Machine learning based classification of EEG signal for detection of child epileptic seizure without snipping

The electroencephalogram (EEG) signal is very important in the diagnosis of epilepsy. Long-term EEG recordings of an epileptic patient contain a huge amount of EEG data. Therefore, detecting epileptic activity is a very demanding process that requires a detailed analysis of the entire length of the EEG data, usually performed by an expert. This paper evaluates machine learning classifiers' performance with their paradigms for classification of raw EEG signals into two classes, i.e., seizure and non-seizure. Here, the 13 descriptive features are taken into consideration and fed to the classifiers. Here, CHB-MIT Scalp EEG Database is used, which comprises paediatric subjects of 24 records. The performance of classifiers is evaluated categorically concerning gender and in total. The results confirmed that the fine KNN is the best classifier in males, females, and all subjects.