Emotion Detection Analysis using EEG and Physiological Signals for Hybrid Systems
Namrata D Rupani1, R. Roseline Mary2

1Namrata D Rupani*, Research Scholar Master of Computer Applications (MCA) Department of Computer Science CHRIST (Deemed to be University), Bangalore, Karnataka, India
2R. Roseline Mary Assistant Professor Department of Computer Science CHRIST (Deemed to be University), Bangalore, Karnataka, India
Manuscript received on March 15, 2020. | Revised Manuscript received on March 28, 2020. | Manuscript published on April 10, 2020. | PP: 534-543 | Volume-9 Issue-6, April 2020. | Retrieval Number: F3801049620/2020©BEIESP | DOI: 10.35940/ijitee.F3801.049620
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: Emotions are an inevitable and integral part of human existence. They form the basis of decisions taken by individuals and the way they perceive their surroundings. Method of articulation of emotions have changed with the increment in dependency between people and innovation. Now the need to recognize emotions has increased with the increasing role of human-Computer Interface (HCI) technology. There are many ways to record and identify human’s emotion using different neurophysiological measurements/ technologies like GSR(Galvanic Skin Response), Electromyography (EMG), Electrocardiogram (ECG) and Electroencephalography (EEG). In this paper, the focus is on emotion detection using EEG signals and other physiological signals and further analyzing them. There exist various machine learning techniques that have been used to pre-process and classify EEG data, have been reviewed in the paper. The analysis involves major aspects of the emotion recognition process like feature extraction, classification and comparison of the approaches. Different supervised machine learning algorithms have been applied to classify the EEG data. This paper focuses on comprehensive analysis of existing systems and based on the result propose the techniques which when applied will reap high-quality results. 
Keywords: Emotions, Emotion Recognition, Human Computer Interface (HCI), Electroencephalogram (EEG), EEG Analysis, Physiological Signals, Valence – Arousal Model
Scope of the Article: Predictive Analysis