EEG Control of a Bionic Hand With Imagination Based on Chaotic Approximation of Largest Lyapunov Exponent: A Single Trial BCI Application Study

This paper investigates a method for imaginary hand fisting pattern recognition based on the electroencephalography (EEG). The proposed method estimate the largest Lyapunov exponent (LLE) chaotic feature that is based on approximation of mutual information (MI) and false nearest neighbor (FNN) methods for reconstructing a phase space. The selected method for MI and FNN approximation approaches is a new version of Tug of War optimization algorithm. The new algorithm utilizes chaotic maps to update candidate solutions. The chaotic approximation of the LLE (CALLE) is the utilized method for extracting the chaotic features and then categorizing features by means of soft margin support vector machine with a generalized radial basis function kernel classifier. Accuracy and paired t-test values are obtained and compared with the traditional LLE method; 18 candidates were participated to record the EEG for imaginary right-hand fisting task. The results show improvements for the CALLE algorithm in comparison with the traditional LLE by achieving a higher accuracy of 68.25%. Feature changes between two imaginary statuses were significant for 17 subjects, and the paired t-test values were (p < 0.05). From the results, it is concluded that the Tug of War optimization method finds different values to reach a higher accuracy than the traditional LLE method, and the traditional methods for the LLE are not optimum.