Efficient wireless system for telemedicine application with reduced PAPR using QMF based pts technique for epilepsy classification from EEG signals

1Citations
Citations of this article
7Readers
Mendeley users who have this article in their library.
Get full text

Abstract

Seizure is a kind of transient abnormal behaviour of neurons occurring within the brain which disturbs the mental and physical activities of the padent. Due to the synchronized activity of large group of neurons, epileptic seizures occur. These epileptic seizures cause numerous changes in the behaviour and perception of the patient Even if the epileptic seizures are quite rare in a given patient, the fear of the occurrence of next seizure and helplessness feeling will have a wry strong influence on the daily life of a patient. To improve the quality of life of these epileptic patients, a systematic method to predict the occurrence of seizures should be reliable. In biomedical science, EEG signals provide very valid contributions and hence the careful analysis of EEG recordings is required to understand the valuable information. To capture the brain signals of the epileptic patient, Electroencephalography (EEG) is widely used. EEG has a good temporal resolution and is non invasive in nature with a low maintenance cost Since the EEG recordings are too huge to process, certain form of dimensionality reduction technique is required to reduce the dimensions of the EEG data in order to process the data. In this paper. Power Spectral Density (PSD) is used a dimensionality reduction technique to reduce the dimensions. It is then transmitted through the Space Time Trellis Coded Multiple Input Multiple Output Orthogonal Frequency Division Multiplexing (STTC MIMO-OFDM) System. As the system suffers from a high PAPR, Quadrature Mirror Filtering Based Partial Transmit Sequence (QMF-PTS) is proposed to reduce the PAPR. At the receiver, the classifier engaged here is Polynomial Kernel Based Support Vector Machine (PK-SVM) to classify the epilepsy from EEG signals. The performance metrics is analyzed in terms of performance index, sensitivity, specificity, time delay, quality value and accuracy.

Author supplied keywords

Cite

CITATION STYLE

APA

Prabhakar, S. K., & Rajaguru, H. (2017). Efficient wireless system for telemedicine application with reduced PAPR using QMF based pts technique for epilepsy classification from EEG signals. In IFMBE Proceedings (Vol. 59, pp. 313–316). Springer Verlag. https://doi.org/10.1007/978-3-319-52875-5_65

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free