Recognition of multi-cognitive tasks from EEG signals using EMD methods

Abstract Mental task classification (MTC), based on the electroencephalography (EEG) signals is a demanding brain–computer interface (BCI). It independent of all types muscular activity. MTC-based BCI systems are capable to identify cognitive activity human. The success system depends upon efficient feature representation from raw EEG for mental activities. This paper mainly presents novel (formation most informative features) signal both, binary as well multi MTC, using combination some statistical, uncertainty and memory- coefficient. In this work, formation carried out in two stages. first stage, split into different oscillatory functions with help three well-known empirical mode decomposition (EMD) algorithms, new set eight parameters (features) calculated function second stage vector construction. Support machine (SVM) used classify vectors obtained corresponding tasks. study consists problem formulation variants MTC; two-class multi-class MTC. suggested scheme outperforms existing work both tasks classification.