DEVELOPMENT OF AN EFFICIENT EPILEPSY CLASSIFICATION SYSTEM FROM EEG SIGNALS FOR TELEMEDICINE APPLICATION

The most prominent tool used in the clinical diagnosis and monitoring of the brain is the Electroencephalograph (EEG). With the help of several electrodes, EEG signals are recorded and for further processing it has to be transmitted through a versatile communication channel. In this paper, initially the dimensions of the raw EEG signal are reduced with the help of Independent Component Analysis (ICA) which is employed here as a dimensionality reduction technique. It is then transmitted through the Differential Space Time Block Coded (DSTBC) Multiple Input Multiple Output (MIMO) Orthogonal Frequency Division Multiplexing (OFDM) system. For the DSTBC MIMO-OFDM System, a Peak to Average Power Ratio (PAPR) reduction algorithm called Projection onto Convex Sets – Active Constellation Extension (POCS-ACE) Algorithm is employed to reduce the PAPR. At the Receiver side, a low Bit Error Rate (BER) is aimed. The receiver side is incorporated with Gaussian Mixture Model (GMM) Classifier to classify from the epilepsy from EEG signals. The Classification Performance Measures are considered in terms of Specificity, Sensitivity, Time Delay, Quality Values, Performance Index and Accuracy