Machine learning method based detection and diagnosis for epilepsy in EEG signal

The epileptic seizure can be detected using electroencephalogram (EEG) signals. The detection of epileptogenic region in brain is important for the detection of epilepsy disease. The signals from epileptogenic region in brain are focal signal and the signal from normal regions in brain is non-focal signal. Hence, the detection of focal signal is important for epilepsy disease detection. This paper proposes an automatic detection and diagnosis of EEG signals for epilepsy disease using soft computing approaches as adaptive neuro fuzzy inference system (ANFIS) and neural networks (NN). In this paper, the features from decomposed coefficients as bias (B), weight feature (W), entropy(E), activity feature (AF), mobility feature (MF), complexity feature (CF), skewness (S) and kurtosis (K) are extracted for the classification of EEG signals into either focal or non-focal signals for epilepsy disease detection and diagnosis. The detection of focal signal is achieved by ANFIS classifier and the diagnosis of the severity levels in focal signal is achieved by NN classification approach. The proposed method is used in many clinical diagnosis.

Automated summary

This study proposes an automatic detection and diagnosis method for epilepsy using soft computing approaches, extracting features from EEG signals and classifying them into focal or non-focal signals for epilepsy detection and diagnosis. The method has been applied in various clinical diagnoses.