Improving Accuracy of Emotion Detection using Brain Waves and Adaptive Swarm Intelligence
Ruchita Timande1, Payal Ghutke2
1Ruchita Timande*, Student, M. tech, G. H. Raisoni College of Engineering in VLSI stream, Nagpur.
2Prof. Payal Ghutke, Assistant Professor in Department of Electronics Engineering, G H Raisoni College of Engineering, Nagpur.
Manuscript received on March 15, 2020. | Revised Manuscript received on March 26, 2020. | Manuscript published on April 10, 2020. | PP: 1845-1848 | Volume-9 Issue-6, April 2020. | Retrieval Number: F4163049620/2020©BEIESP | DOI: 10.35940/ijitee.F4163.049620
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 (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In recent year, Authors had been attempting to find or detect the feeling of human by recorded brain signal for example, EEG (electroencephalogram) alerts. Because of the unnecessary degrees of unwanted signal from EEG recording, a solitary feature alone can’t accomplish great execution. Distinct feature is key for automatic feeling identification. Right now, we present an AI based scheme utilizing various features extricated from EEG recordings. The plan joins these particular highlights in feature space utilizing both managed and unaided component choice procedures. To re-request the joined highlights to max-importance with the names and min-repetition of each feature by applying Maximum Relevance Minimum Redundancy (MRMR). The produced highlights are additionally diminished with principal component analysis(PCA) for removing essential segments. Test report will be generated to show that the proposed work should outperform the condition of-workmanship techniques utilizing similar settings in real time dataset.
Keywords: Brain Signal, Electroencephalogram, Emotion-Recognization, PSO.
Scope of the Article: Digital signal processing theory