Wyniki wyszukiwania - BazTech

1

The Application of Selected Hierarchical Clustering Methods for Classification the Acoustic Emission Signals Generated by Partial Discharges

Borucki Sebastian, Łuczak Jacek, Lorenc Marcin

Archives of Acoustics

|

2021

|

Vol. 46, No. 3

409--417

EN

The paper presents the results of the application of the hierarchical clustering methods for the classification of the acoustic emission (AE) signals generated by eight basic forms of partial discharges (PD), which can occur in paper-oil insulation of power transformers. Based on the registered AE signals from the particular PD forms, using a frequency descriptor in the form of the power spectral density (PSD) of the signal, their representation in the form of the set of points on plane XY was created. Next, these sets were subjected to analysis using research algorithms consisting of selected clustering methods. Based on the suggested numeric performance indicators, the analysis of the degree of reproduction of the actual distribution of points showing the particular time waveforms of the AE signals from eight adopted PD forms (PD classes) in the obtained clusters was carried out. As a result of the analyses carried out, the clustering algorithms of the highest effectiveness in the identification of all eight PD classes, classified simultaneously, where indicated. Within the research carried out, an attempt to draw general conclusions as to the selection of the most effective hierarchical clustering method studied and the similarity function to be used for classification of the selected basic PD forms.

2

Verification of the effectiveness of the selected clustering method used to analyse acoustic emission from partial discharges

Łuczak J.

Zeszyty Naukowe. Elektryka / Politechnika Opolska

|

2017

|

z. 75

51--52

EN

In this paper author describes idea of verification data reproduction in data clustering methods for analysis of acoustic emission generated by basic forms of partial discharges.

3

Use of clustering method to analyse acoustic emission generated by forms of partial discharges

Łuczak J.

Zeszyty Naukowe. Elektryka / Politechnika Opolska

|

2017

|

z. 75

49--50

EN

In this paper author describes ideas of using data clustering methods for analysis of acoustic emission generated by basic forms of partial discharges. Author presents one, exemplary clustering method – Ward’s method for three exemplary basic forms of partial discharges.

4

OFS Technique with DE Algorithm based on Correlation and Clustering method along with its Application

Vhansure Priyanka R, Phatak A A, Shimpi A S.

Annals of Computer Science and Information Systems

|

2017

|

Vol. 10

359--364

EN

Feature Selection is one of the important techniques in the Data mining. For the purpose of reducing the computational cost and reduction of noises to improve the accuracy of classification, the feature selection is very important technique for large-scale dataset. The result of feature selection has restricted to only batch learning. Different from batch learning technique online learning has selected by a motivational scalable, well-organized machine learning algorithm which has been used for large-scale dataset. In many defined techniques are not always conveniently helpful for the large-scale dataset. The real-world applications has huge amount of data which are having very long capacity or it costly to bring the entire set of attributes. Focusing on this loophole the concept of Online Feature Selection (OFS) is established. For every occurrence the online learning technique should be retrieve complete features/ attributes from large scale dataset volume. In OFS technique it is hard to online learner to keep a classifier that consist minimum and exact number of features. The OFS technique has primary defiance that, how to make accurate prediction from a large-scale dataset of iterations by using a fixed and small number of actively working features. In this article two different ways of OFS techniques are used its main work is to acquire minimum number of features. In first task a learner has allowed with the access of all the features to elect the subset of active features, and in the second task, a learner has allowed with access of only limited number of features for every iteration. We have used Differential Evolutionary (DE) algorithm in this study. By using new techniques such as Multiclass classification, DE algorithm, Correlation and clustering method the system is implemented to solve many real-world applications, problem and give their imperial performance analysis of the large-scale dataset.

5

Clustering method for evaluation of beat-to-beat variability in high resolution ECG /MCG signals

Steinhoff U., Lewandowski P., Burghoff M., Maniewski R., Trahms L.

Biocybernetics and Biomedical Engineering

|

1999

|

Vol. 19, no. 3

93-102

EN

A method for automatic signal analysis and signal averaging of multichannel electric or magnetic heart signals is proposed. The method is based on the calculation of a matrix of similarity between all ventricular complexes in the multichannel signal. This similarity matrix is used to group the heart beats into different clusters. The temporal alignment of heart beat signals belonging to one cluster is optimized for signal averaging. The similarity matrix contains also useful informations about physiological processes that alter the pattern of the heart activation. Various applications of the method are described.

PL

W pracy zaproponowano metodę automatycznej analizy i uśredniania wielokanałowych sygnałów czynności elektrycznej lub magnetycznej serca. Metoda jest oparta na wyznaczeniu tablicy współczynników określających podobieństwo między wszystkimi zespołami QRS, opisującymi czynność elektryczną komór, w sygnale wielokanałowym. Tablica podobieństwa jest wykorzystywana do grupowania cykli serca w osobne klasy. Przed uśrednianiem sygnałów jest optymalizowane czasowe położenie cykli serca należących do jednej klasy. Tablica podobieństwa zawiera również użyteczne informacje o fizjologicznych procesach, które zmieniają wzorzec aktywacji serca. W pracy przedstawiono także różne zastosowania opisanej metody.