Feature Extraction and Classification of EEG Signals Using Neural Network Based Techniques

Farheen Siddiqui; M.P.S. Chawla

Feature Extraction and Classification of EEG Signals Using Neural Network Based Techniques

Farheen Siddiqui, M.P.S. Chawla

Abstract

EEG stands for Electroencephalogram. EEG is used to record signals from brain; signals are recorded from the scalp or cortex of brain. EEG used for both clinically purpose as well as for scientifically purpose. Hence measurement of EEG signals plays an important role in mind/brain studies. Reorganization of EEG signals from brain is one of the most overriding approaches to extract the data/knowledge from mind/brain dynamics. Analyzing Electrical activity of brain through EEG provide medical science to examine different brain diseases. Electrical activity of brain can easily be classified as normal brain waves or abnormal brain waves. Normal brain waves used to study various states of mind where as abnormal brain waves used to indicate medical problems. Classification of EEG signals play important role in medical science, some important applications for EEG wave classification are diagnosis of sleep disorders and construction of BCI to assist disabled person.

Reorganization of EEG signals from brain is one of the most overriding approaches to extract the data/knowledge from mind/brain dynamics. Analyzing Electrical activity of brain through EEG provide medical science to examine different brain diseases.

Full Text:

PDF

References

HafeezUllah Amin, “Feature extraction and classification for EEG signals using wavelet transform,” , March 2015, pp.139-149.

M.Jackson, W.Zhao, J.Yan, “hybrid classification method using Artificial Neural Network based decision tree automatic sleep scoring,” International Journal, Vol.5, No.7, 2011.

Mehdi Hoodgar, “Feature extraction methods for EEG signal analysis”, Feb. 2015, pp. 545-552.

Davis Lawrence, “Training Feed forward Neural networks using genetic algorithms”, , Jan. 2010.

A.Turnip and I.R.Setiawan, “Artifacts removal of EEG signals using Nonlinear adaptive Autoregressive,”, Vol.5, No.3, May 2015.

DwiEstiKusumandari, “Artifacts removal of EEG signals using Adaptive Principal Component Analysis”, India, Nov. 2014

D.C.Frua, E.C.Roldan, A.O.Forero, “Automatic sleep stages classification using EEG entropy features and unsupervised pattern analysis techniques,” Vol.16, Dec. 2014, pp.6573-6589.

M.Jackson, W.Zhao, J.Yan, “hybrid classification method using Artificial Neural Network based decision tree automatic sleep scoring,” International Journal, Vol.5, No.7, 2011.

Hemanth Kumar, F.Ahmed, S.Michahial, Nandish.M, “Feature extraction and classification of EEG signal using Neural Network based techniques,”, pp.2277-3754, 2012.

Fewnm-zika, “Multi-feature analysis in motor imagery EEG classification,”,2010, pp.114-117.

Mu.z.d, “Classification of Motor Imagery EEG based on phase synchronization,” Micro-electronics and computer, Vol.25, Sep. 2008, pp.138-140.

Iwan.R.Setiawan, “Artifacts removal of EEG signals using non-linear adaptive autoregressive,”, Vol.5, No.3, May 2015.

Rakeshmehra, “EEG power spectrum and neural network based sleep hypnogram analysis for a model of heat stress,” , Vol.22, 2008, pp.261-268.