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

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%.