper tries to combine the approach of Deep Neural Networks (DNN) with the novel audio features extracted using the Scatter- Ing Wavelet Transform (SWT) for classifying musical genres. The SWT uses A sequence of Wavelet Transforms to compute the modulation spectrum coef- Ficients of multiple orders, which has already shown to be promising for this Task. The DNN in this work uses pre-trained layers using Sparse Autoencoders (SAE). Data obtained from the Creative Commons website jamendo.com is Used to boost the well-known GTZAN database, which is a standard bench- mark for this task. The final classifier is tested using a 10-fold cross validation To achieve results similar to other state-of-the-art approaches.

Źródło:

Computer Science; 2015, 16 (2); 133-144
1508-2806
2300-7036

Pojawia się w:

Computer Science

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 39.

Tytuł:

A Survey on multi-objective based parameter optimization for deep learning

Autorzy:

Chakraborty, Mrittika
Pal, Wreetbhas
Bandyopadhyay, Sanghamitra
Maulik, Ujjwal

Powiązania:

https://bibliotekanauki.pl/articles/27312917.pdf

Data publikacji:

2023

Wydawca:

Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH

Tematy:

deep learning
multi-objective optimization
parameter optimization
neural networks

Opis:

Deep learning models form one of the most powerful machine learning models for the extraction of important features. Most of the designs of deep neural models, i.e., the initialization of parameters, are still manually tuned. Hence, obtaining a model with high performance is exceedingly time-consuming and occasionally impossible. Optimizing the parameters of the deep networks, therefore, requires improved optimization algorithms with high convergence rates. The single objective-based optimization methods generally used are mostly time-consuming and do not guarantee optimum performance in all cases. Mathematical optimization problems containing multiple objective functions that must be optimized simultaneously fall under the category of multi-objective optimization sometimes referred to as Pareto optimization. Multi-objective optimization problems form one of the alternatives yet useful options for parameter optimization. However, this domain is a bit less explored. In this survey, we focus on exploring the effectiveness of multi-objective optimization strategies for parameter optimization in conjunction with deep neural networks. The case studies used in this study focus on how the two methods are combined to provide valuable insights into the generation of predictions and analysis in multiple applications.

Źródło:

Computer Science; 2023, 24 (3); 327--359
1508-2806
2300-7036

Pojawia się w:

Computer Science

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 40.

Tytuł:

A progressive and cross-domain deep transfer learning framework for wrist fracture detection

Autorzy:

Karam, Christophe
El Zini, Julia
Awad, Mariette
Saade, Charbel
Naffaa, Lena
El Amine, Mohammad

Powiązania:

https://bibliotekanauki.pl/articles/2147130.pdf

Data publikacji:

2022

Wydawca:

Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych

Tematy:

deep learning
transfer learning
wrist fracture detection
medical informatics
progressive transfer learning

Opis:

There has been an amplified focus on and benefit from the adoption of artificial intelligence (AI) in medical imaging applications. However, deep learning approaches involve training with massive amounts of annotated data in order to guarantee generalization and achieve high accuracies. Gathering and annotating large sets of training images require expertise which is both expensive and time-consuming, especially in the medical field. Furthermore, in health care systems where mistakes can have catastrophic consequences, there is a general mistrust in the black-box aspect of AI models. In this work, we focus on improving the performance of medical imaging applications when limited data is available while focusing on the interpretability aspect of the proposed AI model. This is achieved by employing a novel transfer learning framework, progressive transfer learning, an automated annotation technique and a correlation analysis experiment on the learned representations. Progressive transfer learning helps jump-start the training of deep neural networks while improving the performance by gradually transferring knowledge from two source tasks into the target task. It is empirically tested on the wrist fracture detection application by first training a general radiology network RadiNet and using its weights to initialize RadiNetwrist, that is trained on wrist images to detect fractures. Experiments show that RadiNetwrist achieves an accuracy of 87% and an AUC ROC of 94% as opposed to 83% and 92% when it is pre-trained on the ImageNet dataset. This improvement in performance is investigated within an explainable AI framework. More concretely, the learned deep representations of RadiNetwrist are compared to those learned by the baseline model by conducting a correlation analysis experiment. The results show that, when transfer learning is gradually applied, some features are learned earlier in the network. Moreover, the deep layers in the progressive transfer learning framework are shown to encode features that are not encountered when traditional transfer learning techniques are applied. In addition to the empirical results, a clinical study is conducted and the performance of RadiNetwrist is compared to that of an expert radiologist. We found that RadiNetwrist exhibited similar performance to that of radiologists with more than 20 years of experience. This motivates follow-up research to train on more data to feasibly surpass radiologists’ performance, and investigate the interpretability of AI models in the healthcare domain where the decision-making process needs to be credible and transparent.

Źródło:

Journal of Artificial Intelligence and Soft Computing Research; 2022, 12, 2; 101--120
2083-2567
2449-6499

Pojawia się w:

Journal of Artificial Intelligence and Soft Computing Research

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 41.

Tytuł:

Yet another research on GANs in cybersecurity

Autorzy:

Zimoń, Michał
Kasprzyk, Rafał

Powiązania:

https://bibliotekanauki.pl/articles/13946602.pdf

Data publikacji:

2023-02-20

Wydawca:

Akademia Sztuki Wojennej

Tematy:

cybersecurity
malware
artificial intelligence
machine learning
deep learning
generative adversarial networks

Opis:

Deep learning algorithms have achieved remarkable results in a wide range of tasks, including image classification, language translation, speech recognition, and cybersecurity. These algorithms can learn complex patterns and relationships from large amounts of data, making them highly effective for many applications. However, it is important to recognize that models built using deep learning are not fool proof and can be fooled by carefully crafted input samples. This paper presents the results of a study to explore the use of Generative Adversarial Networks (GANs) in cyber security. The results obtained confirm that GANs enable the generation of synthetic malware samples that can be used to mislead a classification model.

Źródło:

Cybersecurity and Law; 2023, 9, 1; 61-72
2658-1493

Pojawia się w:

Cybersecurity and Law

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 42.

Tytuł:

Deep features extraction for robust fingerprint spoofing attack detection

Autorzy:

Souza de, Gustavo Botelho
Silva Santos da, Daniel Felipe
Gonçalves Pires, Rafael
Nilceu Marana, Aparecido
Paulo Papa, Joao

Powiązania:

https://bibliotekanauki.pl/articles/91725.pdf

Data publikacji:

2019

Wydawca:

Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych

Tematy:

restricted Boltzmann Machines
Deep Boltzmann Machines
deep learning
fingerprint spoofing detection
biometrics

Opis:

Biometric systems have been widely considered as a synonym of security. However, in recent years, malicious people are violating them by presenting forged traits, such as gelatin fingers, to fool their capture sensors (spoofing attacks). To detect such frauds, methods based on traditional image descriptors have been developed, aiming liveness detection from the input data. However, due to their handcrafted approaches, most of them present low accuracy rates in challenging scenarios. In this work, we propose a novel method for fingerprint spoofing detection using the Deep Boltzmann Machines (DBM) for extraction of high-level features from the images. Such deep features are very discriminative, thus making complicated the task of forgery by attackers. Experiments show that the proposed method outperforms other state-of-the-art techniques, presenting high accuracy regarding attack detection

Źródło:

Journal of Artificial Intelligence and Soft Computing Research; 2019, 9, 1; 41-49
2083-2567
2449-6499

Pojawia się w:

Journal of Artificial Intelligence and Soft Computing Research

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 43.

Tytuł:

Power-Ground Plane Impedance Modeling Using Deep Neural Networks and an Adaptive Sampling Process

Autorzy:

Goay, Chan Hong
Cheong, Zheng Quan
Low, Chen En
Ahmad, Nur Syazreen
Goh, Patrick

Powiązania:

https://bibliotekanauki.pl/articles/2200709.pdf

Data publikacji:

2022

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

adaptive sampling
deep neural networks
deep learning
power-ground plane
Z-parameters

Opis:

This paper proposes a deep neural network (DNN) based method for the purpose of power-ground plane impedance modeling. A composite DNN model, which is a combination of two DNNs is used to predict the Z-parameters of power ground planes from their design parameters. The first DNN predicts the normalized Z-parameters whereas the second DNN predicts the original maximum and minimum values of the nonnormalized Z-parameters. This allows the method to retain a high accuracy when predicting responses that have large variations across designs, as is the case with the Z-parameters of the power-ground planes. We use the adaptive sampling algorithm to generate the training and validation samples for the DNNs. The adaptive sampling algorithm starts with only a few samples, then slowly generates more samples in the non-linear regions within the design parameters space. The level of non-linearity of the regions is determined by a surrogate model which is also trained using the generated samples as well. If the surrogate model has poor prediction accuracy in a region, then the adaptive sampling algorithm will generate more samples in that region. A shallow neural network is used as the surrogate model for non-linearity determination of the regions since it is faster to train and update. Once all the samples have been generated, they will be used to train and validate the composite DNN models. Finally, we present two examples, a square-shaped power ground plane and a squareshaped power ground plane with a hollow square at the center to demonstrate the robustness of the DNN composite models.

Źródło:

International Journal of Electronics and Telecommunications; 2022, 68, 4; 793--798
2300-1933

Pojawia się w:

International Journal of Electronics and Telecommunications

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 44.

Tytuł:

Classification of Parkinsons disease in brain MRI images using Deep Residual Convolutional Neural Network (DRCNN)

Autorzy:

Praneeth, Puppala
Sathvika, Majety
Kommareddy, Vivek
Sarath, Madala
Mallela, Saran
Vani, K. Suvarna
Chkrabarti, Prasun

Powiązania:

https://bibliotekanauki.pl/articles/30148251.pdf

Data publikacji:

2023

Wydawca:

Polskie Towarzystwo Promocji Wiedzy

Tematy:

Parkinson’s disease
Deep Residual Convolutional Neural Network
deep learning
health control

Opis:

In our aging culture, neurodegenerative disorders like Parkinson's disease (PD) are among the most serious health issues. It is a neurological condition that has social and economic effects on individuals. It happens because the brain's dopamine-producing cells are unable to produce enough of the chemical to support the body's motor functions. The main symptoms of this illness are eyesight, excretion activity, speech, and mobility issues, followed by depression, anxiety, sleep issues, and panic attacks. The main aim of this research is to develop a workable clinical decision-making framework that aids the physician in diagnosing patients with PD influence. In this research, the authors propose a technique to classify Parkinson’s disease by MRI brain images. Initially, the input data is normalized using the min-max normalization method, and then noise is removed from the input images using a median filter. The Binary Dragonfly algorithm is then used to select features. In addition, the Dense-UNet technique is used to segment the diseased part from brain MRI images. The disease is then classified as Parkinson's disease or health control using the Deep Residual Convolutional Neural Network (DRCNN) technique along with the Enhanced Whale Optimization Algorithm (EWOA) to achieve better classification accuracy. In this work, the Parkinson's Progression Marker Initiative (PPMI) public dataset for Parkinson's MRI images is used. Indicators of accuracy, sensitivity, specificity and precision are used with manually collected data to evaluate the effectiveness of the proposed methodology.

Źródło:

Applied Computer Science; 2023, 19, 2; 125-146
1895-3735
2353-6977

Pojawia się w:

Applied Computer Science

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 45.

Tytuł:

Deep learning-based framework for tumour detection and semantic segmentation

Autorzy:

Kot, Estera
Krawczyk, Zuzanna
Siwek, Krzysztof
Królicki, Leszek
Czwarnowski, Piotr

Powiązania:

https://bibliotekanauki.pl/articles/2128156.pdf

Data publikacji:

2021

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

deep learning
medical imaging
tumour detection
semantic segmentation
image fusion
technika deep learning
głęboka nauka
obrazowanie medyczne
wykrywanie guza
segmentacja semantyczna
połączenie obrazu

Opis:

For brain tumour treatment plans, the diagnoses and predictions made by medical doctors and radiologists are dependent on medical imaging. Obtaining clinically meaningful information from various imaging modalities such as computerized tomography (CT), positron emission tomography (PET) and magnetic resonance (MR) scans are the core methods in software and advanced screening utilized by radiologists. In this paper, a universal and complex framework for two parts of the dose control process – tumours detection and tumours area segmentation from medical images is introduced. The framework formed the implementation of methods to detect glioma tumour from CT and PET scans. Two deep learning pre-trained models: VGG19 and VGG19-BN were investigated and utilized to fuse CT and PET examinations results. Mask R-CNN (region-based convolutional neural network) was used for tumour detection – output of the model is bounding box coordinates for each object in the image – tumour. U-Net was used to perform semantic segmentation – segment malignant cells and tumour area. Transfer learning technique was used to increase the accuracy of models while having a limited collection of the dataset. Data augmentation methods were applied to generate and increase the number of training samples. The implemented framework can be utilized for other use-cases that combine object detection and area segmentation from grayscale and RGB images, especially to shape computer-aided diagnosis (CADx) and computer-aided detection (CADe) systems in the healthcare industry to facilitate and assist doctors and medical care providers.

Źródło:

Bulletin of the Polish Academy of Sciences. Technical Sciences; 2021, 69, 3; e136750, 1--7
0239-7528

Pojawia się w:

Bulletin of the Polish Academy of Sciences. Technical Sciences

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 46.

Tytuł:

Bearing fault detection and diagnosis based on densely connected convolutional networks

Autorzy:

Niyongabo, Julius
Zhang, Yingjie
Ndikumagenge, Jérémie

Powiązania:

https://bibliotekanauki.pl/articles/2105995.pdf

Data publikacji:

2022

Wydawca:

Politechnika Białostocka. Oficyna Wydawnicza Politechniki Białostockiej

Tematy:

bearing
deep learning
machine learning
transfer learning
fault detection
fault diagnosis
CWRU dataset

Opis:

Rotating machines are widely used in today’s world. As these machines perform the biggest tasks in industries, faults are naturally observed on their components. For most rotating machines such as wind turbine, bearing is one of critical components. To reduce failure rate and increase working life of rotating machinery it is important to detect and diagnose early faults in this most vulner-able part. In the recent past, technologies based on computational intelligence, including machine learning (ML) and deep learning (DL), have been efficiently used for detection and diagnosis of bearing faults. However, DL algorithms are being increasingly favoured day by day because of their advantages of automatically extracting features from training data. Despite this, in DL, adding neural layers reduces the training accuracy and the vanishing gradient problem arises. DL algorithms based on convolutional neural networks (CNN) such as DenseNet have proved to be quite efficient in solving this kind of problem. In this paper, a transfer learning consisting of fine-tuning DenseNet-121 top layers is proposed to make this classifier more robust and efficient. Then, a new intelligent model inspired by DenseNet-121 is designed and used for detecting and diagnosing bearing faults. Continuous wavelet transform is applied to enhance the dataset. Experimental results obtained from analyses employing the Case Western Reserve University (CWRU) bearing dataset show that the proposed model has higher diagnostic performance, with 98% average accuracy and less complexity.

Źródło:

Acta Mechanica et Automatica; 2022, 16, 2; 130--135
1898-4088
2300-5319

Pojawia się w:

Acta Mechanica et Automatica

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 47.

Tytuł:

A survey of big data classification strategies

Autorzy:

Banchhor, Chitrakant
Srinivasu, N.

Powiązania:

https://bibliotekanauki.pl/articles/2050171.pdf

Data publikacji:

2020

Wydawca:

Polska Akademia Nauk. Instytut Badań Systemowych PAN

Tematy:

big data
data mining
MapReduce
classification
machine learning
evolutionary intelligence
deep learning

Opis:

Big data plays nowadays a major role in finance, industry, medicine, and various other fields. In this survey, 50 research papers are reviewed regarding different big data classification techniques presented and/or used in the respective studies. The classification techniques are categorized into machine learning, evolutionary intelligence, fuzzy-based approaches, deep learning and so on. The research gaps and the challenges of the big data classification, faced by the existing techniques are also listed and described, which should help the researchers in enhancing the effectiveness of their future works. The research papers are analyzed for different techniques with respect to software tools, datasets used, publication year, classification techniques, and the performance metrics. It can be concluded from the here presented survey that the most frequently used big data classification methods are based on the machine learning techniques and the apparently most commonly used dataset for big data classification is the UCI repository dataset. The most frequently used performance metrics are accuracy and execution time.

Źródło:

Control and Cybernetics; 2020, 49, 4; 447-469
0324-8569

Pojawia się w:

Control and Cybernetics

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 48.

Tytuł:

Camera-based PHM method in rotating machinery equipment micro-action scenarios

Autorzy:

Junfeng, An
Liu, Jiqiang
Zhen, Hao
Mengmeng, Lu

Powiązania:

https://bibliotekanauki.pl/articles/24200809.pdf

Data publikacji:

2023

Wydawca:

Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN

Tematy:

deep learning
condition monitoring
Rmcad
anomaly detection
defect early warning

Opis:

The health operation of rotating machinery guarantees safety of the project. To ensure a good operating environment, current subway equipment inspections frequency is high, resulting in a waste of resources. Small abnormal changes in mechanical equipment will also contribute to the development of mechanical component defects, which will ultimately lead to the failure of the equipment. Therefore, mechanical equipment defects should be detected and diagnosed as soon as possible. Through the use of graphic processing and deep learning, this paper proposes Rmcad Framework with three aspects: condition monitoring, anomaly detection, defect early warning. Using a network algorithm, this paper proposes an improved model that has the characteristics of two-stream and multi-loss functions, which improves the accuracy of detection. Additionally, a defect warning method is constructed to improve the perception ability of equipment before failure occurs and reduce the frequency of frequent maintenance by detecting anomalies according to the degree of opening.

Źródło:

Eksploatacja i Niezawodność; 2023, 25, 1; art. no. 10
1507-2711

Pojawia się w:

Eksploatacja i Niezawodność

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 49.

Tytuł:

Research on Fault Diagnosis of Highway Bi-LSTM Based on Attention Mechanism

Autorzy:

Li, Xueyi
Su, Kaiyu
He, Qiushi
Wang, Xiangkai
Xie, Zhijie

Powiązania:

https://bibliotekanauki.pl/articles/24200832.pdf

Data publikacji:

2023

Wydawca:

Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN

Tematy:

fault diagnosis
Bi-LSTM
attention
highway
deep learning
Ball Bearing

Opis:

Deep groove ball bearings are widely used in rotary machinery. Accurate for bearing faults diagnosis is essential for equipment maintenance. For common depth learning methods, the feature extraction of inverse time domain signal direction and the attention to key features are usually ignored. Based on the long short term memory(LSTM) network, this study proposes an attention-based highway bidirectional long short term memory (AHBi-LSTM) network for fault diagnosis based on the raw vibration signal. By increasing the Attention mechanism and Highway, the ability of the network to extract features is increased. The bidirectional LSTM network simultaneously extracts the raw vibration signal in positive and inverse time-domains to better extract the fault features. Six deep groove ball bearings with different health conditions were used to validate the AHBi-LSTM method in an experiment. The results showed that the accuracy of the proposed method for bearing fault diagnosis was over 98%, which was 8.66% higher than that of the LSTM model. The AHBi-LSTM model is also better than other relevant models for bearing fault diagnosis.

Źródło:

Eksploatacja i Niezawodność; 2023, 25, 2; art. no. 162937
1507-2711

Pojawia się w:

Eksploatacja i Niezawodność

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 50.

Tytuł:

Career track prediction using deep learning model based on discrete series of quantitative classification

Autorzy:

Hernandez, Rowell
Atienza, Robert

Powiązania:

https://bibliotekanauki.pl/articles/1956033.pdf

Data publikacji:

2021

Wydawca:

Polskie Towarzystwo Promocji Wiedzy

Tematy:

track prediction
deep learning
education
przewidywanie torów
głębokie uczenie
edukacja

Opis:

In this paper, a career track recommender system was proposed using Deep Neural Network model. This study aims to assist guidance counselors in guiding their students in the selection of a suitable career track. It is because a lot of Junior High school students experienced track uncertainty and there are instances of shifting to another program after learning they are not suited for the chosen track or course in college. In dealing with the selection of the best student attributes that will help in the creation of the predictive model, the feature engineering technique is used to remove the irrelevant features that can affect the performance of the DNN model. The study covers 1500 students from the first to the third batch of the K-12 curriculum, and their grades from 11 subjects, sex, age, number of siblings, parent’s income, and academic strand were used as attributes to predict their academic strand in Senior High School. The efficiency and accuracy of the algorithm depend upon the correctness and quality of the collected student’s data. The result of the study shows that the DNN algorithm performs reasonably well in predicting the academic strand of students with a predic-tion accuracy of 83.11%. Also, the work of guidance counselors became more efficient in handling students’ concerns just by using the proposed system. It is concluded that the recommender system serves as a decision tool for counselors in guiding their stu-dents to determine which Senior High School track is suitable for students with the utilization of the DNN model.

Źródło:

Applied Computer Science; 2021, 17, 4; 55-74
1895-3735

Pojawia się w:

Applied Computer Science

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 51.

Tytuł:

Deep learning: theory and practice

Autorzy:

Cichocki, A.
Poggio, T.
Osowski, S.
Lempitsky, V.

Powiązania:

https://bibliotekanauki.pl/articles/202346.pdf

Data publikacji:

2018

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

deep learning
networks
theory
practice
uczenie głębokie
sieci
teoria
praktyka

Opis:

This Special Section of the Bulletin of the Polish Academy of Sciences on Technical Sciences is devoted to theoretical aspects of deep machine learning as well as practical applications in some areas of signal and image processing, particularly in bioengineering.

Źródło:

Bulletin of the Polish Academy of Sciences. Technical Sciences; 2018, 66, 6; 757-759
0239-7528

Pojawia się w:

Bulletin of the Polish Academy of Sciences. Technical Sciences

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 52.

Tytuł:

Deep learning-based framework for tumour detection and semantic segmentation

Autorzy:

Kot, Estera
Krawczyk, Zuzanna
Siwek, Krzysztof
Królicki, Leszek
Czwarnowski, Piotr

Powiązania:

https://bibliotekanauki.pl/articles/2173573.pdf

Data publikacji:

2021

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

deep learning
medical imaging
tumour detection
semantic segmentation
image fusion
technika deep learning
głęboka nauka
obrazowanie medyczne
wykrywanie guza
segmentacja semantyczna
połączenie obrazu

Opis:

For brain tumour treatment plans, the diagnoses and predictions made by medical doctors and radiologists are dependent on medical imaging. Obtaining clinically meaningful information from various imaging modalities such as computerized tomography (CT), positron emission tomography (PET) and magnetic resonance (MR) scans are the core methods in software and advanced screening utilized by radiologists. In this paper, a universal and complex framework for two parts of the dose control process – tumours detection and tumours area segmentation from medical images is introduced. The framework formed the implementation of methods to detect glioma tumour from CT and PET scans. Two deep learning pre-trained models: VGG19 and VGG19-BN were investigated and utilized to fuse CT and PET examinations results. Mask R-CNN (region-based convolutional neural network) was used for tumour detection – output of the model is bounding box coordinates for each object in the image – tumour. U-Net was used to perform semantic segmentation – segment malignant cells and tumour area. Transfer learning technique was used to increase the accuracy of models while having a limited collection of the dataset. Data augmentation methods were applied to generate and increase the number of training samples. The implemented framework can be utilized for other use-cases that combine object detection and area segmentation from grayscale and RGB images, especially to shape computer-aided diagnosis (CADx) and computer-aided detection (CADe) systems in the healthcare industry to facilitate and assist doctors and medical care providers.

Źródło:

Bulletin of the Polish Academy of Sciences. Technical Sciences; 2021, 69, 3; art. no. e136750
0239-7528

Pojawia się w:

Bulletin of the Polish Academy of Sciences. Technical Sciences

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 53.

Tytuł:

A Comprehensive study: - Sarcasm detection in sentimental analysis

Autorzy:

Ratawal, Yamini
Tayal, Devendra

Powiązania:

https://bibliotekanauki.pl/articles/1159725.pdf

Data publikacji:

2018

Wydawca:

Przedsiębiorstwo Wydawnictw Naukowych Darwin / Scientific Publishing House DARWIN

Tematy:

Sentimental analysis
Web mining
deep learning
machine learning
opinion mining
text mining

Opis:

Sarcasm detection is one of the active research area in sentimental analysis. However this paper talks about one of the recent issue in sentimental analysis that us sarcasm detection. In our work, we have described different techniques used in sarcasm detection that helps a novice researcher in efficient way. This paper represent different methodologies of carrying out research in this field.

Źródło:

World Scientific News; 2018, 113; 1-9
2392-2192

Pojawia się w:

World Scientific News

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 54.

Tytuł:

Deep Image Features in Music Information Retrieval

Autorzy:

Gwardys, G.
Grzywczak, D.

Powiązania:

https://bibliotekanauki.pl/articles/226400.pdf

Data publikacji:

2014

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

music information retrieval
deep learning
genre classification
convolutional neural networks
transfer learning

Opis:

Applications of Convolutional Neural Networks (CNNs) to various problems have been the subject of a number of recent studies ranging from image classification and object detection to scene parsing, segmentation 3D volumetric images and action recognition in videos. CNNs are able to learn input data representation, instead of using fixed engineered features. In this study, the image model trained on CNN were applied to a Music Information Retrieval (MIR), in particular to musical genre recognition. The model was trained on ILSVRC-2012 (more than 1 million natural images) to perform image classification and was reused to perform genre classification using spectrograms images. Harmonic/percussive separation was applied, because it is characteristic for musical genre. At final stage, the evaluation of various strategies of merging Support Vector Machines (SVMs) was performed on well known in MIR community - GTZAN dataset. Even though, the model was trained on natural images, the results achieved in this study were close to the state-of-the-art.

Źródło:

International Journal of Electronics and Telecommunications; 2014, 60, 4; 321-326
2300-1933

Pojawia się w:

International Journal of Electronics and Telecommunications

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 55.

Tytuł:

An efficient pedestrian attribute recognition system under challenging conditions

Autorzy:

Nguyen, Ha X.
Hoang, Dong N.
Tran, Tuan A.
Dang, Tuan M.

Powiązania:

https://bibliotekanauki.pl/articles/24200444.pdf

Data publikacji:

2023

Wydawca:

Szkoła Główna Gospodarstwa Wiejskiego w Warszawie. Instytut Informatyki Technicznej

Tematy:

pedestrian attribute recognition
Deep Learning
vision transformer
security surveil-lance

Opis:

In this work, an efficient pedestrian attribute recognition system is introduced. The system is based on a novel processing pipeline that combines the best-performing attribute extraction model with an efficient attribute filtering algorithm using keypoints of human pose. The attribute extraction models are developed based on several state-of-the-art deep networks via transfer learning techniques, including ResNet50, Swin-transformer, and ConvNeXt. Pre-trained models of these networks are fine-tuned using the Ensemble Pedestrian Attribute Recognition (EPAR) dataset. Several optimization techniques, including the advanced optimizer Adam with Decoupled Weight Decay Regularization (AdamW), Random Erasing (RE), and weighted loss functions, are adopted to solve issues of data unbalancing or challenging conditions like partial and occluded bodies. Experimental evaluations are performed via EPAR that contains 26 993 images of 1477 person IDs, most of which are in challenging conditions. The results show that the ConvNeXt-v2-B outperforms other networks; mean accuracy (mA) reaches 85.57%, and other indices are also the highest. The addition of AdamW or RE can improve accuracy by 1-2%. The use of new loss functions can solve the issue of data unbalancing, in which the accuracy of data-less attributes improves by a maximum of 14% in the best case. Significantly, when the attribute filtering algorithm is applied, the results are dramatically improved, and mA reaches an excellent value of 94.85%. Utilizing the state-of-the-art attribute extraction model with optimization techniques on the large-scale and diverse dataset and attribute filtering has shown a good approach and thus has a high potential for practical applications.

Źródło:

Machine Graphics & Vision; 2023, 32, 2; 3--18
1230-0535
2720-250X

Pojawia się w:

Machine Graphics & Vision

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 56.

Tytuł:

Evolutionary data driven modelling and many objective optimization of non linear noisy data in the blast furnace iron making process

Autorzy:

Mahanta, Bashista Kumar
Chakraborti, Nirupam

Powiązania:

https://bibliotekanauki.pl/articles/29520226.pdf

Data publikacji:

2021

Wydawca:

Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH

Tematy:

deep learning
reference vector
neural net
genetic programming
blast furnace

Opis:

Optimization of process parameters in modern blast furnace operation, where both control and accessing large data set with multiple variables and objectives is a challenging task. To handle such non-linear and noisy data set deep learning techniques have been used in recent time. In this study an evolutionary deep neural network algorithm (EvoDN2) has been applied to derive a data driven model for blast furnace. The optimal front generated from deep neural network is compared against the optimal models developed from bi-objective genetic programming algorithm (BioGP) and evolutionary neural network (EvoNN). The optimization process is applied to all the training models by using constraint based reference vector evolutionary algorithm (cRVEA).

Źródło:

Computer Methods in Materials Science; 2021, 21, 3; 163-175
2720-4081
2720-3948

Pojawia się w:

Computer Methods in Materials Science

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 57.

Tytuł:

Learning-free deep features for multispectral palm-print classification

Autorzy:

Aounallah, Asma
Meraoumia, Abdallah
Bendjenna, Hakim

Powiązania:

https://bibliotekanauki.pl/articles/27312870.pdf

Data publikacji:

2023

Wydawca:

Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH

Tematy:

feature extraction
biometrics
multispectral imaging
deep learning
DCTNet
data fusion

Opis:

The feature-extraction step is a major and crucial step in analyzing and understanding raw data, as it has a considerable impact on system accuracy. Despite the very acceptable results that have been obtained by many handcrafted methods, these can unfortunately have difficulty representing features in the cases of large databases or with strongly correlated samples. In this context, we attempt to examine the discriminability of texture features by proposing a novel, simple, and lightweight method for deep feature extraction to characterize the discriminative power of different textures. We evaluated the performance of our method by using a palm print-based biometric system, and the experimental results (using the CASIA multispectral palm--print database) demonstrate the superiority of the proposed method over the latest handcrafted and deep methods.

Źródło:

Computer Science; 2023, 24 (2); 243--271
1508-2806
2300-7036

Pojawia się w:

Computer Science

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 58.

Tytuł:

Deep learning method for classifying items into categories for dutch auctions

Autorzy:

Bobulski, Janusz
Szymoniak, Sabina

Powiązania:

https://bibliotekanauki.pl/articles/38707060.pdf

Data publikacji:

2024

Wydawca:

Instytut Podstawowych Problemów Techniki PAN

Tematy:

deep learning
internet auction
classification
głęboka nauka
aukcja internetowa
klasyfikacja

Opis:

Artificial Intelligence (AI) methods are widely used in our lives (phones, social media, self-driving cars, and e-commerce). In AI methods, we can find convolutional neural networks (CNN). First of all, we can use these networks to analyze images. This paper presents a method for classifying items into particular categories on an auction site. The technique prompts the seller to which category assign the item when creating a new auction. We choose a neural network with a number of image convolution layers as the best available approach to address this task. All tests were carried out in the Matlab environment using GPU and CPU. Then, the tested and verified solution was implemented in the TensorFlow environment with a CPU processor. Thanks to the cross-validation method, the effectiveness of the recognition system was fully verified in several stages. We obtained promising results. Consequently, we implemented the developed method by adding a new sales offer on the Clemens website.

Źródło:

Computer Assisted Methods in Engineering and Science; 2024, 31, 1; 67-79
2299-3649

Pojawia się w:

Computer Assisted Methods in Engineering and Science

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 59.

Tytuł:

Convolutional Neural Networks for C. Elegans Muscle Age Classification Using Only Self-learned Features

Autorzy:

Czaplewski, Bartosz
Dzwonkowski, Mariusz
Panas, Damian

Powiązania:

https://bibliotekanauki.pl/articles/2176172.pdf

Data publikacji:

2022

Wydawca:

Instytut Łączności - Państwowy Instytut Badawczy

Tematy:

biomedical imaging
C. elegans muscle aging
convolutional neural networks
deep learning
machine learning

Opis:

Nematodes Caenorhabditis elegans (C. elegans) have been used as model organisms in a wide variety of biological studies, especially those intended to obtain a better understanding of aging and age-associated diseases. This paper focuses on automating the analysis of C. elegans imagery to classify the muscle age of nematodes based on the known and well established IICBU dataset. Unlike many modern classification methods, the proposed approach relies on deep learning techniques, specifically on convolutional neural networks (CNNs), to solve the problem and achieve high classification accuracy by focusing on non-handcrafted self-learned features. Various networks known from the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) have been investigated and adapted for the purposes of the C. elegans muscle aging dataset by applying transfer learning and data augmentation techniques. The proposed approach of unfreezing different numbers of convolutional layers at the feature extraction stage and introducing different structures of newly trained fully connected layers at the classification stage, enable to better fine-tune the selected networks. The adjusted CNNs, as featured in this paper, have been compared with other state-of-art methods. In anti-aging drug research, the proposed CNNs would serve as a very fast and effective age determination method, thus leading to reductions in time and costs of laboratory research.

Źródło:

Journal of Telecommunications and Information Technology; 2022, 4; 85--94
1509-4553
1899-8852

Pojawia się w:

Journal of Telecommunications and Information Technology

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 60.

Tytuł:

Multi agent deep learning with cooperative communication

Autorzy:

Simões, David
Lau, Nuno
Reis, Luís Paulo

Powiązania:

https://bibliotekanauki.pl/articles/1837537.pdf

Data publikacji:

2020

Wydawca:

Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych

Tematy:

multi-agent systems
deep reinforcement learning
centralized learning

Opis:

We consider the problem of multi agents cooperating in a partially-observable environment. Agents must learn to coordinate and share relevant information to solve the tasks successfully. This article describes Asynchronous Advantage Actor-Critic with Communication (A3C2), an end-to-end differentiable approach where agents learn policies and communication protocols simultaneously. A3C2 uses a centralized learning, distributed execution paradigm, supports independent agents, dynamic team sizes, partiallyobservable environments, and noisy communications. We compare and show that A3C2 outperforms other state-of-the-art proposals in multiple environments.

Źródło:

Journal of Artificial Intelligence and Soft Computing Research; 2020, 10, 3; 189-207
2083-2567
2449-6499

Pojawia się w:

Journal of Artificial Intelligence and Soft Computing Research

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 61.

Tytuł:

New model of photovoltaic system adapted by a digital MPPT control and radiation predictions using deep learning in Morocco agricultural sector

Autorzy:

Zouhri, Amal
El Mallahi, Mostafa

Powiązania:

https://bibliotekanauki.pl/articles/27314237.pdf

Data publikacji:

2023

Wydawca:

Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów

Tematy:

Morocco sustainable development
solar pumping
Deep Learning
renewable energies
solar radiation

Opis:

Solar energy is an essential factor in Moroccan sustainable development, especially in solar pumping in the agricultural sector. It is therefore difficult to dissociate the energy system of a society from its economic development and social development. Solar radiation prediction is useful in giving us a global overview on maintaining the integrity of solar systems. Access to database use makes this process more flexible. Solar forecasts can be generated using various available data sources. There are two major pillars of this data: the exploitation of historical solar radiation data, and the exploitation of other meteorological factors. On the other hand, the choice of data can have an impact on the choice of the model and the approach employed. In this paper we suggest an idea that aims to monitor in real time the situation of solar radiation in Morocco, using Long Short‐Term Memory for deep learning models compared with Artificial Neural Networks and Deep Neural Networks to predict the solar radiation with regard to solar pumping in the Moroccan agricultural sector.

Źródło:

Journal of Automation Mobile Robotics and Intelligent Systems; 2023, 17, 2; 74--84
1897-8649
2080-2145

Pojawia się w:

Journal of Automation Mobile Robotics and Intelligent Systems

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 62.

Tytuł:

Optimization of convolutional neural networks using the fuzzy gravitational search algorithm

Autorzy:

Poma, Yutzil
Melin, Patricia
González, Claudia I.
Martínez, Gabriela E.

Powiązania:

https://bibliotekanauki.pl/articles/384794.pdf

Data publikacji:

2020

Wydawca:

Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów

Tematy:

neural networks
convolutional neural network
fuzzy gravitational search algorithm
deep learning

Opis:

This paper presents an approach to optimize a Convolutional Neural Network using the Fuzzy Gravitational Search Algorithm. The optimized parameters are the number of images per block that are used in the training phase, the number of filters and the filter size of the convolutional layer. The reason for optimizing these parameters is because they have a great impact on performance of the Convolutional Neural Networks. The neural network model presented in this work can be applied for any image recognition or classification applications; nevertheless, in this paper, the experiments are performed in the ORL and Cropped Yale databases. The results are compared with other neural networks, such as modular and monolithic neural networks. In addition, the experiments were performed manually, and the results were obtained (when the neural network is not optimized), and comparison was made with the optimized results to validate the advantage of using the Fuzzy Gravitational Search Algorithm.

Źródło:

Journal of Automation Mobile Robotics and Intelligent Systems; 2020, 14, 1; 109-120
1897-8649
2080-2145

Pojawia się w:

Journal of Automation Mobile Robotics and Intelligent Systems

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 63.

Tytuł:

Subpixel localization of optical vortices using artificial neural networks

Autorzy:

Popiołek-Masajada, Agnieszka
Frączek, Ewa
Burnecka, Emilia

Powiązania:

https://bibliotekanauki.pl/articles/1849005.pdf

Data publikacji:

2021

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

optical vortex
spiral phase map
pseudo phase
deep learning
neural network

Opis:

Optical vortices are getting attention in modern optical metrology. Because of their unique features, they can be used as precise position markers. In this paper, we show that an artificial neural network can be used to improve vortex localization. A deep neural network with several hidden layers was trained to find subpixel vortex positions on the spiral phase maps. Several thousand training samples, differing by spiral density, its orientation, and vortex position, were generated numerically for teaching purposes. As a result, Best Validation Performance of the order of 10-5 pixel has been reached. To verify the usefulness of the proposed method, a related experiment in the setup of an optical vortex scanning microscope has been reported. It is shown that the vortex can be localized with subpixel accuracy also on experimental phase maps.

Źródło:

Metrology and Measurement Systems; 2021, 28, 3; 497-508
0860-8229

Pojawia się w:

Metrology and Measurement Systems

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 64.

Tytuł:

Subpixel localization of optical vortices using artificial neural networks

Autorzy:

Popiołek-Masajada, Agnieszka
Frączek, Ewa
Burnecka, Emilia

Powiązania:

https://bibliotekanauki.pl/articles/1849096.pdf

Data publikacji:

2021

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

optical vortex
spiral phase map
pseudo phase
deep learning
neural network

Opis:

Optical vortices are getting attention in modern optical metrology. Because of their unique features, they can be used as precise position markers. In this paper, we show that an artificial neural network can be used to improve vortex localization. A deep neural network with several hidden layers was trained to find subpixel vortex positions on the spiral phase maps. Several thousand training samples, differing by spiral density, its orientation, and vortex position, were generated numerically for teaching purposes. As a result, Best Validation Performance of the order of 10-5 pixel has been reached. To verify the usefulness of the proposed method, a related experiment in the setup of an optical vortex scanning microscope has been reported. It is shown that the vortex can be localized with subpixel accuracy also on experimental phase maps.

Źródło:

Metrology and Measurement Systems; 2021, 28, 3; 497-508
0860-8229

Pojawia się w:

Metrology and Measurement Systems

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 65.

Tytuł:

Ensemble of classifiers based on deep learning for medical image recognition

Autorzy:

Gil, Fabian
Osowski, Stanisław
Świderski, Bartosz
Słowińska, Monika

Powiązania:

https://bibliotekanauki.pl/articles/2203370.pdf

Data publikacji:

2023

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

breast cancer
CNN
deep learning
ensemble of classifiers
feature selection
melanoma

Opis:

The paper presents special forms of an ensemble of classifiers for analysis of medical images based on application of deep learning. The study analyzes different structures of convolutional neural networks applied in the recognition of two types of medical images: dermoscopic images for melanoma and mammograms for breast cancer. Two approaches to ensemble creation are proposed. In the first approach, the images are processed by a convolutional neural network and the flattened vector of image descriptors is subjected to feature selection by applying different selection methods. As a result, different sets of a limited number of diagnostic features are generated. In the next stage, these sets of features represent input attributes for the classical classifiers: support vector machine, a random forest of decision trees, and softmax. By combining different selection methods with these classifiers an ensemble classification system is created and integrated by majority voting. In the second approach, different structures of convolutional neural networks are directly applied as the members of the ensemble. The efficiency of the proposed classification systems is investigated and compared to medical data representing dermoscopic images of melanoma and breast cancer mammogram images. Thanks to fusion of the results of many classifiers forming an ensemble, accuracy and all other quality measures have been significantly increased for both types of medical images.

Źródło:

Metrology and Measurement Systems; 2023, 30, 1; 139--156
0860-8229

Pojawia się w:

Metrology and Measurement Systems

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 66.

Tytuł:

Story Point Estimation Using Issue Reports With Deep Attention Neural Network

Autorzy:

Kassem, Haithem
Mahar, Khaled
Saad, Amani A.

Powiązania:

https://bibliotekanauki.pl/articles/2203950.pdf

Data publikacji:

2023

Wydawca:

Politechnika Wrocławska. Oficyna Wydawnicza Politechniki Wrocławskiej

Tematy:

story points
deep learning
glove
hierarchical attention networks
agile
planning poker

Opis:

Background: Estimating the effort required for software engineering tasks is incredibly tricky, but it is critical for project planning. Issue reports are frequently used in the agile community to describe tasks, and story points are used to estimate task effort. Aim: This paper proposes a machine learning regression model for estimating the number of story points needed to solve a task. The system can be trained from raw input data to predict outcomes without the need for manual feature engineering. Method: Hierarchical attention networks are used in the proposed model. It has two levels of attention mechanisms implemented at word and sentence levels. The model gradually constructs a document vector by grouping significant words into sentence vectors and then merging significant sentence vectors to create document vectors. Then, the document vectors are fed into a shallow neural network to predict the story point. Results: The experiments show that the proposed approach outperforms the state-of-the-art technique Deep-S which uses Recurrent Highway Networks. The proposed model has improved Mean Absolute Error (MAE) by an average of 16.6% and has improved Median Absolute Error (MdAE) by an average of 53%. Conclusion: An empirical evaluation shows that the proposed approach outperforms the previous work.

Źródło:

e-Informatica Software Engineering Journal; 2023, 17, 1; art. no. 230104
1897-7979

Pojawia się w:

e-Informatica Software Engineering Journal

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 67.

Tytuł:

A Robust CNN Model for Diagnosis of COVID-19 Based on CT Scan Images and DL Techniques

Autorzy:

Eldeeb, Ahmed H.
Amr, Mohammed Nagah
Ibrahim, Amin S.
Kamel, Hesham
Fouad, Sara

Powiązania:

https://bibliotekanauki.pl/articles/2200729.pdf

Data publikacji:

2022

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

Deep learning
COVID-19
Artificial Intelligence
computed tomography
Convolutional Neural Networks

Opis:

The 2019 Coronavirus (COVID-19) virus has caused damage on people's respiratory systems over the world. Computed Tomography (CT) is a faster complement for RT-PCR during peak virus spread times. Nowadays, Deep Learning (DL) with CT provides more robust and reliable methods for classifying patterns in medical pictures. In this paper, we proposed a simple low training proposed customized Convolutional Neural Networks (CNN) customized model based on CNN architecture that layers which are optionals may be included such as the layer of batch normalization to reduce time taken for training and a layer with a dropout to deal with overfitting. We employed a huge dataset of chest CT slices images from diverse sources COVIDx-CT, which consists of a 16,146-image dataset with 810 patients of various nationalities. The proposed customized model's classification results compared to the VGG-16, Alex Net, and ResNet50 Deep Learning models. The proposed CNN model shows robustness by achieving an overall accuracy of 93% compared to 88%, 89%, and 95% for the VGG-16, Alex Net, and ResNet50 DL models for the classification of 3 classes. When this relates to binary classification, the classification accuracy of the proposed model and the VGG-16 models were identical (almost 100% accurate), with 0.17% of misclassification in the class of Non-Covid-19, the Alex Net model achieved almost 100% classification accuracy with 0.33% misclassification in the class of Non-Covid-19. Finally, ResNet50 achieved 95% classification accuracy with 5% misclassification in the Non-Covid-19 class.

Źródło:

International Journal of Electronics and Telecommunications; 2022, 68, 4; 731--739
2300-1933

Pojawia się w:

International Journal of Electronics and Telecommunications

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 68.

Tytuł:

Lexicon and attention based handwritten text recognition system

Autorzy:

Kumari, Lalita
Singh, Sukhdeep
Rathore, Vaibhav Varish Singh
Sharma, Anuj

Powiązania:

https://bibliotekanauki.pl/articles/2201262.pdf

Data publikacji:

2022

Wydawca:

Szkoła Główna Gospodarstwa Wiejskiego w Warszawie. Instytut Informatyki Technicznej

Tematy:

handwriting recognition
deep learning
word beam search
attention
neural network
lexicon

Opis:

The handwritten text recognition problem is widely studied by the researchers of computer vision community due to its scope of improvement and applicability to daily lives. It is a sub-domain of pattern recognition. Due to advancement of computational power of computers since last few decades neural networks based systems heavily contributed towards providing the state-of-the-art handwritten text recognizers. In the same direction, we have taken two state-of-the art neural networks systems and merged the attention mechanism with it. The attention technique has been widely used in the domain of neural machine translations and automatic speech recognition and now is being implemented in text recognition domain. In this study, we are able to achieve 4.15% character error rate and 9.72% word error rate on IAM dataset, 7.07% character error rate and 16.14% word error rate on GW dataset after merging the attention and word beam search decoder with existing Flor et al. architecture. To analyse further, we have also used system similar to Shi et al. neural network system with greedy decoder and observed 23.27% improvement in character error rate from the base model.

Źródło:

Machine Graphics & Vision; 2022, 31, 1/4; 75--92
1230-0535
2720-250X

Pojawia się w:

Machine Graphics & Vision

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 69.

Tytuł:

Distance estimation using artificial neural networks: architectures, capabilities and limitations

Autorzy:

Hachaj, Tomasz

Powiązania:

https://bibliotekanauki.pl/articles/51459494.pdf

Data publikacji:

2023

Wydawca:

Uniwersytet Komisji Edukacji Narodowej w Krakowie. Instytut Filozofii i Socjologii

Tematy:

single-frame depth estimation
encoder-decoder
deep learning
typical errors
limitations

Opis:

The ability to judge distances using vision is an extremely important skill that greatly facilitates exploration of one’s immediate environment. Most commonly, spatial vision is associated with stereo vision. Although human eyes also act as a stereo vision system, we can perform a simple experiment by covering one eye and then look at our surroundings: even though we are now observing the world through a single “sensor” we can still judge which objects are closer and which are further away. Though we can also employ a slight change in viewing perspective to improve our sense of distance, this is not necessary and using even one eye and standing still we are able, through the experience we have gained, to correctly estimate the distances between the objects we can see. Also when we look at photographs although the images are two-dimensional, we are able to estimate the distance portrayed in them. In recent years many solutions based on machine learning methods and deep neural networks have been developed that can mimic this process. In particular, encoder-decoder architectures are effective in this task which allows a robot single-frame depth estimation. However, these solutions still have some limitations, which constitute a challenge for researchers and engineers. This paper will discuss the challenges faced by such architectures based on the author’s experience in the practice of developing deep learning-based single-frame depth estimation algorithms.

Źródło:

ARGUMENT: Biannual Philosophical Journal; 2023, 13, 1; 13-28
2083-6635
2084-1043

Pojawia się w:

ARGUMENT: Biannual Philosophical Journal

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 70.

Tytuł:

Lithuanian undergraduate students approaches to learning English for Specific Purposes

Autorzy:

Burkšaitienė, Nijolė
Šliogerienė, Jolita

Powiązania:

https://bibliotekanauki.pl/articles/1366437.pdf

Data publikacji:

2021-06-17

Wydawca:

Fundacja Pro Scientia Publica

Tematy:

approach to learning
deep learning
surface leaning
English for Specific Purposes
higher education

Opis:

Aim. It has been established by research that the nature of students’ learning is closely related to their approach to learning and to the learning environment in which learning occurs. In higher education environments, students’ approaches to learning have been widely investigated across different fields of study, however, little known research has focused on students’ approaches to learning foreign languages. To contribute to knowledge in this field, the present research aims to establish undergraduate students’ approaches to learning English for Specific purposes (ESP) at a university in Lithuania. Method. The research was conducted with the participation of 111 undergraduate students, majors in 11 different study programmes, who took a mandatory course in ESP. The data were collected from the structured questionnaires; to carry out the research, quantitative methodology was used. Results.  The analysis of students’ engagement in the study activities, their willingness to go beyond the task and their ability to self-regulate their learning revealed that the study participants demonstrated both surface approach and deep approach to learning ESP. Conclusion. The results indicate that to guide the students towards deep approach to learning ESP at the university, their engagement in study activities should be fostered. 

Źródło:

Journal of Education Culture and Society; 2021, 12, 1; 469-477
2081-1640

Pojawia się w:

Journal of Education Culture and Society

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 71.

Tytuł:

Convolutional neural networks for P300 signal detection applied to brain computer interface

Autorzy:

Riyad, Mouad
Khalil, Mohammed
Adib, Abdellah

Powiązania:

https://bibliotekanauki.pl/articles/2141900.pdf

Data publikacji:

2020

Wydawca:

Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów

Tematy:

deep learning
convolutional neural network
brain computer interface
P300
classification

Opis:

A Brain‐Computer Interface (BCI) is an instrument capa‐ ble of commanding machine with brain signal. The mul‐ tiple types of signals allow designing many applications like the Oddball Paradigms with P300 signal. We propose an EEG classification system applied to BCI using the con‐ volutional neural network (ConvNet) for P300 problem. The system consists of three stages. The first stage is a Spatiotemporal convolutional layer which is a succession of temporal and spatial convolutions. The second stage contains 5 standard convolutional layers. Finally, a lo‐ gistic regression is applied to classify the input EEG sig‐ nal. The model includes Batch Normalization, Dropout, and Pooling. Also, It uses Exponential Linear Unit (ELU) function and L1‐L2 regularization to improve the lear‐ ning. For experiments, we use the database Dataset II of the BCI Competition III. As a result, we get an F1‐score of 53.26% which is higher than the BN3 model.

Źródło:

Journal of Automation Mobile Robotics and Intelligent Systems; 2020, 14, 4; 58-63
1897-8649
2080-2145

Pojawia się w:

Journal of Automation Mobile Robotics and Intelligent Systems

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 72.

Tytuł:

Towards textual data augmentation for neural networks: synonyms and maximum loss

Autorzy:

Jungiewicz, Michał
Smywiński-Pohl, Aleksander

Powiązania:

https://bibliotekanauki.pl/articles/305750.pdf

Data publikacji:

2019

Wydawca:

Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH

Tematy:

deep learning
data augmentation
neural networks
natural language processing
sentence classification

Opis:

Data augmentation is one of the ways to deal with labeled data scarcity and overfitting. Both of these problems are crucial for modern deep-learning algorithms, which require massive amounts of data. The problem is better explored in the context of image analysis than for text; this work is a step forward to help close this gap. We propose a method for augmenting textual data when training convolutional neural networks for sentence classification. The augmentation is based on the substitution of words using a thesaurus as well as Princeton University's WordNet. Our method improves upon the baseline in most of the cases. In terms of accuracy, the best of the variants is 1.2% (pp.) better than the baseline.

Źródło:

Computer Science; 2019, 20 (1); 57-83
1508-2806
2300-7036

Pojawia się w:

Computer Science

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 73.

Tytuł:

A lightweight multi-person pose estimation scheme based on Jetson Nano

Autorzy:

Liu, Lei
Blancaflor, Eric B.
Abisado, Mideth

Powiązania:

https://bibliotekanauki.pl/articles/30148243.pdf

Data publikacji:

2023

Wydawca:

Polskie Towarzystwo Promocji Wiedzy

Tematy:

human pose estimation
lightweight model
Edge AI
deep learning
computer vision

Opis:

As the basic technology of human action recognition, pose estimation is attracting more and more researchers' attention, while edge application scenarios pose a higher challenge. This paper proposes a lightweight multi-person pose estimation scheme to meet the needs of real-time human action recognition on the edge end. This scheme uses AlphaPose to extract human skeleton nodes, and adds ResNet and Dense Upsampling Revolution to improve its accuracy. Meanwhile, we use YOLO to enhance AlphaPose’s support for multi-person pose estimation, and optimize the proposed model with TensorRT. In addition, this paper sets Jetson Nano as the Edge AI deployment device of the proposed model and successfully realizes the model migration to the edge end. The experimental results show that the speed of the optimized object detection model can reach 20 FPS, and the optimized multi-person pose estimation model can reach 10 FPS. With the image resolution of 320×240, the model’s accuracy is 73.2%, which can meet the real-time requirements. In short, our scheme can provide a basis for lightweight multi-person action recognition scheme on the edge end.

Źródło:

Applied Computer Science; 2023, 19, 1; 1-14
1895-3735
2353-6977

Pojawia się w:

Applied Computer Science

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 74.

Tytuł:

Automated motion heatmap generation for Bridge Navigation Watch Monitoring System

Autorzy:

Gokcek, Veysel
Kocak, Gazi
Genc, Yakup

Powiązania:

https://bibliotekanauki.pl/articles/32888824.pdf

Data publikacji:

2022

Wydawca:

Politechnika Gdańska. Wydział Inżynierii Mechanicznej i Okrętownictwa

Tematy:

safety of navigation
navigation watch
deep learning
3D body pose

Opis:

Most ship collisions and grounding accidents are due to errors made by watchkeeping personnel (WP) on the bridge. International Maritime Organization (IMO) adopts the resolution on the Bridge Navigation Watch Alarm System (BNWAS) detecting operator disability to avert these accidents. The defined system in the resolution is very basic and vulnerable to abuse. There is a need for a more advanced system of monitoring the behaviour of WP to mitigate watchkeeping errors. In this research, a Bridge Navigation Watch Monitoring System (BNWMS) is suggested to achieve this task. Architecture is proposed to train a model for BNWMS. The literature reveals that vision-based sensors can produce relevant input data required for model training. 2D body poses belonging to the same person are estimated from multiple camera views by using a deep learning-based pose estimation algorithm. Estimated 2D poses are projected into 3D space with a maximum 8 mm error by utilising multiple view computer vision techniques. Finally, the obtained 3D poses are plotted on a bird’s-eye view bridge plan to calculate a heatmap of body motions capturing temporal, as well as spatial, information. The results show that motion heatmaps present significant information about the behaviour of WP within a defined time interval. This automated motion heatmap generation is a novel approach that provides input data for the suggested BNWMS.

Źródło:

Polish Maritime Research; 2022, 1; 63-75
1233-2585

Pojawia się w:

Polish Maritime Research

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 75.

Tytuł:

Ataki na urządzenia mobilne i metody ich wykrywania

Autorzy:

Niewiadomska-Szynkiewicz, Ewa
Litka, Rafał

Powiązania:

https://bibliotekanauki.pl/articles/13947024.pdf

Data publikacji:

2023-02-20

Wydawca:

Akademia Sztuki Wojennej

Tematy:

cybersecurity
cyberattack detection
mobile applications
artificial
intelligence
machine learning
artificial neural networks
deep learning

Opis:

Individual protection of autonomous systems using simple analysis of transmitted messages is unfortunately becoming insufficient. There is a clear need for new solutions using data from multiple sources, integrating various methods, mechanisms and algorithms, including Big Data processing and data classification techniques using artificial intelligence methods. The quantity, quality, reliability and timeliness of data and information about the network situation, as well as the speed of its processing, determine the effectiveness of protection. The paper presents examples of the application of various artificial intelligence techniques for detecting attacks on ICT systems. Attention is focused on the application of deep learning methods for the detection of malicious applications installed on mobile devices. The effectiveness of the presented solutions was confirmed by numerous simulation experiments conducted on real data. Promising results were obtained.

Źródło:

Cybersecurity and Law; 2023, 9, 1; 95-107
2658-1493

Pojawia się w:

Cybersecurity and Law

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 76.

Tytuł:

Simultaneous monitoring of chromatic dispersion and optical signal to noise ratio in optical links using convolutional neural network and asynchronous delay-tap sampling

Autorzy:

Mrozek, Tomasz
Perlicki, Krzysztof
Jakubiak, Andrzej

Powiązania:

https://bibliotekanauki.pl/articles/1835803.pdf

Data publikacji:

2020

Wydawca:

Politechnika Wrocławska. Oficyna Wydawnicza Politechniki Wrocławskiej

Tematy:

deep learning
convolutional neural network
chromatic dispersion
OSNR
asynchronous delay-tap sampling

Opis:

The article presents a method for image analysis using asynchronous delay-tap sampling (ADTS) technique and convolutional neural networks (CNNs), allowing simultaneous monitoring of many phenomena occurring in the physical layer of the optical network. The ADTS method makes it possible to visualize the course of the optical signal in the form of characteristics (so-called phase portraits), which change their shape under the influence of phenomena (including chromatic dispersion, amplified spontaneous emission noise and other). Using the VPI photonics software,a simulation model of the ADTS technique was built. After the simulation tests, 10000 images were obtained, which after proper preparation were subjected to further analysis using CNN algorithms. The main goal of the study was to train a CNN to recognize the selected impairment (distortion); then to test its accuracy and estimate the impairment for the selected set of test images. The input data consisted of processed binary images in the form of two-dimensional matrices, with the position of the pixel. This article focuses on the analysis of images containing simultaneously the phenomena of chromatic dispersion and optical signal to noise ratio.

Źródło:

Optica Applicata; 2020, 50, 3; 331-341
0078-5466
1899-7015

Pojawia się w:

Optica Applicata

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 77.

Tytuł:

Deep Learning Can Improve Early Skin Cancer Detection

Autorzy:

Mohamed, Abeer
Mohamed, Wael A.
Zekry, Abdel Halim

Powiązania:

https://bibliotekanauki.pl/articles/963798.pdf

Data publikacji:

2019

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

technology
dermoscopic lesions
convolutional
neural network
ISIC dataset
deep learning
neural networks

Opis:

Skin cancer is the most common form of cancer affecting humans. Melanoma is the most dangerous type of skin cancer; and early diagnosis is extremely vital in curing the disease. So far, the human knowledge in this field is very limited, thus, developing a mechanism capable of identifying the disease early on can save lives, reduce intervention and cut unnecessary costs. In this paper, the researchers developed a new learning technique to classify skin lesions, with the purpose of observing and identifying the presence of melanoma. This new technique is based on a convolutional neural network solution with multiple configurations; where the researchers employed an International Skin Imaging Collaboration (ISIC) dataset. Optimal results are achieved through a convolutional neural network composed of 14 layers. This proposed system can successfully and reliably predict the correct classification of dermoscopic lesions with 97.78% accuracy.

Źródło:

International Journal of Electronics and Telecommunications; 2019, 65, 3; 507-512
2300-1933

Pojawia się w:

International Journal of Electronics and Telecommunications

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 78.

Tytuł:

Uczenie głębokie w diagnostyce medycznej
Deep Learning in Medical Diagnosis

Autorzy:

Antczak, K.

Powiązania:

https://bibliotekanauki.pl/articles/404011.pdf

Data publikacji:

2016

Wydawca:

Polskie Towarzystwo Symulacji Komputerowej

Tematy:

sieci neuronowe
diagnostyka medyczna
uczenie głębokie
neural networks
medical diagnosis
deep learning

Opis:

W pracy przeanalizowano perspektywy zastosowania metod uczenia głębokiego w diagnostyce medycznej. Jedną z kluczowych cech uczenia głębokiego jest zdolność do wyodrębniania złożonych wzorców o strukturze hierarchicznej. Wzorce takie występują również w diagnostyce, jako tak zwane diamenty diagnostyczne. Zastosowanie głębokich sieci neuronowych mogłoby poprawić jakość klasyfikatorów wykrywających choroby na podstawie objawów. Dodatkowo umożliwiłoby to sterowanie czułoscią i swoistością klasyfikatorów.
In this paper we analyze perspectives of applying deep learning methods in a field of medical diagnosis. One of key features of deep learning is ability to extract complex, hierarchical patterns. Such patterns are present also in a medical diagnosis, where they are known as diagnostic diamonds. Applying deep neural networks could increase performance of medical classifiers. Moreover, it would allow to adjust sensitivity and specificity of classifiers.

Źródło:

Symulacja w Badaniach i Rozwoju; 2016, 7, 3-4; 83-88
2081-6154

Pojawia się w:

Symulacja w Badaniach i Rozwoju

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 79.

Tytuł:

On training deep neural networks using a streaming approach

Autorzy:

Duda, Piotr
Jaworski, Maciej
Cader, Andrzej
Wang, Lipo

Powiązania:

https://bibliotekanauki.pl/articles/91796.pdf

Data publikacji:

2020

Wydawca:

Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych

Tematy:

deep learning
data streams
convolutional neural networks
strumienie danych
konwolucyjne sieci neuronowe

Opis:

In recent years, many deep learning methods, allowed for a significant improvement of systems based on artificial intelligence methods. Their effectiveness results from an ability to analyze large labeled datasets. The price for such high accuracy is the long training time, necessary to process such large amounts of data. On the other hand, along with the increase in the number of collected data, the field of data stream analysis was developed. It enables to process data immediately, with no need to store them. In this work, we decided to take advantage of the benefits of data streaming in order to accelerate the training of deep neural networks. The work includes an analysis of two approaches to network learning, presented on the background of traditional stochastic and batch-based methods.

Źródło:

Journal of Artificial Intelligence and Soft Computing Research; 2020, 10, 1; 15-26
2083-2567
2449-6499

Pojawia się w:

Journal of Artificial Intelligence and Soft Computing Research

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 80.

Tytuł:

A Proposed Model to Forecast Hourly Global Solar Irradiation Based on Satellite Derived Data, Deep Learning and Machine Learning Approaches

Autorzy:

Benamrou, Badr
Ouardouz, Mustapha
Allaouzi, Imane
Ben Ahmed, Mohamed

Powiązania:

https://bibliotekanauki.pl/articles/123503.pdf

Data publikacji:

2020

Wydawca:

Polskie Towarzystwo Inżynierii Ekologicznej

Tematy:

solar energy
forecast
global solar irradiation
satellite-derived data
GHI
deep learning

Opis:

An accurate short-term global solar irradiation (GHI) forecast is essential for integrating the photovoltaic systems into the electricity grid by reducing some of the problems caused by the intermittency of solar energy, including rapid fluctuations in energy, management storage, and the high costs of electricity. In this paper, the authors proposed a new hybrid approach to forecast hourly GHI for the Al-Hoceima city, Morocco. For this purpose, a deep long short-term memory network is trained on a combination of the hourly GHI ground measurements from the meteorological station of Al-Hoceima and the satellite-derived GHI from the neighbouring pixels of the point of interest. Xgboost, Random Forest, and Recursive Feature Elimination with cross-validation were used to select the most relevant features, the lagged satellite-derived GHI around the point of interest, as input to the proposed model where the best forecasting model is selected using the Grid Search algorithm. The simulation and results showed that the proposed approach gives high performance and outperformed other benchmark approaches.

Źródło:

Journal of Ecological Engineering; 2020, 21, 4; 26-38
2299-8993

Pojawia się w:

Journal of Ecological Engineering

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 81.

Tytuł:

Diagnozowanie stanu retinopatii cukrzycowej przy pomocy głębokich sieci neuronowych
Classification of the stage of the disease by deep neural networks

Autorzy:

Jarzembiński, B.
Kwasigroch, A.
Grochowski, M.

Powiązania:

https://bibliotekanauki.pl/articles/267831.pdf

Data publikacji:

2018

Wydawca:

Politechnika Gdańska. Wydział Elektrotechniki i Automatyki

Tematy:

uczenie głębokie
sieci neuronowe
retinopatia cukrzycowa
deep learning
neural networks
diabetic retinopathy

Opis:

W referacie opisano problem wykrywania oraz klasyfikacji stanu retinopatii cukrzycowej ze zdjęć dna oka przy pomocy głębokich sieci neuronowych. Retinopatia cukrzycowa jest chorobą oczu często występującą u osób z cukrzycą. Nieleczona prowadzi do uszkodzenia wzroku, a nawet ślepoty. W pracy badawczej opracowano system wykrywania retinopatii cukrzycowej na podstawie zdjęć dna oka. Opracowana sieć neuronowa przypisuje stan choroby w 5 stopniowej skali – od braku choroby do najbardziej zaawansowanego stanu choroby. Zaproponowano specjalny system kodowania klas w celu uchwycenia wielkości różnicy pomiędzy rzeczywistymi a predykowanymi stanami choroby. Uzyskano wysokie wyniki klasyfikacji na zbiorze testowym. W celu oceny skuteczności działania systemu wykorzystano miary statystyczne takie jak ważona Kappa i dokładność.
In the paper we described computer aided detection system of diabetic retinopathy based on fundus photos of retina. Diabetic retinopathy is an eye disease associated with diabetes. Non-treated diabetic retinopathy leads to sight degeneration and even blindness. Early detection is crucial due to provide effective treatment. Currently, diabetic retinopathy detection is time consuming process, done manualy by medical specialist. The disease is dangerous issue in places where the availability of phisicians is limited. We employed the computer system that detect diabetic retinopathy and assess a stage of the disease based on retinal photo of fundus. We used one of the best image classification system – deep neural networks. Employed system assess the stage of the disease in 5 level scale – from absence of disease to the most severe stage of disease. We employed transfer learning and data augmentation to enhance classification result. Moreover we proposed special class coding system to catch the difference between real and predicted stage of disease. We tested employed system using different statistical measures like accuracy, sensitivity, specificity and Kappa score.

Źródło:

Zeszyty Naukowe Wydziału Elektrotechniki i Automatyki Politechniki Gdańskiej; 2018, 60; 37-40
1425-5766
2353-1290

Pojawia się w:

Zeszyty Naukowe Wydziału Elektrotechniki i Automatyki Politechniki Gdańskiej

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 82.

Tytuł:

The automatic focus segmentation of multi-focus image fusion

Autorzy:

Hawari, K.
Ismail

Powiązania:

https://bibliotekanauki.pl/articles/2173548.pdf

Data publikacji:

2022

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

deep learning
ResNet50
multifocus image fusion
głęboka nauka
wieloogniskowa fuzja obrazu

Opis:

Multi-focus image fusion is a method of increasing the image quality and preventing image redundancy. It is utilized in many fields such as medical diagnostic, surveillance, and remote sensing. There are various algorithms available nowadays. However, a common problem is still there, i.e. the method is not sufficient to handle the ghost effect and unpredicted noises. Computational intelligence has developed quickly over recent decades, followed by the rapid development of multi-focus image fusion. The proposed method is multi-focus image fusion based on an automatic encoder-decoder algorithm. It uses deeplabV3+ architecture. During the training process, it uses a multi-focus dataset and ground truth. Then, the model of the network is constructed through the training process. This model was adopted in the testing process of sets to predict the focus map. The testing process is semantic focus processing. Lastly, the fusion process involves a focus map and multi-focus images to configure the fused image. The results show that the fused images do not contain any ghost effects or any unpredicted tiny objects. The assessment metric of the proposed method uses two aspects. The first is the accuracy of predicting a focus map, the second is an objective assessment of the fused image such as mutual information, SSIM, and PSNR indexes. They show a high score of precision and recall. In addition, the indexes of SSIM, PSNR, and mutual information are high. The proposed method also has more stable performance compared with other methods. Finally, the Resnet50 model algorithm in multi-focus image fusion can handle the ghost effect problem well.

Źródło:

Bulletin of the Polish Academy of Sciences. Technical Sciences; 2022, 70, 1; e140352, 1--8
0239-7528

Pojawia się w:

Bulletin of the Polish Academy of Sciences. Technical Sciences

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 83.

Tytuł:

Aircraft Bleed Air System Fault Prediction based on Encoder-Decoder with Attention Mechanism

Autorzy:

Su, Siyu
Sun, Youchao
Peng, Chong
Wang, Yifan

Powiązania:

https://bibliotekanauki.pl/articles/27312776.pdf

Data publikacji:

2023

Wydawca:

Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN

Tematy:

bleed air system
fault prediction
attention mechanism
deep learning
EWMA control chart

Opis:

The engine bleed air system (BAS) is one of the important systems for civil aircraft, and fault prediction of BAS is necessary to improve aircraft safety and the operator's profit. A dual-stage two-phase attention-based encoder-decoder (DSTP-ED) prediction model is proposed for BAS normal state estimation. Unlike traditional ED networks, the DSTP-ED combines spatial and temporal attention to better capture the spatiotemporal relationships to achieve higher prediction accuracy. Five data-driven algorithms, autoregressive integrated moving average (ARIMA), support vector regression (SVR), long short-term memory (LSTM), ED, and DSTP-ED, are applied to build prediction models for BAS. The comparison experiments show that the DSTP-ED model outperforms the other four data-driven models. An exponentially weighted moving average (EWMA) control chart is used as the evaluation criterion for the BAS failure warning. An empirical study based on Quick Access Recorder (QAR) data from Airbus A320 series aircraft demonstrates that the proposed method can effectively predict failures.

Źródło:

Eksploatacja i Niezawodność; 2023, 25, 3; art. no. 167792
1507-2711

Pojawia się w:

Eksploatacja i Niezawodność

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 84.

Tytuł:

Fault diagnosis of machines operating in variable conditions using artificial neural network not requiring training data from a faulty machine

Autorzy:

Pawlik, Paweł
Kania, Konrad
Przysucha, Bartosz

Powiązania:

https://bibliotekanauki.pl/articles/27312778.pdf

Data publikacji:

2023

Wydawca:

Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN

Tematy:

fault diagnosis
vibroacoustic diagnostics
deep learning
neural networks
maintenance of technical systems

Opis:

The fault diagnosis for maintenance of machines operating in variable conditions requires special dedicated methods. Variable load or temperature conditions affect the vibration signal values. The article presents a new approach to diagnosing rotating machines using an artificial neural network, the training of which does not require data from the damaged machine. This is a new approach not previously found in the literature. Until now, neural networks have been used for machine diagnosis in the form of classifiers, where data from individual faults were required. A new diagnostic parameter rDPNS (Relative Differences Product of Network Statistics) as a function of the machine's shaft order was proposed as a kind of new order spectrum independent of the machine's operating conditions. The presented work analyses the use of the proposed method to diagnose misalignment and unbalance. The results of an experiment carried out in the laboratory demonstrated the effectiveness of the proposed method.

Źródło:

Eksploatacja i Niezawodność; 2023, 25, 3; art. no. 168109
1507-2711

Pojawia się w:

Eksploatacja i Niezawodność

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 85.

Tytuł:

System wspomagający wykrywanie treści wizualnych i tekstowych zagrażających bezpieczeństwu dzieci w cyberprzestrzeni

Autorzy:

Niewiadomska-Szynkiewicz, Ewa
Różycka, Martyna
Staciwa, Katarzyna
Nyczka, Katarzyna

Powiązania:

https://bibliotekanauki.pl/articles/20311655.pdf

Data publikacji:

2023-10-31

Wydawca:

Akademia Sztuki Wojennej

Tematy:

cybersecurity
Child Sexual Abuse Material
CSAM
decision support system
artificial intelligence
machine learning
deep learning

Opis:

In recent years, there has been a significant increase in threats to children’s safety in cyberspace. The most serious of these include children’s participation in illegal online activities and the production of sexually explicit content involving them. Therefore, it is of fundamental importance to build awareness of cyber threats among our society’s youngest members and teach them skills for the safe use of products and services assigned to cyberspace. A key action for effectively protecting children in this environment is the early detection and reporting to the relevant authorities of illegal behavior and child abuse content. Teams such as Dyżurnet.pl, whose tasks currently include responding to potentially illegal content reported by cyberspace users, and in the near future, possibly also conducting proactive activities in this area, play an important role here. The experience of Dyżurnet.pl clearly shows that effective detection of such content requires automation of activities and appropriate IT tools. This paper presents a novel network monitoring and decision support system using artificial intelligence methods, including deep learning, to automatically detect potentially harmful material, such as Child Sexual Abuse Material (CSAM), erotic content involving children, pornographic content with a created or processed image of a child and pornography involving adults.

Źródło:

Cybersecurity and Law; 2023, 10, 2; 202-220
2658-1493

Pojawia się w:

Cybersecurity and Law

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 86.

Tytuł:

On graph mining with deep learning: introducing model r for link weight prediction

Autorzy:

Hou, Yuchen
Holder, Lawrence B.

Powiązania:

https://bibliotekanauki.pl/articles/91884.pdf

Data publikacji:

2019

Wydawca:

Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych

Tematy:

deep learning
neural networks
machine learning
graph mining
link weight prediction
predictive models
node embeddings

Opis:

Deep learning has been successful in various domains including image recognition, speech recognition and natural language processing. However, the research on its application in graph mining is still in an early stage. Here we present Model R, a neural network model created to provide a deep learning approach to the link weight prediction problem. This model uses a node embedding technique that extracts node embeddings (knowledge of nodes) from the known links’ weights (relations between nodes) and uses this knowledge to predict the unknown links’ weights. We demonstrate the power of Model R through experiments and compare it with the stochastic block model and its derivatives. Model R shows that deep learning can be successfully applied to link weight prediction and it outperforms stochastic block model and its derivatives by up to 73% in terms of prediction accuracy. We analyze the node embeddings to confirm that closeness in embedding space correlates with stronger relationships as measured by the link weight. We anticipate this new approach will provide effective solutions to more graph mining tasks

Źródło:

Journal of Artificial Intelligence and Soft Computing Research; 2019, 9, 1; 21-40
2083-2567
2449-6499

Pojawia się w:

Journal of Artificial Intelligence and Soft Computing Research

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 87.

Tytuł:

Predictive modelling of turbofan engine components condition using machine and deep learning methods

Autorzy:

Matuszczak, Michał
Żbikowski, Mateusz
Teodorczyk, Andrzej

Powiązania:

https://bibliotekanauki.pl/articles/1841686.pdf

Data publikacji:

2021

Wydawca:

Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN

Tematy:

reliability
prognostics
deep learning
machine learning
gas turbine
turbofan engine
neural network
condition-based maintenance

Opis:

The article proposes an approach based on deep and machine learning models to predict a component failure as an enhancement of condition based maintenance scheme of a turbofan engine and reviews currently used prognostics approaches in the aviation industry. Component degradation scale representing its life consumption is proposed and such collected condition data are combined with engines sensors and environmental data. With use of data manipulation techniques, a framework for models training is created and models' hyperparameters obtained through Bayesian optimization. Models predict the continuous variable representing condition based on the input. Best performed model is identified by detemining its score on the holdout set. Deep learning models achieved 0.71 MSE score (ensemble meta-model of neural networks) and outperformed significantly machine learning models with their best score at 1.75. The deep learning models shown their feasibility to predict the component condition within less than 1 unit of the error in the rank scale.

Źródło:

Eksploatacja i Niezawodność; 2021, 23, 2; 359-370
1507-2711

Pojawia się w:

Eksploatacja i Niezawodność

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 88.

Tytuł:

Model Faster R-CNN uczony na syntetycznych obrazach
Faster R-CNN model learning on synthetic images

Autorzy:

Łach, Błażej
Łukasik, Edyta

Powiązania:

https://bibliotekanauki.pl/articles/1427643.pdf

Data publikacji:

2020

Wydawca:

Politechnika Lubelska. Instytut Informatyki

Tematy:

computer vision
sztuczne obrazy
Faster R-CNN
głębokie uczenie
synthetic images
deep learning

Opis:

Uczenie maszynowe wymaga opisu danych przez człowieka. Opisywanie zbioru danych ręcznie jest bardzo czasochłonne. W artykule zbadano jak model uczył się na zdjęciach sztucznie wytworzonych, z jak najmniejszym udziałem człowieka przy opisywaniu danych. Sprawdzono jaki wpływ miało zastosowanie augmentacji i progresywnego rozmiaru zdjęcia przy treningu modelu na syntetycznym zbiorze. Model osiągnął nawet o 3,35% wyższą średnią precyzję na syntetycznym zbiorze danych przy zastosowaniu treningów z rosnącą rozdzielczością. Augmentacje poprawiły jakość detekcji na rzeczywistych zdjęciach. Wytwarzanie sztucznie danych treningowych ma duży wpływ na przyśpieszenie przygotowania treningów, ponieważ nie wymaga tak dużych nakładów ludzkich, jak klasyczne uczenie modeli z danymi opisanymi przez człowieka.
Machine learning requires a human description of the data. The manual dataset description is very time consuming. In this article was examined how the model learns from artificially created images, with the least human participation in describing the data. It was checked how the model learned on artificially produced images with augmentations and progressive image size. The model has achieve up to 3.35 higher mean average precision on syntetic dataset in the training with increasing images resolution. Augmentations improved the quality of detection on real photos. The production of artificially generated training data has a great impact on the acceleration of prepare training, because it does not require as much human resources as normal learning process.

Źródło:

Journal of Computer Sciences Institute; 2020, 17; 401-404
2544-0764

Pojawia się w:

Journal of Computer Sciences Institute

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 89.

Tytuł:

The Study of the Influence of Architecture on Effectiveness of Deep Neural Networks Training
Badania wpływu architektury na skuteczność uczenia głębokich sieci neuronowych

Autorzy:

Kolbusz, Janusz
Różycki, Paweł
Bartczak, Tomasz

Powiązania:

https://bibliotekanauki.pl/articles/509270.pdf

Data publikacji:

2018

Wydawca:

Akademia Finansów i Biznesu Vistula

Tematy:

deep learning
ANN architectures
Bridged MLP
NBN
uczenie głębokie
architektury sztucznych sieci neuronowych

Opis:

Paper presents impact of the neural network architecture on the training effectiveness and training time. Selected network architectures and training algorithm are described. Presented experimental results of research confirming the significant influence of architecture on the success of network training.
W artykule przedstawiono wpływ architektury sieci neuronowej na skuteczność i czas uczenia sieci. Opisano wybrane architektury sieci, algorytm uczenia oraz zaprezentowano wyniki badań potwierdzających znaczący wpływ architektury na sukces uczenia sieci.

Źródło:

Zeszyty Naukowe Uczelni Vistula; 2018, 59(2) Informatyka; 60-71
2353-2688

Pojawia się w:

Zeszyty Naukowe Uczelni Vistula

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 90.

Tytuł:

VSC-Based DSTATCOM for PQ Improvement: A Deep-Learning Approach

Autorzy:

Mangaraj, Mrutyunjaya
Sabat, Jogeswara
Barisal, Ajit Kumar
Ramaiah, K. Subba
Rao, Gudivada Eswara

Powiązania:

https://bibliotekanauki.pl/articles/2175932.pdf

Data publikacji:

2022

Wydawca:

Politechnika Wrocławska. Oficyna Wydawnicza Politechniki Wrocławskiej

Tematy:

DL approach
deep learning approach
DSTATCOM
distributed static compensator
ALMS
PQ
power quality

Opis:

With the rapid advancement of the technology, deep learning supported voltage source converter (VSC)-based distributed static compensator (DSTATCOM) for power quality (PQ) improvement has attracted significant interest due to its high accuracy. In this paper, six subnets are structured for the proposed deep learning approach (DL-Approach) algorithm by using its own mathematical equations. Three subnets for active and the other three for reactive weight components are used to extract the fundamental component of the load current. These updated weights are utilised for the generation of the reference source currents for VSC. Hysteresis current controllers (HCCs) are employed in each phase in which generated switching signal patterns need to be carried out from both predicted reference source current and actual source current. As a result, the proposed technique achieves better dynamic performance, less computation burden and better estimation speed. Consequently, the results were obtained for different loading conditions using MATLAB/Simulink software. Finally, the feasibility was effective as per the benchmark of IEEE guidelines in response to harmonics curtailment, power factor (p.f) improvement, load balancing and voltage regulation.

Źródło:

Power Electronics and Drives; 2022, 7, 42; 174--186
2451-0262
2543-4292

Pojawia się w:

Power Electronics and Drives

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 91.

Tytuł:

Prediction and classification of pressure injuries by deep learning
Wykrywanie i klasyfikacja odleżyn z wykorzystaniem deep learning

Autorzy:

Yilmaz, A.
Kızıl, H.
Kaya, U.
Cakır, R.
Demiral, M.

Powiązania:

https://bibliotekanauki.pl/articles/2047948.pdf

Data publikacji:

2021

Wydawca:

Akademia Bialska Nauk Stosowanych im. Jana Pawła II w Białej Podlaskiej

Tematy:

deep learning
pressure ulcers
artificial intelligence
nursing care
odleżyny
sztuczna inteligencja
opieka pielęgniarska

Opis:

Pressure injuries are a serious medical problem that both negatively affects the patient's quality of life and results in significant healthcare costs. In cases where a patient doesn’t receive appropriate treatment and care, death may result. Nurses play critical roles in the prevention, care, and treatment of pressure injuries as members of the healthcare team who closely monitor the health status of the patient. Today, the use of artificial intelligence is becoming more prevalent in healthcare, as in many other areas. Artificial intelligence is a method that aims to solve complex problems by using computers to mathematically simulate the way the brain works. In this article, we compile and share information about a deep learning model developed for the detection and classification of pressure injuries. Deep learning can operate on many types of data. Convolutional Neural Networks (CNN) prefer images because they can handle 2D arrays. In this case, the images, annotated according to the National Pressure Injury Advisory Panel pressure injury classification system, have been fed into a deep learning model using CNN. The developed CNN model has a 97% success in detecting and classifying pressure injuries, and as more images are collected and fed into the CNN, the prediction accuracy will increase. This deep learning model allows for the automatic detection and classification of pressure injuries, an indicator of health outcomes, at an early stage and for quick and accurate intervention. In this context, it is expected that the quality of nursing care will increase, the prevalence of pressure injury will decrease, and the economic burden of this health problem will decrease.
Odleżyny są problemem zdrowotnym, który negatywnie wpływa na jakość życia pacjenta i powoduje poważne koszty opieki. W przypadku braku odpowiedniego leczenia i opieki może to doprowadzić do śmierci pacjenta. Pielęgniarki odgrywają kluczową rolę w zapobieganiu, opiece i leczeniu odleżyn jako członkowie zespołu opieki zdrowotnej, którzy ściśle i stale monitorują stan zdrowia danej osoby. Obecnie w dziedzinie zdrowia, podobnie jak w wielu innych dziedzinach, coraz częściej wykorzystuje się sztuczną inteligencję. Sztuczna inteligencja jest metodą, która ma na celu rozwiązywanie złożonych problemów poprzez matematyczne symulowanie sposobu działania mózgu z wykorzystaniem komputerów. Niniejszy artykuł jest przeglądem zaprojektowanym w celu podzielenia się informacjami na temat modelu deep learning opracowanego do wykrywania i klasyfikacji odleżyn. Deep learning może działać na wielu typach danych. Konwolucyjne sieci neuronowe (ang. convolutional neural networks, CNN) preferują obrazy, ponieważ mogą obsługiwać macierze 2D. Obrazy, uporządkowane zgodnie z systemem klasyfikacji odleżyn według National Pressure Injury Advisory Panel (NPIAP), zostały przekształcone w "Deep Learning Model" z wykorzystaniem CNN. Opracowywany model CNN ma 97% skuteczności w wykrywaniu i klasyfikowaniu odleżyn, a im więcej obrazów zostanie zebranych i wykorzystanych w CNN, tym większe będzie prawdopodobieństwo trafnej prognozy. Ten model deep learning daje możliwość automatycznego wykrywania i klasyfikacji odleżyn, które są wskaźnikiem jakości zdrowia, na wczesnym etapie oraz dokładnej i szybkiej interwencji. W tym kontekście oczekuje się, że jakość opieki pielęgniarskiej wzrośnie, zmniejszy się częstość występowania odleżyn oraz obciążenie ekonomiczne związane z tym problemem zdrowotnym.

Źródło:

Health Problems of Civilization; 2021, 15, 4; 328-335
2353-6942
2354-0265

Pojawia się w:

Health Problems of Civilization

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 92.

Tytuł:

Theory II: Deep learning and optimization

Autorzy:

Poggio, T.
Liao, Q.

Powiązania:

https://bibliotekanauki.pl/articles/201787.pdf

Data publikacji:

2018

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

deep learning
convolutional neural networks
loss surface
optimization
uczenie głębokie
sieć neuronowa
optymalizacja

Opis:

The landscape of the empirical risk of overparametrized deep convolutional neural networks (DCNNs) is characterized with a mix of theory and experiments. In part A we show the existence of a large number of global minimizers with zero empirical error (modulo inconsistent equations). The argument which relies on the use of Bezout theorem is rigorous when the RELUs are replaced by a polynomial nonlinearity. We show with simulations that the corresponding polynomial network is indistinguishable from the RELU network. According to Bezout theorem, the global minimizers are degenerate unlike the local minima which in general should be non-degenerate. Further we experimentally analyzed and visualized the landscape of empirical risk of DCNNs on CIFAR-10 dataset. Based on above theoretical and experimental observations, we propose a simple model of the landscape of empirical risk. In part B, we characterize the optimization properties of stochastic gradient descent applied to deep networks. The main claim here consists of theoretical and experimental evidence for the following property of SGD: SGD concentrates in probability – like the classical Langevin equation – on large volume, ”flat” minima, selecting with high probability degenerate minimizers which are typically global minimizers.

Źródło:

Bulletin of the Polish Academy of Sciences. Technical Sciences; 2018, 66, 6; 775-787
0239-7528

Pojawia się w:

Bulletin of the Polish Academy of Sciences. Technical Sciences

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 93.

Tytuł:

Deep learning for automatic LiDAR point cloud processing
Głębokie uczenie w automatycznym przetwarzaniu chmury punktów skanowania laserowego

Autorzy:

Dominik, Wojciech
Bożyczko, Marcin
Tułacz-Maziarz, Karolina

Powiązania:

https://bibliotekanauki.pl/articles/27322929.pdf

Data publikacji:

2021

Wydawca:

Stowarzyszenie Geodetów Polskich

Tematy:

deep learning
LiDAR
point cloud
classification
automation
głębokie uczenie
chmura punktów
klasyfikacja
automatyzacja

Opis:

The paper presents the method of automatic point cloud classification that has been developed by OPEGIEKA. The method is based on deep learning techniques and consists of an in- house developed algorithm of point cloud transformation to a regular array accompanied by internally designed convolutional neural network architecture. The developed workflow as well as experiences from its application during the execution of the CAPAP project are described. Results obtained on real project data as well as statistics obtained on the ISPRS 3D semantic labelling benchmark with the use of OPEGIEKA's method are presented. The achieved results place OPEGIEKA in the top 3 of the classification accuracy rating in the ISPRS benchmark. The implementation of OPEGIEKA's solution into LiDAR point clouds classification workflow allowed to reduce the amount of necessary manual work.
W artykule przedstawiono metodę automatycznej klasyfikacji chmur punktów opracowaną przez firmę OPEGIEKA. Metoda opiera się na technice głębokiego uczenia i składa się z opracowanego przez autorów algorytmu transformacji chmury punktów do regularnej macierzy, któremu towarzyszy wewnętrznie zaprojektowana architektura konwolucyjnej sieci neuronowej. W tekście opisano opracowany ciąg technologiczny uwzględniający metodykę na przykładzie doświadczenia podczas realizacji projektu CAPAP. Przedstawiono wyniki uzyskane na rzeczywistych danych projektowych oraz statystyki uzyskane na benchmarku ISPRS dotyczącego etykietowania semantycznego z wykorzystaniem metody OPEGIEKA. Osiągnięte wyniki plasują OPEGIEKA w pierwszej 3 rankingu dokładności klasyfikacji w benchmarku ISPRS. Wdrożenie rozwiązania OPEGIEKA do przepływu pracy klasyfikacji chmur punktów LiDAR pozwoliło zmniejszyć ilość niezbędnej pracy manualnej.

Źródło:

Archiwum Fotogrametrii, Kartografii i Teledetekcji; 2021, 33; 13--22
2083-2214
2391-9477

Pojawia się w:

Archiwum Fotogrametrii, Kartografii i Teledetekcji

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 94.

Tytuł:

Enhancing the performance of deep learning technique by combining with gradient boosting in rainfall-runoff simulation

Autorzy:

Abdullaeva, Barno S.

Powiązania:

https://bibliotekanauki.pl/articles/28411647.pdf

Data publikacji:

2023

Wydawca:

Instytut Technologiczno-Przyrodniczy

Tematy:

deep learning
gradient boosting
hybrid model
multi-step ahead forecasting
rainfall-runoff simulation

Opis:

Artificial neural networks are widely employed as data mining methods by researchers across various fields, including rainfall-runoff (R-R) statistical modelling. To enhance the performance of these networks, deep learning (DL) neural networks have been developed to improve modelling accuracy. The present study aims to improve the effectiveness of DL networks in enhancing the performance of artificial neural networks via merging with the gradient boosting (GB) technique for daily runoff data forecasting in the river Amu Darya, Uzbekistan. The obtained results showed that the new hybrid proposed model performed exceptionally well, achieving a 16.67% improvement in determination coefficient (R2) and a 23.18% reduction in root mean square error (RMSE) during the training phase compared to the single DL model. Moreover, during the verification phase, the hybrid model displayed remarkable performance, demonstrating a 66.67% increase in R2 and a 50% reduction in RMSE. Furthermore, the hybrid model outperformed the single GB model by a significant margin. During the training phase, the new model showed an 18.18% increase in R2 and a 25% reduction in RMSE. In the verification phase, it improved by an impressive 75% in R2 and a 33.33% reduction in RMSE compared to the single GB model. These findings highlight the potential of the hybrid DL-GB model in improving daily runoff data forecasting in the challenging hydrological context of the Amu Darya River basin in Uzbekistan.

Źródło:

Journal of Water and Land Development; 2023, 59; 216--223
1429-7426
2083-4535

Pojawia się w:

Journal of Water and Land Development

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 95.

Tytuł:

A comparison of conventional and deep learning methods of image classification
Porównanie metod klasycznego i głębokiego uczenia maszynowego w klasyfikacji obrazów

Autorzy:

Dovbnych, Maryna
Plechawska-Wójcik, Małgorzata

Powiązania:

https://bibliotekanauki.pl/articles/2055127.pdf

Data publikacji:

2021

Wydawca:

Politechnika Lubelska. Instytut Informatyki

Tematy:

image classification
machine learning
deep learning
neural networks
klasyfikacja obrazów
uczenie maszynowe
uczenie głębokie
sieci neuronowe

Opis:

The aim of the research is to compare traditional and deep learning methods in image classification tasks. The conducted research experiment covers the analysis of five different models of neural networks: two models of multi–layer perceptron architecture: MLP with two hidden layers, MLP with three hidden layers; and three models of convolutional architecture: the three VGG blocks model, AlexNet and GoogLeNet. The models were tested on two different datasets: CIFAR–10 and MNIST and have been applied to the task of image classification. They were tested for classification performance, training speed, and the effect of the complexity of the dataset on the training outcome.
Celem badań jest porównanie metod klasycznego i głębokiego uczenia w zadaniach klasyfikacji obrazów. Przeprowa-dzony eksperyment badawczy obejmuje analizę pięciu różnych modeli sieci neuronowych: dwóch modeli wielowar-stwowej architektury perceptronowej: MLP z dwiema warstwami ukrytymi, MLP z trzema warstwami ukrytymi; oraz trzy modele architektury konwolucyjnej: model z trzema VGG blokami, AlexNet i GoogLeNet. Modele przetrenowano na dwóch różnych zbiorach danych: CIFAR–10 i MNIST i zastosowano w zadaniu klasyfikacji obrazów. Zostały one zbadane pod kątem wydajności klasyfikacji, szybkości trenowania i wpływu złożoności zbioru danych na wynik trenowania.

Źródło:

Journal of Computer Sciences Institute; 2021, 21; 303--308
2544-0764

Pojawia się w:

Journal of Computer Sciences Institute

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 96.

Tytuł:

Theory I: Deep networks and the curse of dimensionality

Autorzy:

Poggio, T.
Liao, Q.

Powiązania:

https://bibliotekanauki.pl/articles/200623.pdf

Data publikacji:

2018

Wydawca:

Polska Akademia Nauk. Czytelnia Czasopism PAN

Tematy:

deep network
shallow network
convolutional neural network
function approximation
deep learning
sieci neuronowe
aproksymacja funkcji
uczenie głębokie

Opis:

We review recent work characterizing the classes of functions for which deep learning can be exponentially better than shallow learning. Deep convolutional networks are a special case of these conditions, though weight sharing is not the main reason for their exponential advantage.

Źródło:

Bulletin of the Polish Academy of Sciences. Technical Sciences; 2018, 66, 6; 761-773
0239-7528

Pojawia się w:

Bulletin of the Polish Academy of Sciences. Technical Sciences

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 97.

Tytuł:

An AI & ML based detection & identification in remote imagery: state-of-the-art

Autorzy:

Hashmi, Hina
Dwivedi, Rakesh
Kumar, Anil

Powiązania:

https://bibliotekanauki.pl/articles/2141786.pdf

Data publikacji:

2021

Wydawca:

Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów

Tematy:

convolutional neural network
remote sensed imagery
object detection
artificial intelligence
feature extraction
deep learning
machine learning

Opis:

Remotely sensed images and their allied areas of application have been the charm for a long time among researchers. Remote imagery has a vast area in which it is serving and achieving milestones. From the past, after the advent of AL, ML, and DL-based computing, remote imagery is related techniques for processing and analyzing are continuously growing and offering countless services like traffic surveillance, earth observation, land surveying, and other agricultural areas. As Artificial intelligence has become the charm of researchers, machine learning and deep learning have been proven as the most commonly used and highly effective techniques for object detection. AI & ML-based object segmentation & detection makes this area hot and fond to the researchers again with the opportunities of enhanced accuracy in the same. Several researchers have been proposed their works in the form of research papers to highlight the effectiveness of using remotely sensed imagery for commercial purposes. In this article, we have discussed the concept of remote imagery with some preprocessing techniques to extract hidden and fruitful information from them. Deep learning techniques applied by various researchers along with object detection, object recognition are also discussed here. This literature survey is also included a chronological review of work done related to detection and recognition using deep learning techniques.

Źródło:

Journal of Automation Mobile Robotics and Intelligent Systems; 2021, 15, 4; 3-17
1897-8649
2080-2145

Pojawia się w:

Journal of Automation Mobile Robotics and Intelligent Systems

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 98.

Tytuł:

Remaining useful life prediction with insufficient degradation data based on deep learning approach

Autorzy:

Lyu, Yi
Jiang, Yijie
Zhang, Qichen
Chen, Ci

Powiązania:

https://bibliotekanauki.pl/articles/2038109.pdf

Data publikacji:

2021

Wydawca:

Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN

Tematy:

deep learning
remaining useful life
degradation data
data amplification
cycle-consistent generative adversarial network

Opis:

Remaining useful life (RUL) prediction plays a crucial role in decision-making in conditionbased maintenance for preventing catastrophic field failure. For degradation-failed products, the data of performance deterioration process are the key for lifetime estimation. Deep learning has been proved to have excellent performance in RUL prediction given that the degradation data are sufficiently large. However, in some applications, the degradation data are insufficient, under which how to improve the prediction accuracy is yet a challenging problem. To tackle such a challenge, we propose a novel deep learning-based RUL prediction framework by amplifying the degradation dataset. Specifically, we leverage the cycle-consistent generative adversarial network to generate the synthetic data, based on which the original degradation dataset is amplified so that the data characteristics hidden in the sample space could be captured. Moreover, the sliding time window strategy and deep bidirectional long short-term memory network are employed to complete the RUL prediction framework. We show the effectiveness of the proposed method by running it on the turbine engine data set from the National Aeronautics and Space Administration. The comparative experiments show that our method outperforms a case without the use of the synthetically generated data.

Źródło:

Eksploatacja i Niezawodność; 2021, 23, 4; 745-756
1507-2711

Pojawia się w:

Eksploatacja i Niezawodność

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 99.

Tytuł:

Unsupervised dynamic topic model for extracting adverse drug reaction from health forums

Autorzy:

Eslami, Behnaz
Motlagh, Mehdi Habibzadeh
Rezaei, Zahra
Eslami, Mohammad
Amini, Mohammad Amin

Powiązania:

https://bibliotekanauki.pl/articles/117691.pdf

Data publikacji:

2020

Wydawca:

Polskie Towarzystwo Promocji Wiedzy

Tematy:

Deep Learning
topic modeling
Text Mining
ADR
NMF
analiza tekstu
uczenie maszynowe
modelowanie tematyczne

Opis:

The relationship between drug and its side effects has been outlined in two websites: Sider and WebMD. The aim of this study was to find the association between drug and its side effects. We compared the reports of typical users of a web site called: “Ask a patient” website with reported drug side effects in reference sites such as Sider and WebMD. In addition, the typical users’ comments on highly-commented drugs (Neurotic drugs, Anti-Pregnancy drugs and Gastrointestinal drugs) were analyzed, using deep learning method. To this end, typical users’ comments on drugs' side effects, during last decades, were collected from the website “Ask a patient”. Then, the data on drugs were classified based on deep learning model (HAN) and the drugs’ side effect. And the main topics of side effects for each group of drugs were identified and reported, through Sider and WebMD websites. Our model demonstrates its ability to accurately describe and label side effects in a temporal text corpus by a deep learning classifier which is shown to be an effective method to precisely discover the association between drugs and their side effects. Moreover, this model has the capability to immediately locate information in reference sites to recognize the side effect of new drugs, applicable for drug companies. This study suggests that the sensitivity of internet users and the diverse scientific findings are for the benefit of distinct detection of adverse effects of drugs, and deep learning would facilitate it.

Źródło:

Applied Computer Science; 2020, 16, 1; 41-59
1895-3735

Pojawia się w:

Applied Computer Science

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce

Skocz do pozycji: 100.

Tytuł:

Klasyfikacja sygnału EKG przy użyciu konwolucyjnych sieci neuronowych
ECG signal classification using convolutional neural networks

Autorzy:

Ogryczak, Maria

Powiązania:

https://bibliotekanauki.pl/articles/1841908.pdf

Data publikacji:

2020

Wydawca:

Politechnika Gdańska. Wydział Elektrotechniki i Automatyki

Tematy:

EKG
arytmia
uczenie głębokie
konwolucyjne sieci neuronowe
ECG
arrhythmia
deep learning
convolutional neural networks

Opis:

Podniesienie jakości i zautomatyzowanie procesu diagnozy jest istotnym elementem rozwoju medycyny i samokontroli stanu zdrowia pacjentów. Od dłuższego czasu istnieją i są stosowane różne metody analizy i klasyfikacji sygnału EKG, jednak nie zawsze ich dokładność jest zadowalająca. Największym problemem jest trudność rozpoznania istniejącej nieprawidłowości, w przypadku gdy jej reprezentacja jest podobna do prawidłowej pracy serca np. przedwczesny skurcz komorowy. W ostatnich latach obserwujemy dynamiczny rozwój nowego narzędzia z rodziny metod sztucznej inteligencji - głębokich sieci neuronowych. Cechuje je duża selektywność klasyfikacji nawet najbardziej skomplikowanych sygnałów w postaci szeregów czasowych czy obrazów, często na podstawie cech niezauważalnych dla ludzkiego oka. W niniejszym artykule przedstawiono sposób analizy zarejestrowanego sygnału elektrycznej czynności mięśnia sercowego (EKG), na podstawie pojedynczego, wyodrębnionego cyklu pracy serca. Celem badania było zdiagnozowanie sześciu różnych typów ewolucji mogących świadczyć o występowaniu arytmii. Badania przeprowadzono z wykorzystaniem ogólnodostępnej bazy danych MIT-BIH Arrhythmia Database. W celu podniesienia jakości ekstrakcji cech analizowanego sygnału, dokonano jego dekompozycji czasowo-przestrzennej przy wykorzystaniu transformacji falkowej. W rezultacie uzyskano zadowalające wyniki klasyfikacji: dokładność 92,4% i swoistość (zdolność do wykrycia braku cechy) 96,5%. Osiągnięte wyniki potwierdzają skuteczność systemu automatycznej klasyfikacji cyklów pracy serca, mogącego wspomóc lekarzy w procesie żmudnej analizy dużej liczby zarejestrowanych danych.
Automation and improvement of diagnostic process is a vital element of medicine development and patient’s condition self-control. For a long time different ECG signal classification methods exist and are successfully applied, nevertheless their accuracy is not always satisfying enough. The lack of identification of an existing abnormality, which is very similar to a normal heartbeat is the biggest issue - for example premature ventricular contraction. Over the past few years there was a rapid development of an artificial intelligence tool - deep neural networks. They characterise by a high classification ability even the most complicated patterns in the form of time series or images, often based on features unnoticeable for human eye. In this paper the approach to electrocardiography (ECG) analysis was presented, taking into consideration a single heartbeat. The aim of this research was diagnosis of six different types of beat that may indicate arrhythmia occurrence. The study were performed on the public database MIT-BIH Arrhythmia Database. In order to enhance feature extraction quality of the analysed signal the time-space decomposition was made using wavelet transform. The satisfying performance with 92.4% accuracy and 96.5% specificity were accomplished. The achieved results may be used to develop an automatic heartbeat classification system that would significantly contribute medicians in the arduous process of data analysis.

Źródło:

Zeszyty Naukowe Wydziału Elektrotechniki i Automatyki Politechniki Gdańskiej; 2020, 71; 51-54
1425-5766
2353-1290

Pojawia się w:

Zeszyty Naukowe Wydziału Elektrotechniki i Automatyki Politechniki Gdańskiej

Dostawca treści:

Biblioteka Nauki

/5

Artykuł

Zmień widok

• na półce