2017 | OriginalPaper | Buchkapitel
Hadamard Transform Based PAPR Reduction for Telemedicine Applications Utilized for Epilepsy Classification
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
A set of long term associated neurological disorders which is characterized by seizures is epilepsy. Because of the abnormal electrical activities occurring in the brain, the occurrence of epileptic seizures become prominent. In epilepsy research, convulsions too are sometimes related to epileptic seizures. So to investigate and understand the brain’s electrical activity, recording the scalp is important and that can be done with the help of Electroencephalograph (EEG). The time consumption with the long term measurements is enormous and so reviewing it becomes quite a hectic task. So the need for an automatic detection of seizures is required. As the long term measurements produce a huge amount of data, it would be pretty difficult to process and so with the help of Independent Component Analysis (ICA), the dimensions of the data are reduced. Then it is transmitted via a Space Time Block Coded Multiple Input Single Output (2 x 1) Orthogonal Frequency Division Multiplexing (STBC MISO-OFDM) System. As the system has a high Peak to Average Power Ratio (PAPR), it is reduced with the help of Hadamard Based PAPR Reduction and then at the receiver the Bit Error Rate (BER) is computed. Also at the receiver side, the classifier employed is Linear Kernel Support Vector Machines (L-SVM). Finally the epilepsy risk level classification from EEG Signals is measured in terms in Specificity, Sensitivity, Accuracy, Time Delay and Quality Values.