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 "Machine learning algorithm" wg kryterium: Temat

  Lista filtrów
Wyrównaj
Wyświetlanie 1-15 z 25
Tytuł:
A comprehensive study on the application of firefly algorithm in prediction of energy dissipation on block ramps
Autorzy:
Mahdavi-Meymand, Amin
Sulisz, Wojciech
Zounemat-Kermani, Mohammad
Powiązania:
https://bibliotekanauki.pl/articles/2087026.pdf
Data publikacji:
2022
Wydawca:
Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN
Tematy:
firefly algorithm
machine learning
energy dissipation
block ramp
Opis:
In this study novel integrative machine learning models embedded with the firefly algorithm (FA) were developed and employed to predict energy dissipation on block ramps. The used models include multi-layer perceptron neural network (MLPNN), adaptive neuro-fuzzy inference system (ANFIS), group method of data handling (GMDH), support vector regression (SVR), linear equation (LE), and nonlinear regression equation (NE). The investigation focused on the evaluation of the performance of standard and integrative models in different runs. The performances of machine learning models and the nonlinear equation are higher than the linear equation. The results also show that FA increases the performance of all applied models. Moreover, the results indicate that the ANFIS-FA is the most stable integrative model in comparison to the other embedded methods and reveal that GMDH and SVR are the most stable technique among all applied models. The results also show that the accuracy of the LE-FA technique is relatively low, RMSE=0.091. The most accurate results provide SVR-FA, RMSE=0.034.
Źródło:
Eksploatacja i Niezawodność; 2022, 24, 2; 200--210
1507-2711
Pojawia się w:
Eksploatacja i Niezawodność
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A real-valued genetic algorithm to optimize the parameters of support vector machine for classification of multiple faults in NPP
Autorzy:
Amer, F. Z.
El-Garhy, A. M.
Awadalla, M. H.
Rashad, S. M.
Abdien, A. K.
Powiązania:
https://bibliotekanauki.pl/articles/147652.pdf
Data publikacji:
2011
Wydawca:
Instytut Chemii i Techniki Jądrowej
Tematy:
support vector machine (SVM)
fault classification
multi fault classification
genetic algorithm (GA)
machine learning
Opis:
Two parameters, regularization parameter c, which determines the trade off cost between minimizing the training error and minimizing the complexity of the model and parameter sigma (σ) of the kernel function which defines the non-linear mapping from the input space to some high-dimensional feature space, which constructs a non-linear decision hyper surface in an input space, must be carefully predetermined in establishing an efficient support vector machine (SVM) model. Therefore, the purpose of this study is to develop a genetic-based SVM (GASVM) model that can automatically determine the optimal parameters, c and sigma, of SVM with the highest predictive accuracy and generalization ability simultaneously. The GASVM scheme is applied on observed monitored data of a pressurized water reactor nuclear power plant (PWRNPP) to classify its associated faults. Compared to the standard SVM model, simulation of GASVM indicates its superiority when applied on the dataset with unbalanced classes. GASVM scheme can gain higher classification with accurate and faster learning speed.
Źródło:
Nukleonika; 2011, 56, 4; 323-332
0029-5922
1508-5791
Pojawia się w:
Nukleonika
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A rule based machine learning approach to the nonlinear multifingered robot gripper problem
Autorzy:
Abu-Zitar, R.
Al-Fahed Nuseirat, A. M.
Powiązania:
https://bibliotekanauki.pl/articles/970099.pdf
Data publikacji:
2005
Wydawca:
Polska Akademia Nauk. Instytut Badań Systemowych PAN
Tematy:
zacisk robota
programowanie ewolucyjne
komputerowe uczenie się
robot gripper
nonlinear complementarity problem (NCP)
Evolutionary Programming (EP)
machine learning
nearest-classifier-algorithm
Opis:
In this paper, we present a novel method that utilizes the accumulation of knowledge in a rule base for solving the nonlinear frictional gripper problem for both the isotropic and orthotropic cases. The knowledge is discovered and accumulated in a rule base with the aid of a genetic based machine learning mechanism. This machine learning mechanism extracts rules for solving the problem with the help of the Evolutionary Programming [EP) algorithm. The retrievals are done using the nearest-classifier-algorithm. This approach provides online solutions for the problem, and establishes a dynamic and evolving environment that adapts with new and sudden changes on the grip specifications or on the external forces. The resulting grasping forces using the presented method are compared with grasping forces obtained using other methods, such as the Complementarity Problems. The proposed online method could update the needed grasping forces to keep firm grip if the configuration of the forces externally applied to the object is changed. Numerical examples that illustrate the proposed method are presented.
Źródło:
Control and Cybernetics; 2005, 34, 2; 553-573
0324-8569
Pojawia się w:
Control and Cybernetics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A survey on prediction of diabetes using classification algorithms
Autorzy:
Khanwalkar, A.
Soni, R.
Powiązania:
https://bibliotekanauki.pl/articles/1818807.pdf
Data publikacji:
2021
Wydawca:
Stowarzyszenie Komputerowej Nauki o Materiałach i Inżynierii Powierzchni w Gliwicach
Tematy:
diabetes
diabetes prediction
algorithm
data mining
machine learning
cukrzyca
algorytm
eksploracja danych
uczenie maszynowe
Opis:
Purpose: Diabetes is a chronic disease that pays for a large proportion of the nation's healthcare expenses when people with diabetes want medical care continuously. Several complications will occur if the polymer disorder is not treated and unrecognizable. The prescribed condition leads to a diagnostic center and a doctor's intention. One of the real-world subjects essential is to find the first phase of the polytechnic. In this work, basically a survey that has been analyzed in several parameters within the poly-infected disorder diagnosis. It resembles the classification algorithms of data collection that plays an important role in the data collection method. Automation of polygenic disorder analysis, as well as another machine learning algorithm. Design/methodology/approach: This paper provides extensive surveys of different analogies which have been used for the analysis of medical data, For the purpose of early detection of polygenic disorder. This paper takes into consideration methods such as J48, CART, SVMs and KNN square, this paper also conducts a formal surveying of all the studies, and provides a conclusion at the end. Findings: This surveying has been analyzed on several parameters within the poly-infected disorder diagnosis. It resembles that the classification algorithms of data collection plays an important role in the data collection method in Automation of polygenic disorder analysis, as well as another machine learning algorithm. Practical implications: This paper will help future researchers in the field of Healthcare, specifically in the domain of diabetes, to understand differences between classification algorithms. Originality/value: This paper will help in comparing machine learning algorithms by going through results and selecting the appropriate approach based on requirements.
Źródło:
Journal of Achievements in Materials and Manufacturing Engineering; 2021, 104, 2; 77--84
1734-8412
Pojawia się w:
Journal of Achievements in Materials and Manufacturing Engineering
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Analiza istotności cech znamion skórnych dla celów diagnostyki czerniaka złośliwego
Skin lesion features analysis for malignant melanoma classification
Autorzy:
Mikołajczyk, A.
Grochowski, M.
Powiązania:
https://bibliotekanauki.pl/articles/268540.pdf
Data publikacji:
2018
Wydawca:
Politechnika Gdańska. Wydział Elektrotechniki i Automatyki
Tematy:
algorytm ewolucyjny
uczenie maszynowe
sieci neuronowe
systemy wspomagania decyzji
evolutionary algorithm
neural networks
decision support system
machine learning
Opis:
Pomimo dynamicznego rozwoju metod uczenia maszynowego i ich wdrażania do praktyki lekarskiej, automatyczna analiza znamion skórnych wciąż jest nierozwiązanym problemem. Poniższy artykuł proponuje zastosowanie algorytmu ewolucyjnego do zaprojektowania, wytrenowania i przetestowania całych populacji klasyfikatorów (sztucznych sieci neuronowych) oraz ich iteracyjnego udoskonalania w każdej kolejnej populacji, w celu osiągnięcia jak najlepszej dokładności klasyfikacji znamion skórnych. Algorytm zwraca optymalny zestaw cech opisujących obraz dermatoskopowy wraz z proponowaną architekturą sieci neuronowej. Uzyskano dokładność równą 85,83%, swoistość równą 79,07% oraz czułość równą 92,60%.
Despite the dynamic development of machine learning methods, automatic analysis of skin lesions is still open issue. The following article proposes the use of an evolutionary algorithm to design, train, and to test a whole population of classifiers (artificial neural networks) and to iteratively improve them in each subsequent population, in order to achieve the best possible accuracy in the classification of skin lesions task. The algorithm returns an optimal set of features describing the dermatoscopic image together with the proposed architecture of the neural network. High classification results were obtained, in particular: accuracy equal to 85.83%, specificity 79.07% and sensitivity 92.60%.
Źródło:
Zeszyty Naukowe Wydziału Elektrotechniki i Automatyki Politechniki Gdańskiej; 2018, 60; 67-70
1425-5766
2353-1290
Pojawia się w:
Zeszyty Naukowe Wydziału Elektrotechniki i Automatyki Politechniki Gdańskiej
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Analiza wybranych metod tworzenia sztucznej inteligencji na przykładzie popularnej gry w karty
Analysis of selected methods of creating artificial intelligence on the example of a popular card game
Autorzy:
Gałka, Łukasz
Dzieńkowski, Mariusz
Powiązania:
https://bibliotekanauki.pl/articles/98306.pdf
Data publikacji:
2020
Wydawca:
Politechnika Lubelska. Instytut Informatyki
Tematy:
artificial intelligence
machine learning
algorithm efficiency evaluation
computer games
sztuczna inteligencja
uczenie maszynowe
ocena skuteczności algorytmów
gry komputerowe
Opis:
The aim of the article was to analyze selected methods of creating artificial intelligence in a popular card game. Two experiments were conducted: with a human and with a computer. The following algorithms were analyzed: random, min-max, based on a neural network, statistical and statistical with the use of “cheating” technique. The examined parameters were as follows: efficiency, execution time, number of implementation code lines, implementation time and training duration. The indicator with the greatest impact on the selection of the most optimal method was efficiency. The research has shown no difference in efficiency for the neural network-based algorithm and the statistical algorithm. In other cases, the differences in this feature were significant. The use of the “cheating” technique has increased the efficiency.
Celem artykułu była analiza wybranych metod tworzenia sztucznej inteligencji w popularnej grze w karty. Zostały przeprowadzone dwa eksperymenty: z człowiekiem oraz z komputerem. Analizie poddano algorytmy: losowy, minmax, bazujący na sieci neuronowej, statystyczny oraz statystyczny z użyciem techniki „oszukiwania”. Zbadano takie parametry jak: skuteczność, czas wykonania, liczbę linii kodu implementacji, czas implementacji oraz czas trwania treningu. Wskaźnikiem mającym największy wpływ na wybór najbardziej optymalnej metody była skuteczność. Badania wykazały brak różnic w skuteczności dla algorytmu bazującego na sieci neuronowej i algorytmu statystycznego. W pozostałych przypadkach różnice tej cechy były istotne. Użycie techniki „oszukiwania” zwiększyło skuteczność.
Źródło:
Journal of Computer Sciences Institute; 2020, 16; 233-240
2544-0764
Pojawia się w:
Journal of Computer Sciences Institute
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Applicability of artificial intelligence in smart healthcare systems for automatic detection of Parkinson’s Disease
Autorzy:
Pallathadka, Harikumar
Padminivalli V., S.J.R.K.
Vasavi, M.
Nancy, P.
Naved, Mohd
Kumar, Harish
Ray, Samrat
Powiązania:
https://bibliotekanauki.pl/articles/38709253.pdf
Data publikacji:
2024
Wydawca:
Instytut Podstawowych Problemów Techniki PAN
Tematy:
Parkinson’s disease
detection
machine learning
relief algorithm
LDA algorithm
SVM-RBF
accuracy
sensitivity
specificity
choroba Parkinsona
wykrywanie
nauczanie maszynowe
algorytm ulgi
Algorytm LDA
dokładność
wrażliwość
specyficzność
Opis:
Parkinson’s disease is associated with memory loss, anxiety, and depression in the brain. Problems such as poor balance and difficulty during walking can be observed in addition to symptoms of impaired posture and rigidity. The field dedicated to making computers capable of learning autonomously, without having to be explicitly programmed, is known as machine learning. An approach to the diagnosis of Parkinson’s disease, which is based on artificial intelligence, is discussed in this article. The input for this system is provided through photographic examples of Parkinson’s disease patient handwriting. Received photos are preprocessed using the relief feature option to begin the process. This is helpful in the process of selecting characteristics for the identification of Parkinson’s disease. After that, the linear discriminant analysis (LDA) algorithm is employed to reduce the dimensions, bringing down the total number of dimensions that are present in the input data. The photos are then classified via radial basis function-support vector machine (SVM-RBF), k-nearest neighbors (KNN), and naive Bayes algorithms, respectively.
Źródło:
Computer Assisted Methods in Engineering and Science; 2024, 31, 2; 175-185
2299-3649
Pojawia się w:
Computer Assisted Methods in Engineering and Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Artificial intelligence-powered pulse sequences in nuclear magnetic resonance and magnetic resonance imaging: historical trends, current innovations and perspectives
Autorzy:
Tokarz, Paweł
Powiązania:
https://bibliotekanauki.pl/articles/35508129.pdf
Data publikacji:
2024
Wydawca:
Radomskie Towarzystwo Naukowe
Tematy:
artificial intelligence
machine learning
evolutionary algorithm
artificial neural network
nuclear magnetic resonance
magnetic resonance imaging
pulse sequence
shaped pulse
sztuczna inteligencja
uczenie maszynowe
algorytm ewolucyjny
sztuczna sieć neuronowa
magnetyczny rezonans jądrowy
rezonans magnetyczny
sekwencja impulsów
impuls ukształtowany
Opis:
This review article explores the historical background and recent advances in the application of artificial intelligence (AI) in the development of radiofrequency pulses and pulse sequences in nuclear magnetic resonance spectroscopy (NMR) and imaging (MRI). The introduction of AI into this field, which traces back to the late 1970s, has recently witnessed remarkable progress, leading to the design of specialized frameworks and software solutions such as DeepRF, MRzero, and GENETICS-AI. Through an analysis of literature and case studies, this review tracks the transformation of AI-driven pulse design from initial proof-of-concept studies to comprehensive scientific programs, shedding light on the potential implications for the broader NMR and MRI communities. The fusion of artificial intelligence and magnetic resonance pulse design stands as a promising frontier in spectroscopy and imaging, offering innovative enhancements in data acquisition, analysis, and interpretation across diverse scientific domains.
Źródło:
Scientiae Radices; 2024, 3, 1; 30-52
2956-4808
Pojawia się w:
Scientiae Radices
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Automatic identification of malfunctions of large turbomachinery during transient states with genetic algorithm optimization
Autorzy:
Barszcz, Tomasz
Zabaryłło, Mateusz
Powiązania:
https://bibliotekanauki.pl/articles/2052104.pdf
Data publikacji:
2022
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
machine learning
fault detection
transient
turbine generator
genetic algorithm
Opis:
Turbines and generators operating in the power generation industry are a major source of electrical energy worldwide. These are critical machines and their malfunctions should be detected in advance in order to avoid catastrophic failures and unplanned shutdowns. A maintenance strategy which enables to detect malfunctions at early stages of their existence plays a crucial role in facilities using such types of machinery. The best source of data applied for assessment of the technical condition are the transient data measured during start-ups and coast-downs. Most of the proposed methods using signal decomposition are applied to small machines with a rolling element bearing in steady-state operation with a shaft considered as a rigid body. The machines examined in the authors’ research operate above their first critical rotational speed interval and thus their shafts are considered to be flexible and are equipped with a hydrodynamic sliding bearing. Such an arrangement introduces significant complexity to the analysis of the machine behavior, and consequently, analyzing such data requires a highly skilled human expert. The main novelty proposed in the paper is the decomposition of transient vibration data into components responsible for particular failure modes. The method is automated and can be used for identification of turbogenerator malfunctions. Each parameter of a particular decomposed function has its physical representation and can help the maintenance staff to operate the machine properly. The parameters can also be used by the managing personnel to plan overhauls more precisely. The method has been validated on real-life data originating from a 200 MW class turbine. The real-life field data, along with the data generated by means of the commercial software utilized in GE’s engineering department for this particular class of machines, was used as the reference data set for an unbalanced response during the transients in question.
Źródło:
Metrology and Measurement Systems; 2022, 29, 1; 175-190
0860-8229
Pojawia się w:
Metrology and Measurement Systems
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Building computer vision systems using machine learning algorithms
Autorzy:
Boyko, N.
Sokil, N.
Powiązania:
https://bibliotekanauki.pl/articles/410768.pdf
Data publikacji:
2017
Wydawca:
Polska Akademia Nauk. Oddział w Lublinie PAN
Tematy:
algorithm
information system
neural network
machine learning
client-server architecture
script
artificial system
machine learning algorithms
algorytm
systemy informacyjne
sieci neuronowe
systemy uczące
architektura klient-serwer
skrypt
Opis:
In this paper theoretic aspects of machine learning system in the field of computer vision is considered. There are presented methods of behavior analysis. There are offered tasks and problems associated with building systems using machine learning algorithm. The paper provides signs of problems that can be solved by using machine learning algorithms There is demonstrated step by step construction of computer vision system. The paper provides the algorithm of solving the problem of binary (two classes) classification for demonstration the machine learning algorithm possibilities in image recognition field, which can recognize the gender of the person on the photo. Aspects related to the search of data processing are also considered. There is analyzed the search of optimal parameters for algorithms. An interpretation of results in machine learning algorithm is provided. Binarization methods in machine learning algorithm are offered. There is analyzed the technology for improving the accuracy of machine learning algorithm. There are proposed ways to improve computer vision system in neural systems. Also there are analyzed large software modules that work using machine learning systems. The article provides prospects of powerful information technologies, which are necessary for the proper data selection in learning and configuration of feature extraction algorithm to create a computer vision system.
Źródło:
ECONTECHMOD : An International Quarterly Journal on Economics of Technology and Modelling Processes; 2017, 6, 2; 15-20
2084-5715
Pojawia się w:
ECONTECHMOD : An International Quarterly Journal on Economics of Technology and Modelling Processes
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
CellProfiler and WEKA Tools: Image Analysis for Fish Erythrocytes Shape and Machine Learning Model Algorithm Accuracy Prediction of Dataset
Autorzy:
Talapatra, Soumendra Nath
Chaudhuri, Rupa
Ghosh, Subhasis
Powiązania:
https://bibliotekanauki.pl/articles/1193348.pdf
Data publikacji:
2021
Wydawca:
Przedsiębiorstwo Wydawnictw Naukowych Darwin / Scientific Publishing House DARWIN
Tematy:
Automatic image analysis
CellProfiler tool
Fish erythrocytes quantification
Machine learning algorithm
Model classifier accuracy
Shapes measurement
WEKA tool
Opis:
The first part of the study was detected the number of cells and measurement of shape of cells, cytoplasm, and nuclei in an image of Giemsa-stained of fish peripheral erythrocytes by using CellProfiler (CP, version 2.1.0) tool, an image analysis tool. In the second part, it was evaluated machine learning (ML) algorithm models viz. BayesNet (BN), NaiveBayes (NB), logistic regression (LR), Lazy.KStar (K*), decision tree (DT) J48, Random forest (RF) and Random tree (RT) in the WEKA tool (version 3.8.5) for the prediction of the accuracy of the dataset generated from an image. The CP predicts the numbers and individual cellular area shape (arbitrary unit) of cells, cytoplasm, and nuclei as primary, secondary, and tertiary object data in an image. The performance of model accuracy of studied ML algorithm classifications as per correctly and incorrectly classified instances, the highest values were observed in RF and RT followed by K*, LR, BN and DTJ48 and lowest in NB as per training and testing set of correctly classified instances. In case of performance accuracy of class for K value, the highest values were observed in RF and RT followed by K*, LR, BN and DTJ48 and lowest in NB while lowest values were obtained for mean absolute error (MAE) and root mean squared error (RMSE) in case of RT followed by RF, K*, LR, BN and DTJ48 and comparatively highest value in case of NB as per training and testing set. In conclusion, both tools performed well as an image to the dataset and obtained dataset to rich information through ML modelling and future study in WEKA tool can easily be analysed many biological big data to predict classifier accuracy.
Źródło:
World Scientific News; 2021, 154; 101-116
2392-2192
Pojawia się w:
World Scientific News
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Clothing Image Classification with a Dragonfly Algorithm Optimised Online Sequential Extreme Learning Machine
Klasyfikacja obrazu odzieży za pomocą zoptymalizowanego algorytmu Dragonfly sekwencyjnej maszyny uczącej się
Autorzy:
Li, Jianqiang
Shi, Weimin
Yang, Donghe
Powiązania:
https://bibliotekanauki.pl/articles/1419412.pdf
Data publikacji:
2021
Wydawca:
Sieć Badawcza Łukasiewicz - Instytut Biopolimerów i Włókien Chemicznych
Tematy:
Dragonfly algorithm
Online Sequential Extreme Learning Machine
clothing image classification
optimised parameter
algorytm Dragonfly
OSELM
maszyna ucząca się
klasyfikacja obrazu odzieży
parametr zoptymalizowany
Opis:
This study proposes a solution for the issue of the low classification accuracy of clothing images. Using Fashion-MNIST as the clothing image dataset, we propose a clothing image classification technology based on an online sequential extreme learning machine (OSELM) optimised by the dragonfly algorithm (DA). First, we transform the Fashion-MNIST dataset into a data set that we extract from the corresponding grey image. Then, considering that the input weight and hidden layer bias of an OSELM are generated randomly, a DA is proposed to optimise the input weight and hidden layer bias of the OSELM to reduce the influence of random generation on the classification results. Finally, the optimised OSELM is applied to the clothing image classification. Compared to the other seven types of classification algorithms, the proposed clothing image classification model with the DA-optimised OSELM reached 93.98% accuracy when it contained 350 hidden nodes. Its performance was superior to other algorithms that were configured with the same number of hidden nodes. From a stability analysis of the box-plot, it was found that there were no outliers exhibited by the DA-OSELM model, whereas some other models had outliers or had lower stability compared to the model proposed, thereby validating the efficacy of the solution proposed.
W pracy zaproponowano rozwiązanie problemu niskiej dokładności klasyfikacyjnej obrazów odzieży. Wykorzystując Fashion-MNIST jako zbiór danych obrazu odzieży, zaproponowano technologię klasyfikacji obrazów odzieży w oparciu o sekwencyjną maszynę uczącą się (OSELM) zoptymalizowaną przez algorytm Dragonfly (DA). Najpierw przekształcono zbiór danych Fashion-MNIST w zestaw danych, który wyodrębniono z obrazu. Następnie, biorąc pod uwagę, że waga wejściowa i odchylenie warstwy ukrytej OSELM były generowane losowo, w celu zmniejszenia wpływu generowania losowego na wyniki klasyfikacji zaproponowano DA w celu optymalizacji wagi wejściowej i obciążenia warstwy ukrytej OSELM. Następnie, zoptymalizowany OSELM zastosowano do klasyfikacji obrazu odzieży. W porównaniu z pozostałymi siedmioma typami algorytmów klasyfikacji, proponowany model klasyfikacji obrazu odzieży ze zoptymalizowanym przez DA OSELM osiągnął dokładność 93,98%. Jego wydajność przewyższyła inne algorytmy. Na podstawie analizy stabilności wykresu stwierdzono, że nie było wartości odstających wykazywanych przez model DA-OSELM, podczas gdy niektóre inne modele miały wartości odstające lub miały niższą stabilność w porównaniu z proponowanym modelem, potwierdzono w ten sposób skuteczność proponowanego rozwiązania.
Źródło:
Fibres & Textiles in Eastern Europe; 2021, 3 (147); 91-96
1230-3666
2300-7354
Pojawia się w:
Fibres & Textiles in Eastern Europe
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Cost-sensitive feature selection
Selekcja cech z uwzględnieniem kosztu ich pozyskania
Autorzy:
Ciupke, K.
Powiązania:
https://bibliotekanauki.pl/articles/327830.pdf
Data publikacji:
2006
Wydawca:
Polska Akademia Nauk. Polskie Towarzystwo Diagnostyki Technicznej PAN
Tematy:
selekcja cech
algorytm mrówkowy
uczenie maszynowe
sztuczna inteligencja
diagnostyka techniczna
feature selection
ant algorithm
machine learning
artificial intelligence
technical diagnostics
Opis:
The paper concerns the selection of features in the technical diagnostics domain. The author focused his attention on a wrapper approach. In this approach an application of the ant algorithm as a search engine is proposed. The proposed method of so-called ant wrapper approach is presented. The method takes advantage of cost of features, where the cost is connected with the cost of sensors. The algorithm as a pseudo-code and some results of a verification experiment are shown. The verification was carried out on data derived from an active diagnostic experiment concerning a rotating machine. The obtained results show, that the proposed method could allow to reduce the number of used sensors.
W artykule opisano metodę selekcji cech z zastosowaniem algorytmu mrówkowego. Metoda pozwala także na uwzględnienie kosztu atrybutu, przy czym jego koszt związany jest z kosztem pozyskanie sygnału diagnostycznego. W przypadku gdy sygnał ten jest już wykorzystywany uznaje się, że koszt wyznaczenia danej cechy jest pomijalnie mały. Metodę przedstawiono w postaci pseudo-kodu i zweryfikowano dla danych pochodzących z czynnego eksperymentu diagnostycznego. Uzyskane wyniki pokazują, że istnieje możliwość ograniczenia liczby stosowanych czujników.
Źródło:
Diagnostyka; 2006, 2(38); 45-48
1641-6414
2449-5220
Pojawia się w:
Diagnostyka
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Designing Smart Antennas Using Machine Learning Algorithms
Autorzy:
Samantaray, Barsa
Das, Kunal Kumar
Roy, Jibendu Sekhar
Powiązania:
https://bibliotekanauki.pl/articles/27312957.pdf
Data publikacji:
2023
Wydawca:
Instytut Łączności - Państwowy Instytut Badawczy
Tematy:
artificial neural network
decision tree
ensemble algorithm
machine learning
smart antenna
support vector machine
Opis:
Smart antenna technologies improve spectral efficiency, security, energy efficiency, and overall service quality in cellular networks by utilizing signal processing algorithms that provide radiation beams to users while producing nulls for interferers. In this paper, the performance of such ML solutions as the support vector machine (SVM) algorithm, the artificial neural network (ANN), the ensemble algorithm (EA), and the decision tree (DT) algorithm used for forming the beam of smart antennas are compared. A smart antenna array made up of 10 half-wave dipoles is considered. The ANN method is better than the remaining approaches when it comes to achieving beam and null directions, whereas EA offers better performance in terms of reducing the side lobe level (SLL). The maximum SLL is achieved using EA for all the user directions. The performance of the ANN algorithm in terms of forming the beam of a smart antenna is also compared with that of the variable-step size adaptive algorithm.
Źródło:
Journal of Telecommunications and Information Technology; 2023, 4; 46--52
1509-4553
1899-8852
Pojawia się w:
Journal of Telecommunications and Information Technology
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Forecasting short-term electric load using extreme learning machine with improved tree seed algorithm based on Lévy flight
Autorzy:
Chen, Xuan
Przystupa, Krzysztof
Ye, Zhiwei
Chen, Feng
Wang, Chunzhi
Liu, Jinhang
Gao, Rong
Wei, Ming
Kochan, Orest
Powiązania:
https://bibliotekanauki.pl/articles/2087016.pdf
Data publikacji:
2022
Wydawca:
Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN
Tematy:
short-term electric load forecast
extreme learning machine
Lévy flight
tree-seed algorithm
Kernel principal component analysis
Opis:
In recent years, forecasting has received increasing attention since it provides an important basis for the effective operation of power systems. In this paper, a hybrid method, composed of kernel principal component analysis (KPCA), tree seed algorithm based on Lévy flight (LTSA) and extreme learning machine (ELM), is proposed for short-term load forecasting. Specifically, the randomly generated weights and biases of ELM have a significant impact on the stability of prediction results. Therefore, in order to solve this problem, LTSA is utilized to obtain the optimal parameters before the prediction process is executed by ELM, which is called LTSA-ELM. Meanwhile, the input data is extracted by KPCA considering the sparseness of the electric load data and used as the input of LTSA-ELM model. The proposed method is tested on the data from European network on intelligent technologies (EUNITE) and experimental results demonstrate the superiority of the proposed approaches compared to the other methods involved in the paper.
Źródło:
Eksploatacja i Niezawodność; 2022, 24, 2; 153--162
1507-2711
Pojawia się w:
Eksploatacja i Niezawodność
Dostawca treści:
Biblioteka Nauki
Artykuł
Wyświetlanie 1-15 z 25

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