PATIENT FACING SYSTEMS Patient-Specific Seizure Detection Method using Hybrid Classifier with Optimized Electrodes R. Shantha Selvakumari 1 & M. Mahalakshmi 2 & P. Prashalee 1 Received: 21 December 2018 /Accepted: 6 March 2019 # Springer Science+Business Media, LLC, part of Springer Nature 2019 Abstract In this paper the EEG signal is analyzed by reconstructing the time series EEG signal in High dimensional Phase Space. The computational complexity in higher dimension is reduced by Principal Component Analysis for the High dimensional Phase Space output. Poincare sectioning is done for the first and second Principal Components (PCs). The intersection points of PCs and the Poincare section are collected and used for features calculation. Two layer of classification is done using SVM as first layer and Naive Bayes as second layer. The proposed methodology is evaluated using the CHB-MIT database for 23 subjects. The results are obtained using different channel combinations of EEG signal and highest of 95.63% accuracy, 95.7% sensitivity and 96.55% specificity is obtained for 12 electrode combinations which include electrodes from parietal and occipital lobes. This infers that most of the subjects have dysfunction in hearing (controlled by parietal) and vision (controlled by occipital) during the time of seizure. This GUI has channel selection option and seizure detection for every channel (23) for every 1 s. Keywords High dimensional phase space . Principal component analysis . Poincare section . SVM . Naive Bayes . Optimized electrodes Introduction At present, Humans are undergoing various kind of stress in their fast daily life and half of them are suffering from different neurological disorders [1]. Among the various neurological disorders of brain, epilepsy is the most common one affecting approximately 50 million population worldwide [2]. The un- expected and sudden electrical disturbances of the brain re- sults in an acute disease called Epileptic seizures. Epilepsy is one of the most common diseases of the central nervous system. Epilepsy is unpredictable and can be detected by an- alyzing the brain signals (EEG). The people affected by this disease have the symptoms of abnormal sensations, twitching of arms, changes in vision, loss awareness, hear, smell or see things differently. But they usually do not have any physical symptoms in between seizures [3]. Cerebrum or cortex is the largest part of the brain responsible for controlling major func- tions of the body including thought and action. Cerebral cor- tex is the only area where origin of epilepsy arises. Cerebral cortex is divided into four lobes. They are frontal lobe, parietal lobe, occipital lobe, and temporal lobe. Each lobe is responsi- ble for particular function. & Frontal Lobe- controls reasoning, planning, parts of speech, movement, emotions, and problem solving & Parietal Lobe- controls movement, orientation, recogni- tion, perception of stimuli & Occipital Lobe- controls visual processing & Temporal Lobe- controls perception and recognition of auditory stimuli, memory, and speech People may experience abnormal activities in sensation, movement, awareness, and behaviour during seizure as a This article is part of the Topical Collection on Patient Facing Systems * R. Shantha Selvakumari rshantha@mepcoeng.ac.in M. Mahalakshmi mahalakshmi2446@gmail.com P. Prashalee prashu23.p@gmail.com 1 Department of ECE, Mepco Schlenk Engineering College, Sivakasi, India 2 Cognizant Technology Solutions, Chennai, India Journal of Medical Systems (2019) 43:121 https://doi.org/10.1007/s10916-019-1234-4