EEG Signal Classification Using Hidden Markov Model

Lieferzeit: Lieferbar innerhalb 14 Tagen

39,90 

ISBN: 6139961327
ISBN 13: 9786139961320
Autor: Arunachalam, Vigneshkumar/Rajaguru, Harikumar/Babu Chidambaram, Ganesh
Verlag: LAP LAMBERT Academic Publishing
Umfang: 60 S.
Erscheinungsdatum: 24.12.2018
Auflage: 1/2018
Format: 0.4 x 22 x 15
Gewicht: 107 g
Produktform: Kartoniert
Einband: Kartoniert
Artikelnummer: 6155996 Kategorie:

Beschreibung

This book emphasize on Epilepsy which is a neurological disorder with preponderance of about 1-2% of the worlds population. It is due to excessive synchronization of cortical neuronal networks and is characterized by sudden recurrent and transient disturbances of perception or behavior. Epileptic seizures are classified as partial or focal, generalized, unilateral and unclassified seizures. Focal epileptic seizures involve only part of cerebral hemisphere and in corresponding parts of the body. Generalized epileptic seizures involve the entire brain and produce bilateral motor symptoms usually with loss of consciousness. Both types of epileptic seizures can occur at all ages.One of the most important tools for diagnosing Epilepsy includes monitoring brain activity through the electroencephalogram (EEG). The EEG signature is transient waveform of isolated spikes, spike trains.It also assists in classifying the underlying epileptic syndrome. The feature extraction is done by Independent Component Analysis (ICA) and final risk level classification is done by Hidden Markov Model (HMM). Performance evaluation is done by Kappa function and Mean Square Error (MSE).

Autorenporträt

Vigneshkumar Arunachalam was awarded M.E in CSE from Anna University Chennai in April 2013.He has 5 Years of teaching experience at college level. Currently he is Assistant Professor CSE Department at Bannari Amman Institute of Technology, Sathyamangalam. His area of interest is Big Data Analytics and Signal Processing

Herstellerkennzeichnung:


BoD - Books on Demand
In de Tarpen 42
22848 Norderstedt
DE

E-Mail: info@bod.de

Das könnte Ihnen auch gefallen …