Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

English (EN)·Polski (PL)·Yкраїнський (UK)
Przejdź do strony domowej biblioteki Centralna Biblioteka Wojskowa Link otwiera się w nowym oknie Logo biblioteki Prolib Integro - strona głównaCentralna Biblioteka Wojskowa

Wyszukujesz frazę "Convolutional Neural Network" wg kryterium: Temat

  Lista filtrów
Wyrównaj
Wyświetlanie 1-15 z 72
Tytuł:
A deep hybrid model for human-computer interaction using dynamic hand gesture recognition
Autorzy:
Ramalingam, Brindha
Angappan, Geetha
Powiązania:
https://bibliotekanauki.pl/articles/38702766.pdf
Data publikacji:
2023
Wydawca:
Instytut Podstawowych Problemów Techniki PAN
Tematy:
dynamic hand gesture
human-computer interaction
long short-term memory
convolutional neural network
dynamiczny gest ręki
interakcja człowiek-komputer
pamięć krótkotrwała
konwolucyjna sieć neuronowa
Opis:
Dynamic hand gestures attract great interest and are utilized in different fields. Amongthese, man-machine interaction is an interesting area that makes use of the hand to providea natural way of interaction between them. A dynamic hand gesture recognition system isproposed in this paper, which helps to perform control operations in applications such asmusic players, video games, etc. The key motivation of this research is to provide a simple, touch-free system for effortless and faster human-computer interaction (HCI). As thisproposed model employs dynamic hand gestures, HCI is achieved by building a modelwith a convolutional neural network (CNN) and long short-term memory (LSTM) net-works. CNN helps in extracting important features from the images and LSTM helpsto extract the motion information between the frames. Various models are constructedby differing the LSTM and CNN layers. The proposed system is tested on an existing EgoGesture dataset that has several classes of gestures from which the dynamic gesturesare utilized. This dataset is used as it has more data with a complex background, actionsperformed with varying speeds, lighting conditions, etc. This proposed hand gesture recognition system attained an accuracy of 93%, which is better than other existing systemssubject to certain limitations.
Źródło:
Computer Assisted Methods in Engineering and Science; 2023, 30, 3; 263-276
2299-3649
Pojawia się w:
Computer Assisted Methods in Engineering and Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A DHCR_ SmartNet: A smart Devanagari handwritten character recognition using level-wised CNN architecture
Autorzy:
Deore, Shalaka Prasad
Powiązania:
https://bibliotekanauki.pl/articles/27312907.pdf
Data publikacji:
2022
Wydawca:
Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:
convolutional neural network
VGG16
fine-tuned
handwritten script
Devanagari characters
Opis:
Handwritten script recognition is a vital application of the machine-learning domain. Applications like automatic license plate detection, pin-code detection, and historical document management increases attention toward handwritten script recognition. English is the most widely spoken language in India; hence, there has been a lot of research into identifying a script using a machine. Devanagari is a popular script that is used by a large number of people on the Indian subcontinent. In this paper, a level-wised efficient transfer-learning approach is presented on the VGG16 model of a convolutional neural network (CNN) for identifying isolated Devanagari handwritten characters. In this work, a new dataset of Devanagari characters is presented and made accessible to the public. This newly created dataset is comprised of 5800 samples for 12 vowels, 36 consonants, and 10 digits. Initially, a simple CNN is implemented and trained on this new small dataset. During the next stage, a transfer-learning approach is implemented on the VGG16 model, and during the last stage, the efficient fine-tuned VGG16 model is implemented. The obtained accuracy of the fine-tuned model’s training and testing came to 98.16% and 96.47%, respectively.
Źródło:
Computer Science; 2022, 23 (3); 301--320
1508-2806
2300-7036
Pojawia się w:
Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A distributed big data analytics model for traffic accidents classification and recognition based on SparkMlLib cores
Autorzy:
Mallahi, Imad El
Riffi, Jamal
Tairi, Hamid
Ez-Zahout, Abderrahmane
Mahraz, Mohamed Adnane
Powiązania:
https://bibliotekanauki.pl/articles/27314355.pdf
Data publikacji:
2022
Wydawca:
Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów
Tematy:
big data
machine learning
traffic accident
severity prediction
convolutional neural network
Opis:
This paper focuses on the issue of big data analytics for traffic accident prediction based on SparkMllib cores; however, Spark’s Machine Learning Pipelines provide a helpful and suitable API that helps to create and tune classification and prediction models to decision-making concerning traffic accidents. Data scientists have recently focused on classification and prediction techniques for traffic accidents; data analytics techniques for feature extraction have also continued to evolve. Analysis of a huge volume of received data requires considerable processing time. Practically, the implementation of such processes in real-time systems requires a high computation speed. Processing speed plays an important role in traffic accident recognition in real-time systems. It requires the use of modern technologies and fast algorithms that increase the acceleration in extracting the feature parameters from traffic accidents. Problems with overclocking during the digital processing of traffic accidents have yet to be completely resolved. Our proposed model is based on advanced processing by the Spark MlLib core. We call on the real-time data streaming API on spark to continuously gather real-time data from multiple external data sources in the form of data streams. Secondly, the data streams are treated as unbound tables. After this, we call the random forest algorithm continuously to extract the feature parameters from a traffic accident. The use of this proposed method makes it possible to increase the speed factor on processors. Experiment results showed that the proposed method successfully extracts the accident features and achieves a seamless classification performance compared to other conventional traffic accident recognition algorithms. Finally, we share all detected accidents with details onto online applications with other users.
Źródło:
Journal of Automation Mobile Robotics and Intelligent Systems; 2022, 16, 4; 62--71
1897-8649
2080-2145
Pojawia się w:
Journal of Automation Mobile Robotics and Intelligent Systems
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A few-shot fine-grained image recognition method
Autorzy:
Wang, Jianwei
Chen, Deyun
Powiązania:
https://bibliotekanauki.pl/articles/2204540.pdf
Data publikacji:
2023
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
few-shot learning
attention metric
CNN
convolutional neural network
feature expression
wskaźnik uwagi
sieć neuronowa splotowa
cechy wyrażeń
Opis:
Deep learning methods benefit from data sets with comprehensive coverage (e.g., ImageNet, COCO, etc.), which can be regarded as a description of the distribution of real-world data. The models trained on these datasets are considered to be able to extract general features and migrate to a domain not seen in downstream. However, in the open scene, the labeled data of the target data set are often insufficient. The depth models trained under a small amount of sample data have poor generalization ability. The identification of new categories or categories with a very small amount of sample data is still a challenging task. This paper proposes a few-shot fine-grained image recognition method. Feature maps are extracted by a CNN module with an embedded attention network to emphasize the discriminative features. A channel-based feature expression is applied to the base class and novel class followed by an improved cosine similarity-based measurement method to get the similarity score to realize the classification. Experiments are performed on main few-shot benchmark datasets to verify the efficiency and generality of our model, such as Stanford Dogs, CUB-200, and so on. The experimental results show that our method has more advanced performance on fine-grained datasets.
Źródło:
Bulletin of the Polish Academy of Sciences. Technical Sciences; 2023, 71, 1; art. no. e144584
0239-7528
Pojawia się w:
Bulletin of the Polish Academy of Sciences. Technical Sciences
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A genetic algorithm based optimized convolutional neural network for face recognition
Autorzy:
Karlupia, Namrata
Mahajan, Palak
Abrol, Pawanesh
Lehana, Parveen K.
Powiązania:
https://bibliotekanauki.pl/articles/2201023.pdf
Data publikacji:
2023
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
convolutional neural network
genetic algorithm
deep learning
evolutionary technique
sieć neuronowa konwolucyjna
algorytm genetyczny
uczenie głębokie
technika ewolucyjna
Opis:
Face recognition (FR) is one of the most active research areas in the field of computer vision. Convolutional neural networks (CNNs) have been extensively used in this field due to their good efficiency. Thus, it is important to find the best CNN parameters for its best performance. Hyperparameter optimization is one of the various techniques for increasing the performance of CNN models. Since manual tuning of hyperparameters is a tedious and time-consuming task, population based metaheuristic techniques can be used for the automatic hyperparameter optimization of CNNs. Automatic tuning of parameters reduces manual efforts and improves the efficiency of the CNN model. In the proposed work, genetic algorithm (GA) based hyperparameter optimization of CNNs is applied for face recognition. GAs are used for the optimization of various hyperparameters like filter size as well as the number of filters and of hidden layers. For analysis, a benchmark dataset for FR with ninety subjects is used. The experimental results indicate that the proposed GA-CNN model generates an improved model accuracy in comparison with existing CNN models. In each iteration, the GA minimizes the objective function by selecting the best combination set of CNN hyperparameters. An improved accuracy of 94.5% is obtained for FR.
Źródło:
International Journal of Applied Mathematics and Computer Science; 2023, 33, 1; 21--31
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A High-Accuracy of Transmission Line Faults (TLFs) Classification Based on Convolutional Neural Network
Autorzy:
Fuada, S.
Shiddieqy, H. A.
Adiono, T.
Powiązania:
https://bibliotekanauki.pl/articles/1844462.pdf
Data publikacji:
2020
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
fault detection
fault classification
transmission lines
convolutional neural network
machine learning
Opis:
To improve power system reliability, a protection mechanism is highly needed. Early detection can be used to prevent failures in the power transmission line (TL). A classification system method is widely used to protect against false detection as well as assist the decision analysis. Each TL signal has a continuous pattern in which it can be detected and classified by the conventional methods, i.e., wavelet feature extraction and artificial neural network (ANN). However, the accuracy resulting from these mentioned models is relatively low. To overcome this issue, we propose a machine learning-based on Convolutional Neural Network (CNN) for the transmission line faults (TLFs) application. CNN is more suitable for pattern recognition compared to conventional ANN and ANN with Discrete Wavelet Transform (DWT) feature extraction. In this work, we first simulate our proposed model by using Simulink® and Matlab®. This simulation generates a fault signal dataset, which is divided into 45.738 data training and 4.752 data tests. Later, we design the number of machine learning classifiers. Each model classifier is trained by exposing it to the same dataset. The CNN design, with raw input, is determined as an optimal output model from the training process with 100% accuracy.
Źródło:
International Journal of Electronics and Telecommunications; 2020, 66, 4; 655-664
2300-1933
Pojawia się w:
International Journal of Electronics and Telecommunications
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A hybrid approach of a deep learning technique for real-time ECG beat detection
Autorzy:
Patro, Kiran Kumar
Prakash, Allam Jaya
Samantray, Saunak
Pławiak, Joanna
Tadeusiewicz, Ryszard
Pławiak, Paweł
Powiązania:
https://bibliotekanauki.pl/articles/2172118.pdf
Data publikacji:
2022
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
cardiac abnormalities
CAD
convolutional neural network
CNN
deep learning
ECG
electrocardiogram
supra ventricular ectopic beats
SVE
nieprawidłowości kardiologiczne
sieć neuronowa konwolucyjna
uczenie głębokie
EKG
elektrokardiogram
Opis:
This paper presents a new customized hybrid approach for early detection of cardiac abnormalities using an electrocardiogram (ECG). The ECG is a bio-electrical signal that helps monitor the heart’s electrical activity. It can provide health information about the normal and abnormal physiology of the heart. Early diagnosis of cardiac abnormalities is critical for cardiac patients to avoid stroke or sudden cardiac death. The main aim of this paper is to detect crucial beats that can damage the functioning of the heart. Initially, a modified Pan–Tompkins algorithm identifies the characteristic points, followed by heartbeat segmentation. Subsequently, a different hybrid deep convolutional neural network (CNN) is proposed to experiment on standard and real-time long-term ECG databases. This work successfully classifies several cardiac beat abnormalities such as supra-ventricular ectopic beats (SVE), ventricular beats (VE), intra-ventricular conduction disturbances beats (IVCD), and normal beats (N). The obtained classification results show a better accuracy of 99.28% with an F1 score of 99.24% with the MIT–BIH database and a descent accuracy of 99.12% with the real-time acquired database.
Źródło:
International Journal of Applied Mathematics and Computer Science; 2022, 32, 3; 455--465
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A hybrid two-stage SqueezeNet and support vector machine system for Parkinson’s disease detection based on handwritten spiral patterns
Autorzy:
Bernardo, Lucas Salvador
Damaševičius, Robertas
de Albuquerque, Victor Hugo C.
Maskeliūnas, Rytis
Powiązania:
https://bibliotekanauki.pl/articles/2055162.pdf
Data publikacji:
2021
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
Parkinson’s disease
spirography
convolutional neural network
deep learning
choroba Parkinsona
spirografia
sieć neuronowa konwolucyjna
uczenie głębokie
Opis:
Parkinson’s disease (PD) is the second most common neurological disorder in the world. Nowadays, it is estimated that it affects from 2% to 3% of the global population over 65 years old. In clinical environments, a spiral drawing task is performed to help to obtain the disease’s diagnosis. The spiral trajectory differs between people with PD and healthy ones. This paper aims to analyze differences between handmade drawings of PD patients and healthy subjects by applying the SqueezeNet convolutional neural network (CNN) model as a feature extractor, and a support vector machine (SVM) as a classifier. The dataset used for training and testing consists of 514 handwritten draws of Archimedes’ spiral images derived from heterogeneous sources (digital and paper-based), from which 296 correspond to PD patients and 218 to healthy subjects. To extract features using the proposed CNN, a model is trained and 20% of its data is used for testing. Feature extraction results in 512 features, which are used for SVM training and testing, while the performance is compared with that of other machine learning classifiers such as a Gaussian naive Bayes (GNB) classifier (82.61%) and a random forest (RF) (87.38%). The proposed method displays an accuracy of 91.26%, which represents an improvement when compared to pure CNN-based models such as SqueezeNet (85.29%), VGG11 (87.25%), and ResNet (89.22%).
Źródło:
International Journal of Applied Mathematics and Computer Science; 2021, 31, 4; 549--561
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A new method of cardiac sympathetic index estimation using a 1D-convolutional neural network
Autorzy:
Kołodziej, Marcin
Majkowski, Andrzej
Tarnowski, Paweł
Rak, Remigiusz Jan
Rysz, Andrzej
Powiązania:
https://bibliotekanauki.pl/articles/2090741.pdf
Data publikacji:
2021
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
epilepsy
seizure detection
seizure prediction
convolutional neural network
deep learning
ECG
HRV
cardiac sympathetic index
padaczka
wykrywanie napadu
przewidywanie napadu
splotowa sieć neuronowa
głęboka nauka
technika deep learning
EKG
wskaźnik współczulny serca
Opis:
Epilepsy is a neurological disorder that causes seizures of many different types. The article presents an analysis of heart rate variability (HRV) for epileptic seizure prediction. Considering that HRV is nonstationary, our research focused on the quantitative analysis of a Poincare plot feature, i.e. cardiac sympathetic index (CSI). It is reported that the CSI value increases before the epileptic seizure. An algorithm using a 1D-convolutional neural network (1D-CNN) was proposed for CSI estimation. The usability of this method was checked for 40 epilepsy patients. Our algorithm was compared with the method proposed by Toichi et al. The mean squared error (MSE) for testing data was 0.046 and the mean absolute percentage error (MAPE) amounted to 0.097. The 1D-CNN algorithm was also compared with regression methods. For this purpose, a classical type of neural network (MLP), as well as linear regression and SVM regression, were tested. In the study, typical artifacts occurring in ECG signals before and during an epileptic seizure were simulated. The proposed 1D-CNN algorithm estimates CSI well and is resistant to noise and artifacts in the ECG signal.
Źródło:
Bulletin of the Polish Academy of Sciences. Technical Sciences; 2021, 69, 3; e136921, 1--9
0239-7528
Pojawia się w:
Bulletin of the Polish Academy of Sciences. Technical Sciences
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A new method of cardiac sympathetic index estimation using a 1D-convolutional neural network
Autorzy:
Kołodziej, Marcin
Majkowski, Andrzej
Tarnowski, Paweł
Rak, Remigiusz Jan
Rysz, Andrzej
Powiązania:
https://bibliotekanauki.pl/articles/2173565.pdf
Data publikacji:
2021
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
epilepsy
seizure detection
seizure prediction
convolutional neural network
deep learning
ECG
HRV
cardiac sympathetic index
padaczka
wykrywanie napadu
przewidywanie napadu
splotowa sieć neuronowa
głęboka nauka
technika deep learning
EKG
wskaźnik współczulny serca
Opis:
Epilepsy is a neurological disorder that causes seizures of many different types. The article presents an analysis of heart rate variability (HRV) for epileptic seizure prediction. Considering that HRV is nonstationary, our research focused on the quantitative analysis of a Poincare plot feature, i.e. cardiac sympathetic index (CSI). It is reported that the CSI value increases before the epileptic seizure. An algorithm using a 1D-convolutional neural network (1D-CNN) was proposed for CSI estimation. The usability of this method was checked for 40 epilepsy patients. Our algorithm was compared with the method proposed by Toichi et al. The mean squared error (MSE) for testing data was 0.046 and the mean absolute percentage error (MAPE) amounted to 0.097. The 1D-CNN algorithm was also compared with regression methods. For this purpose, a classical type of neural network (MLP), as well as linear regression and SVM regression, were tested. In the study, typical artifacts occurring in ECG signals before and during an epileptic seizure were simulated. The proposed 1D-CNN algorithm estimates CSI well and is resistant to noise and artifacts in the ECG signal.
Źródło:
Bulletin of the Polish Academy of Sciences. Technical Sciences; 2021, 69, 3; art. no. e136921
0239-7528
Pojawia się w:
Bulletin of the Polish Academy of Sciences. Technical Sciences
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A novel method for automatic detection of arrhythmias using the unsupervised convolutional neural network
Autorzy:
Zhang, Junming
Yao, Ruxian
Gao, Jinfeng
Li, Gangqiang
Wu, Haitao
Powiązania:
https://bibliotekanauki.pl/articles/23944827.pdf
Data publikacji:
2023
Wydawca:
Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
Tematy:
convolutional neural network
arrhythmia detection
unsupervised learning
ECG classification
Opis:
In recent years, various models based on convolutional neural networks (CNN) have been proposed to solve the cardiac arrhythmia detection problem and achieved saturated accuracy. However, these models are often viewed as “blackbox” and lack of interpretability, which hinders the understanding of cardiologists, and ultimately hinders the clinical use of intelligent terminals. At the same time, most of these approaches are supervised learning and require label data. It is a time-consuming and expensive process to obtain label data. Furthermore, in human visual cortex, the importance of lateral connection is same as feed-forward connection. Until now, CNN based on lateral connection have not been studied thus far. Consequently, in this paper, we combines CNNs, lateral connection and autoencoder (AE) to propose the building blocks of lateral connection convolutional autoencoder neural networks (LCAN) for cardiac arrhythmia detection, which learn representations in an unsupervised manner. Concretely, the LCAN contains a convolution layer, a lateral connection layer, an AE layer, and a pooling layer. The LCAN detects salient wave features through the lateral connection layer. The AE layer and competitive learning is used to update the filters of the convolution network—an unsupervised process that ensures similar weight distribution for all adjacent filters in each convolution layer and realizes the neurons’ semantic arrangement in the LCAN. To evaluate the performances of the proposed model, we have implemented the experiments on the well-known MIT–BIH Arrhythmia Database. The proposed model yields total accuracies and kappa coefficients of 98% and 0.95, respectively. The experiment results show that the LCAN is not only effective, but also a useful tool for arrhythmia detection.
Źródło:
Journal of Artificial Intelligence and Soft Computing Research; 2023, 13, 3; 181--196
2083-2567
2449-6499
Pojawia się w:
Journal of Artificial Intelligence and Soft Computing Research
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A single upper limb pose estimation method based on the improved stacked hourglass network
Autorzy:
Peng, Gang
Zheng, Yuezhi
Li, Jianfeng
Yang, Jin
Powiązania:
https://bibliotekanauki.pl/articles/1838179.pdf
Data publikacji:
2021
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
convolutional neural network
stacked hourglass network
skeleton key point
single upper limb pose estimation
human machine coordination
Opis:
At present, most high-accuracy single-person pose estimation methods have high computational complexity and insufficient real-time performance due to the complex structure of the network model. However, a single-person pose estimation method with high real-time performance also needs to improve its accuracy due to the simple structure of the network model. It is currently difficult to achieve both high accuracy and real-time performance in single-person pose estimation. For use in human–machine cooperative operations, this paper proposes a single-person upper limb pose estimation method based on an end-to-end approach for accurate and real-time limb pose estimation. Using the stacked hourglass network model, a single-person upper limb skeleton key point detection model is designed. A deconvolution layer is employed to replace the up-sampling operation of the hourglass module in the original model, solving the problem of rough feature maps. Integral regression is used to calculate the position coordinates of key points of the skeleton, reducing quantization errors and calculations. Experiments show that the developed single-person upper limb skeleton key point detection model achieves high accuracy and that the pose estimation method based on the end-to-end approach provides high accuracy and real-time performance.
Źródło:
International Journal of Applied Mathematics and Computer Science; 2021, 31, 1; 123-133
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A Study on the Impact of Lombard Effect on Recognition of Hindi Syllabic Units Using CNN Based Multimodal ASR Systems
Autorzy:
Uma Maheswari, Sadasivam
Shahina, A.
Rishickesh, Ramesh
Nayeemulla Khan, A.
Powiązania:
https://bibliotekanauki.pl/articles/176415.pdf
Data publikacji:
2020
Wydawca:
Polska Akademia Nauk. Czasopisma i Monografie PAN
Tematy:
Lombard speech
multimodal ASR
throat microphone
visual speech
Convolutional Neural Network
Hidden Markov Model
late fusion
intermediate fusion
Opis:
Research work on the design of robust multimodal speech recognition systems making use of acoustic, and visual cues, extracted using the relatively noise robust alternate speech sensors is gaining interest in recent times among the speech processing research fraternity. The primary objective of this work is to study the exclusive influence of Lombard effect on the automatic recognition of the confusable syllabic consonant-vowel units of Hindi language, as a step towards building robust multimodal ASR systems in adverse environments in the context of Indian languages which are syllabic in nature. The dataset for this work comprises the confusable 145 consonant-vowel (CV) syllabic units of Hindi language recorded simultaneously using three modalities that capture the acoustic and visual speech cues, namely normal acoustic microphone (NM), throat microphone (TM) and a camera that captures the associated lip movements. The Lombard effect is induced by feeding crowd noise into the speaker’s headphone while recording. Convolutional Neural Network (CNN) models are built to categorise the CV units based on their place of articulation (POA), manner of articulation (MOA), and vowels (under clean and Lombard conditions). For validation purpose, corresponding Hidden Markov Models (HMM) are also built and tested. Unimodal Automatic Speech Recognition (ASR) systems built using each of the three speech cues from Lombard speech show a loss in recognition of MOA and vowels while POA gets a boost in all the systems due to Lombard effect. Combining the three complimentary speech cues to build bimodal and trimodal ASR systems shows that the recognition loss due to Lombard effect for MOA and vowels reduces compared to the unimodal systems, while the POA recognition is still better due to Lombard effect. A bimodal system is proposed using only alternate acoustic and visual cues which gives a better discrimination of the place and manner of articulation than even standard ASR system. Among the multimodal ASR systems studied, the proposed trimodal system based on Lombard speech gives the best recognition accuracy of 98%, 95%, and 76% for the vowels, MOA and POA, respectively, with an average improvement of 36% over the unimodal ASR systems and 9% improvement over the bimodal ASR systems.
Źródło:
Archives of Acoustics; 2020, 45, 3; 419-431
0137-5075
Pojawia się w:
Archives of Acoustics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A two-step fall detection algorithm combining threshold-based method and convolutional neural network
Autorzy:
Xu, Tao
Se, Haifeng
Liu, Jiahui
Powiązania:
https://bibliotekanauki.pl/articles/1848958.pdf
Data publikacji:
2021
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
wearable
fall detection
MPU6050
threshold-based method
convolutional neural network
Opis:
Falls are one of the leading causes of disability and premature death among the elderly. Technical solutions designed to automatically detect a fall event may mitigate fall-related health consequences by immediate medical assistance. This paper presents a wearable device called TTXFD based on MPU6050 which can collect triaxial acceleration signals. We have also designed a two-step fall detection algorithm that fuses threshold-based method (TBM) and machine learning (ML). The TTXFD exploits the TBM stage with low computational complexity to pick out and transmit suspected fall data (triaxial acceleration data). The ML stage of the two-step algorithm is implemented on a server which encodes the data into an image and exploits a fall detection algorithm based on convolutional neural network to identify a fall on the basis of the image. The experimental results show that the proposed algorithm achieves high sensitivity (97.83%), specificity (96.64%) and accuracy (97.02%) on the open dataset. In conclusion, this paper proposes a reliable solution for fall detection, which combines the advantages of threshold-based method and machine learning technology to reduce power consumption and improve classification ability.
Źródło:
Metrology and Measurement Systems; 2021, 28, 1; 23-40
0860-8229
Pojawia się w:
Metrology and Measurement Systems
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A weighted wrapper approach to feature selection
Autorzy:
Kusy, Maciej
Zajdel, Roman
Powiązania:
https://bibliotekanauki.pl/articles/2055180.pdf
Data publikacji:
2021
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
feature selection
wrapper approach
feature significance
weighted combined ranking
convolutional neural network
classification accuracy
selekcja cech
sieć neuronowa konwolucyjna
dokładność klasyfikacji
Opis:
This paper considers feature selection as a problem of an aggregation of three state-of-the-art filtration methods: Pearson’s linear correlation coefficient, the ReliefF algorithm and decision trees. A new wrapper method is proposed which, on the basis of a fusion of the above approaches and the performance of a classifier, is capable of creating a distinct, ordered subset of attributes that is optimal based on the criterion of the highest classification accuracy obtainable by a convolutional neural network. The introduced feature selection uses a weighted ranking criterion. In order to evaluate the effectiveness of the solution, the idea is compared with sequential feature selection methods that are widely known and used wrapper approaches. Additionally, to emphasize the need for dimensionality reduction, the results obtained on all attributes are shown. The verification of the outcomes is presented in the classification tasks of repository data sets that are characterized by a high dimensionality. The presented conclusions confirm that it is worth seeking new solutions that are able to provide a better classification result while reducing the number of input features.
Źródło:
International Journal of Applied Mathematics and Computer Science; 2021, 31, 4; 685--696
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Wyświetlanie 1-15 z 72

Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies