Functional Connectivity and Classification of Actual and Imaginary Motor Movement
Nilima Salankar1, Anjali Mishra2, Pratikshya Mishra3

1Dr. Nilima Salankar, Assistant Professor, Department of School of Computer Science, University of Petroleum and Energy Studies Dehradun, India.
2Anjali Mishra, Mtech Student in Computer Science, University of Petroleum and Energy Studies Dehradun, India.
3Pratikshya Mishra, Mtech student in Computer Science, University of Petroleum and Energy Studies Dehradun, India.
Manuscript received on November 25, 2019. | Revised Manuscript received on December 08, 2019. | Manuscript published on December 30, 2019. | PP: 529-535 | Volume-9 Issue-2, December, 2019. | Retrieval Number: B3257129219/2019©BEIESP | DOI: 10.35940/ijeat.B3257.129219
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

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 whereas very less involvement has been seen of occipital region.