• Madhav Singh Solanki

Emotion Recognition (ER) is becoming a highly significant and rapidly growing area of study in recent decades. Emotion Detection (ED) technology has had a significant effect on a variety of fields, particularly research and development. Previously, face gestures and voice intonation were employed to identify emotions; but body expressions and the spoken words may provide factually inaccurate findings. As a consequence, research has chosen to use the electroencephalogram (EEG) method, which has been shown to be a reliable tool for identifying emotions. Some methods collected EEG data using conventional and pre-defined signal pre-processing and associated processes, whereas others utilized smaller channels or people. This paper describes a quantitative feature-based emotion detection method. After the best characteristics have indeed been selected, the dataset is given to a classification algorithm for training and testing purposes. As per the results of the study, the proposed method has an accuracy rate of 91.54 percent for the data samples examined. Furthermore, in terms of accuracy, the suggested approach surpasses existing methods.

EEG, Electroencephalogram (EEG), Emotion Recognition, Human-Computer Interactions (HCI), Support Vector Machine (SVM).

"Support Vector Machine Classifier for EEG-based Emotion Recognition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 2, page no.944-951, February-2019, Available :http://www.jetir.org/papers/JETIRFH06159.pdf

"Support Vector Machine Classifier for EEG-based Emotion Recognition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 2, page no. pp944-951, February-2019, Available at : http://www.jetir.org/papers/JETIRFH06159.pdf