2017 | OriginalPaper | Buchkapitel
Entropy Based PAPR Reduction for STTC System Utilized for Classification of Epilepsy from EEG Signals Using PSD and SVM
verfasst von : S. K. Prabhakar, H. Rajaguru
Erschienen in: 3rd International Conference on Movement, Health and Exercise
Verlag: Springer Singapore
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Epilepsy is one of the major disorders of the brain that affect the nervous system and is characterized by the recurrent seizures. The day to day life of the patient is severely disturbed because of the abrupt and unpredictable nature of the epileptic seizures. An investigative technique which provides comprehensive information about the classification, analysis and diagnosis of brain conditions is Electroencephalography (EEG). The useful information about the different diseases affecting the brain especially epilepsy are given by the frequency and energy content of this signal. As the recordings made from the EEG are quite large and difficult to process, Power Spectral Density (PSD) is employed here to reduce the dimensions of the entire data. Then the dimensionally reduced EEG data is transmitted through the Space Time Trellis Coded Multiple Input Multiple Output Orthogonal Frequency Division Multiplexing (STTC MIMO OFDM) system. As the system suffers a high Peak to Average Power Ratio (PAPR), entropy based Partial Transmit Scheme (E-PTS) is proposed to reduce the PAPR and Bit Error Rate (BER) is analyzed in the receiver side. Also at the receiver side, Radial Basis Function Kernel Based Support Vector Machine (SVM) is employed to classify the epilepsy from EEG signals. The performance metrics analyzed here are Specificity, Sensitivity, Time Delay, Quality Value, Accuracy, Performance Index, PAPR and BER.