Open AccessAnalysis of EEG signal of specific epileptic patient prior to its occurrence
Author(s) -
Sachin Shrestha,
Rupesh Dahi Shrestha,
Amit Shah,
Bhoj Raj Thapa
Publication year - 2018
Publication title -
scitech nepal
Language(s) - English
Resource type - Journals
ISSN - 2091-1742
DOI - 10.3126/scitech.v13i1.23497
Subject(s) - electroencephalography , epilepsy , signal (programming language) , daubechies wavelet , pattern recognition (psychology) , epileptic seizure , artificial intelligence , feature (linguistics) , computer science , wavelet , discrete wavelet transform , wavelet transform , psychology , neuroscience , linguistics , philosophy , programming language
Epilepsy is a neurological disorder of brain and the electroencephalogram (EEG) signals are commonly used to detect the epileptic seizures, the result of abnormal electrical activity in the brain. This paper is focussed on the analysis of EEG signal to detect the presence of the epileptic seizure prior to its occurrence. The result could aid the individual in the initiation of delay sensitive diagnostic, therapeutic and alerting procedures. The methodology involves the multi-resolution analysis (MRA) of the EEG signals of epileptic patient. MRA is carried out using discrete wavelet transform with daubechies 8 as the mother wavelet. For EEG data, the database of MJT-BIH of one of the patient with 41 different cases is used. The result showed that a unique pattern is observed during the spectral analysis of the signal over different bands with positive predictive value of 100%, negative predictive value of 82.35% and the overall accuracy of 85.37%. This unique pattern, basically energy burst in two of the bands of the signal can be used as important feature for the early detection of the epileptic seizure. All the results have been simulated within the Matlab environment.