RT Journal Article SR Electronic T1 Performance Evaluation of Empirical Mode Decomposition Algorithms for Mental Task Classification JF bioRxiv FD Cold Spring Harbor Laboratory SP 076646 DO 10.1101/076646 A1 Akshansh Gupta A1 Dhirendra Kumar A1 Anirban Chakraborti A1 Kiran Sharma YR 2016 UL http://biorxiv.org/content/early/2016/09/21/076646.abstract AB The electroencephalograph (EEG) signal is the one of the monitoring techniques to observe brain functionality. EEG is most preferable technology not just because of its non-invasive and cost effective quality, but also it can detect the cognitive activity of human. Brain Computer Interface (BCI), a direct pathway between the human brain and computer, is one of the most pragmatic applications of EEG signal. Mental Task Classification (MTC) is a demanding BCI as it does not involve any muscular activity. Empirical Mode Decomposition (EMD) is a filter based heuristic technique to analyze non-linear and non-stationary signal like EEG. There are several variants of EMD algorithms which have their own merits and demerits. In this paper, we have explored three different EMD algorithms on EEG data for MTC-based BCI named as Empirical Mode Decomposition (EMD),Ensemble Empirical Mode Decomposition (EEMD) and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN). Features are extracted from EEG signal in two phases; in the first phase, the signal is decomposed into different oscillatory functions with the help of different EMD algorithm and in the second phase, eight different parameters (features) are calculated for the each function for compact representation. In this paper a new feature known as Hurst Exponent along with other feature have been investigated for mental task classification. These features are fed up into Support Vector Machine (SVM) classifier to classify the different mental tasks. We have formulated two different typs of MTC, the first one is binary and second one is multi-MTC. The proposed work outperforms the existing work for both binary and multi mental tasks classification.