Because of unusual discharges in the brain, epilepsy occurs. During epilepsy, the electrical activities become more intense because of the temporary disruptions happening to normal activities and functions of brain. Epilepsy is widely characterized by recurrent seizures and is one of the most common brain disorders. To evaluate the epileptic patients, a non-invasive tool called Electroencephalography (EEG) is used. To examine the patterns of the brain and to assist in the diagnosis of epilepsy, EEG is very helpful. As the recordings of the EEG are too large to process, certain kind of dimensionality reduction technique is required to reduce the dimensions of the EEG data. The dimensionality reduction technique used here is Fuzzy Mutual Information (FMI). The dimensionally reduced data is then transmitted through the Space Time Block Coded Multiple Input Multiple Output Orthogonal Frequency Division Multiplexing (STBC MIMO-OFDM) System. Since the STBC MIMO-OFDM System suffers a high Peak to Average Power Ratio (PAPR), K-means modified Partial Transmit Sequence (K-PTS) is used to reduce the PAPR. At the receiver side, the Linear Support Vector Machine (L-SVM) algorithm is used to classify the epilepsy from EEG signals. The performance metrics includes specificity, sensitivity, time delay, quality values, accuracy and performance index. Bit Error Rate (BER) and PAPR.
CITATION STYLE
Prabhakar, S. K., & Rajaguru, H. (2017). Wireless systems with reduced PAPR using K-means modified PTS implemented for epilepsy classification from EEG signals. In IFMBE Proceedings (Vol. 59, pp. 309–312). Springer Verlag. https://doi.org/10.1007/978-3-319-52875-5_64
Mendeley helps you to discover research relevant for your work.