Paper Title
Multimodal System To Predict Epileptic Seizures Using Machine Learning Technique
Abstract
Abstract— In this paper we proposed a method to an automatic prediction of epilepsy using Multimodal signal. Major aim
is to develop a new wireless sensor based system for detecting and monitoring epileptic patients in a non-clinical
environment. In order to achieve this, a mechanism will be developed for capturing multi-modal data such as
electroencephalogram (EEG), electro dermal activity (EDA), accelerometry (ACM) and heart beat from epileptic patients
using EEG cap and wrist-worn biosensor. The captured multi-modal data from sensors will be sent to smart phone through
wireless transmission for processing Support Vector Machine (SVM) will be developed and used as classifier The proposed
system will sense the aura of pre-ictal stage in advance and takes the necessary safety measures such as alarm, sending SMS
along with location information using GPS to emergency medical service, relative and doctor automatically, in order to
prevent Sudden Unexpected Death in Epilepsy (SUDEP).