In this paper, a new hybrid feature extraction method combining adaptive optimal radially Gaussian kernel (AORGK) time-frequency representation with two dimensional nonnegative matrix factorization (2DNMF) is proposed for partial discharge (PD) classification. Firstly, AORGK is applied to obtain the time-frequency matrices of PD ultra-high-frequency (UHF) signals. Then 2DNMF is employed to compress the AORGK amplitude (AORGKA) matrices to extract various feature vectors with different (d1, d2) combinations, i.e. (5, 5), (5, 10), (10, 5) and (10, 10). Finally, the extracted features are classified by fuzzy k nearest neighbor (FkNN) classifier and back propagation neural network (BPNN). 600 samples sam pled from four typical artificial defect models in Laboratory are adopting for testing of the proposed feature extraction algorithm. It is shown that the successful rate by FkNN and BPNN are all higher than 80%, and FkNN has superior classification accuracies than BPNN under four circumstances of (d1, d2) combinations. In addition, FkNN achieves the highest classification accuracy 93.73% with (10, 5) combination. The results demonstrate that it is feasible to apply the proposed algorithm to PD signal classification.
PL
W artykule przedstawiono nową hybrydową metodę klasyfikacji wyładowań niezupełnych (ang. Partial Discharge), wykorzystującą algorytm AORGK (ang. Adaptive Optimal Radially-Gaussian Kernel) o nieujemnej, matrycowej faktoryzacji dwuwymiarowej (ang. 2-Dimensional Nonnegative Matrix Factorization). W metodzie wykorzystano także algorytm k najbliższych sąsiadów oparty na teorii zbiorów rozmytych (ang. Fuzzy k Nearest Neighbour Classifier) oraz sieci neuronowe (ang. Back Propagation Neural Network).
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
EEG is the most popular potential non-invasive interface, mainly due to its fine temporal resolution, ease of use, portability and low set-up cost. However, it has some limitations. The main limitation is that EEG is frequently contaminated by various artifacts. In this paper, a novel approach to classify various electromyography and electrooculography artifacts in EEG signals is presented. EEG signals were acquired at the Department of Electrical and Electronics Engineering Karadeniz Technical University from three healthy human subjects in age groups between 28 and 30 years old and on two different days. Extracted feature vectors based on root mean square, polynomial fitting and Hjorth descriptors were classified by k-nearest neighbor algorithm. The proposed method was successfully applied to the data sets and achieved an average classification rate of 94% on the test data.
PL
W artykule przedstawiono nową metodę analizy sygnałów w technice EEG pod względem klasyfikacji błędów zakłóceniowych w wynikach badań elektromiografii i elektrookulografii. Badanie przeprowadzone zostało na podstawie rzeczywistych wyników EEG.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.