Functional Connectivity and Classification of Actual and Imaginary Motor Movement

Abstract

Imaginary Motor movement is an utmost important for the designing of brain computer interface to assist the individual with physically disability. Brain signals associated with actual motor movement include the signal for muscle activity whereas in case of imaginary motor movement actual muscle movement is not present .Authors have investigated the similarity/dissimilarity between the eeg signals generated in both the cases along with the baseline activity. To instruct the brain computer interface signals generated by electrodes of EEG must resemble with actual motor movement. Selection of electrodes placement plays an important role for this purpose. In this study major four regions of the brain has been covered frontal, temporal, parietal and occipital region of the scalp and features are extracted from the signals are standard deviations, kurtosis, skew and mean. Support Vector Machine is used for the classification between actual and imaginary motor movement along with differentiation between baseline and imaginary motor movement and actual motor movement at 14 different electrodes positions. Statistical performances of the classifier have been evaluated by computing sensitivity, specificity and accuracy. The location involved to achieve maximum accuracy for the classification of motor movements (actual and imaginary) and no motor movement is at frontal, temporal and parietal region

Imaginary Finger Movements Decoding Using Empirical Mode Decomposition and a Stacked BiLSTM Architecture

“…The sensorimotor cortex produces similar activation patterns during the imagined and physical movement according to the synchronization and desynchronization of the mu-rhythm [13]. Li Feng et al implemented a left-and right-hand MI-EEG signal classifier for a BCI using a Continuous Wavelet Transform (CWT) and a simplified Convolutional Neural Network (CNN) [14].…”