Logo

EEG classification of physiological conditions in 2D/3D environments using neural network

Mumtaz, Wajid and Xia, Likun and Malik, Aamir Saeed and Mohd Yasin, Mohd Azhar (2013) EEG classification of physiological conditions in 2D/3D environments using neural network. In: 35th Annual International Conference of the IEEE EMBS, July 3 - 7, 2013, Osaka, Japan.

[img]
Preview
PDF
559Kb

Official URL: http://dx.doi.org/10.1109/EMBC.2013.6610480

Abstract

Higher classification accuracy is more desirable for brain computer interface (BCI) applications. The accuracy can be achieved by appropriate selection of relevant features. In this paper a new scheme is proposed based on six different nonlinear features. These features include Sample entropy (SampEn), Composite permutation entropy index (CPEI), Approximate entropy (ApEn), Fractal dimension (FD), Hurst exponent (H) and Hjorth parameters (complexity and mobility). These features are decision variables for classification of physiological conditions: Eyes Open (EO), Eyes Closed (EC), Game Playing 2D (GP2D), Game playing 3D active (GP3DA) and Game playing 3D passive (GP3DP). Results show that the scheme can successfully classify the conditions with an accuracy of 88.9%.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:Nonlinear analysis of biomedical signals, Biomedical signal classification, Neural networks in biosignal processing and classification
Subjects:Q Science > Q Science (General)
R Medicine > RZ Other systems of medicine
T Technology > T Technology (General)
Academic Subject One:Academic Department - Electrical And Electronics - Communications - Digital Communications - Digital Signal Processing
Departments / MOR / COE:Centre of Excellence > Center for Intelligent Signal and Imaging Research
Research Institutes > Institute for Health Analytics
ID Code:10826
Deposited By: Dr Aamir Saeed Malik
Deposited On:16 Dec 2013 23:48
Last Modified:16 Dec 2013 23:48

Repository Staff Only: item control page

Document Downloads

More statistics for this item...