Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Application of Fuzzy Logic for Epileptic Seizure Detection


Affiliations
1 Department of Electronics and Communication Engineering, Vignan Institute of Technology and Science, Deshmukhi-508284, Nalgonda Dist, A.P., India
2 Anurag Group of Institutions, Hyderabad, India
     

   Subscribe/Renew Journal


In this work fuzzy logic approach was presented for epileptic seizure detection. The EEG signal is decomposed into five sub bands using discrete wavelet transforms. Energy, Covariance, Inter quartile Range (IQR), and Median absolute deviation (MAD) features were extracted from each sub band and considered as the inputs for a fuzzy system Fuzzy rules were derived based on expert's knowledge and reasoning. For each sub band fuzzy system is applied the fuzzy output is combined from each sub band and threshold technique is applied to discriminate normal and epileptic. The overall classification accuracy of 97% was achieved.

Keywords

Electroencephalogram (EEG) Epileptic Seizures, Discrete Wavelet Transform (DWT).
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 218

PDF Views: 1




  • Application of Fuzzy Logic for Epileptic Seizure Detection

Abstract Views: 218  |  PDF Views: 1

Authors

Shaik Jakeer Husain
Department of Electronics and Communication Engineering, Vignan Institute of Technology and Science, Deshmukhi-508284, Nalgonda Dist, A.P., India
K. Srinivasa Rao
Anurag Group of Institutions, Hyderabad, India

Abstract


In this work fuzzy logic approach was presented for epileptic seizure detection. The EEG signal is decomposed into five sub bands using discrete wavelet transforms. Energy, Covariance, Inter quartile Range (IQR), and Median absolute deviation (MAD) features were extracted from each sub band and considered as the inputs for a fuzzy system Fuzzy rules were derived based on expert's knowledge and reasoning. For each sub band fuzzy system is applied the fuzzy output is combined from each sub band and threshold technique is applied to discriminate normal and epileptic. The overall classification accuracy of 97% was achieved.

Keywords


Electroencephalogram (EEG) Epileptic Seizures, Discrete Wavelet Transform (DWT).