Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Identification of Brain Functions and its Disorders Using SVM


Affiliations
1 Annamalai University, Annamalai Nagar-608002, India
     

   Subscribe/Renew Journal


This paper helps the neurologists to diagnose and determine weather a patient is epileptic or non epileptic. EEG standard is an acronym for Electroencephalogram has been traditionally used to diagnose the brain activity of a patient which corresponds to epilepsy and other brain disorders. The features are extracted using medical data signals and SVM is trained using the extracted signals. This paper focuses on developing a classification technique called SVM for multichannel EEG recordings. Traditional SVMs are used to exploit both spatial and temporal characteristics of EEG data. The proposed technique is tested on two EEG data sets acquired from ten patients respectively SVM is based on the principle of structural risk minimization and it can be used for non linear regression. This study is a necessary application of data mining to advance the diagnosis and treatment of human epilepsy. The performance system achieves the identification rate of 96.0% for 10 subjects.

Keywords

Electroencephalogram (EEG) Classification, Epilepsy Diagnosis, Discrete Wavelet Transform and Support Vector Machine.
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 215

PDF Views: 4




  • Identification of Brain Functions and its Disorders Using SVM

Abstract Views: 215  |  PDF Views: 4

Authors

S. Sathiya
Annamalai University, Annamalai Nagar-608002, India
V. Rathikarani
Annamalai University, Annamalai Nagar-608002, India
M. Balasubramanian
Annamalai University, Annamalai Nagar-608002, India
P. Dhanalakshmi
Annamalai University, Annamalai Nagar-608002, India

Abstract


This paper helps the neurologists to diagnose and determine weather a patient is epileptic or non epileptic. EEG standard is an acronym for Electroencephalogram has been traditionally used to diagnose the brain activity of a patient which corresponds to epilepsy and other brain disorders. The features are extracted using medical data signals and SVM is trained using the extracted signals. This paper focuses on developing a classification technique called SVM for multichannel EEG recordings. Traditional SVMs are used to exploit both spatial and temporal characteristics of EEG data. The proposed technique is tested on two EEG data sets acquired from ten patients respectively SVM is based on the principle of structural risk minimization and it can be used for non linear regression. This study is a necessary application of data mining to advance the diagnosis and treatment of human epilepsy. The performance system achieves the identification rate of 96.0% for 10 subjects.

Keywords


Electroencephalogram (EEG) Classification, Epilepsy Diagnosis, Discrete Wavelet Transform and Support Vector Machine.