Imbalance-aware Machine Learning for Epileptic Seizure Detection

Automatic epileptic seizure detection is a challenging task that could cope with sudden seizures and help epileptic patients to have a normal life. The electroencephalography (EEG) recording remains the most common method used for detecting epileptic seizures. The precision and accuracy of seizure detection are the most important elements in automatic EEG-based seizure detection systems, which could be achieved by training the classification models with relevant features. In this work, we propose a robust machine learning framework for epileptic seizure detection from EEG data. Imbalance class problem and high dimensional feature space issue have been handled for classification. Our approach has been tested on the largest EEG database (The Temple University Hospital EEG Seizure Corpus, TUSZ). A comparative study on three categories of data balancing techniques: costsensitive learning (weighting), oversampling and under sampling has been made. An efficient feature selection algorithm based on feature interaction graph analysis has been used for selecting minimal number of relevant inputs before classification. Results in terms of accuracy and area under the curve (AUC), have showed that the features subset selected using the graph-based method, balanced by the Synthetic Minority Over Sampling method (SMOTE) achieved the highest classification performance using random forest classifier.