Wyniki wyszukiwania - BazTech

1

Automated detection of epileptic seizures using mixed-methodology: Wavelet-Chaos-KNN Classifier-Mutual Information

Mirzaei A., Ayatollahi A., Nasrabadi A. M.

Przegląd Elektrotechniczny

|

2011

|

R. 87, nr 4

220-223

EN

Electroencephalogram (EEG) is the brain signal that contains the valuable information about different states of the brain. In this study EEG signals are analyzed for evaluating epileptic seizures in these signals and their sub-bands and comparing epileptic states with other states. A discrete wavelet transform is applied for decompose the EEGs into its sub-bands. The chaotic behavior of EEGs is evaluated by means ol normalized Shannon and spectral entropies. Entropy method is presented for detection of epileptic seizures through the analysis of EEGs and their sub-bands. At the end the mixture K-nearest neighbor and mutual information method is applied as a classifier to classify the different states in EEGs and their sub-bands. This method is applied to three different groups of EEG signals: 1) healthy states, 2) epileptic states during a seizure-free interval (interictal EEG), 3) epileptic states during a seizure (ictal EEG). The proposed method could classify different states with 99% accuracy.

PL

Elektroencefalografia EEG jest analizą sygnału mózgu. W artykule przedstawiono metody analizy sygnału EEG stosowane w celu wykrycia epilepsji. Zastosowano dyskretną transformatę falkową do dekompozycji sygnału EEG. Wykorzystano metodę entropii do detekcji sygnału związanego z epilepsją. Metody zastosowano do trzech grup pacjentów: zdrowych, chorych na epilepsję i chorych w czasie ataku epilepsji.

2

Application of signal processing elements for the characteristics of acoustic emission pulses generated by partial discharges

Boczar T., Borucki S., Cichoń A., Lorenc M.

Molecular and Quantum Acoustics

|

2007

|

Vol. 28

23-38

EN

The subject matter of this paper refers to the issues connected with the application of modern numerical methods in processing and analysis of the signals measured by the acoustic emission method (AE) during high-power experiments carried out in laboratory conditions in the setups modelling basic partial discharge forms (PDs). The detailed cognitive aim of the research work was determining the possibilities and the application range of the short time Fourier transform (STFT) and wavelet transform in the analysis of the AE pulses generated by basic PD forms that can occur in oil insulation systems of such appliances as transformers, measuring transformers, bushing insulators, switchgears, and power condensers. The time – frequency analysis was carried out for the particular PDs from the point of view of determining differences and indicating common features for the frequency structures determined, for the positive and negative voltage polarizations separately. The research concentrated mainly on the following types of PDs: point-plane, multipoint-plane, multipoint-plane with a layer of pressboard, surface, generated in gas bubbles and on the indeterminate-potential particles moving in oil. In calculations using wavelet transformations basic types of analyzing functions, the so-called basic wavelets, were applied. When determining amplitude spectrograms of the AE pulses measured various types of observation windows were used. Moreover, for the approximation runs determined and for the particular details the autocorrelation functions (ACF) were calculated, and the probability density functions (PDF) were calculated to determine statistical properties. Also, frequency spectrum runs for the AE pulses measured and the diagrams corresponding with the details analyzed, which visualize the size of energy transferred at the particular decomposition levels, were determined. The paper presents the results of measurements and analyses of the AE pulses generated by the PDs in oil in the multipoint-plane with a layer of pressboard system.

3

Application Possibilities of The Statistical Analysis and Digital Processing Methods in the Characteristics of the AE Signals Generateg by PDs

Boczar T.

Molecular and Quantum Acoustics

|

2002

|

Vol. 23

63-82

EN

The subject matter of this paper refers to the improvement of the AE method used in the measurements of PDs occuring in oil insulation systems of power appliances. The deatailed subject matter, however, is connected with presenting appilacion possibilities of the descriptive statistics indicators, statistical analysis, and the methods of digital signal processing in the characterstics of the AE pulses generated by basic PD forms.