PERFORMANCE ANALYSIS OF EXTREME LEARNING MACHINES IN DETECTION AND CLASSIFICATION OF EPILEPSY RISK LEVELS FROM EEG SIGNALS

The motto of this paper is to analyze the performance of Code converter and Extreme Learning Machine (ELM) as the classifiers for classifications of the epilepsy risk levels obtained from extracted features from EEG signals. The code converter acts as a level one classifier. The seven features like energy, variance, positive and negative peaks, spike and sharp waves, events, average duration and covariance are extracted from EEG signals. A study of twenty patients is reported in this paper. The performance of the code converter and ELM classifiers are compared based on the parametric metrics such as Performance Index (PI) and Quality Value (QV). The Performance Index and Quality Value of Code Converters are at lower value of 40% and 6.5 respectively. The highest PI of 93.1% and QV of 23.1 are attained at ELM with twenty hidden neuron. All the ELM architecture is settled at PI value of more than 90% at QV of 20.