EMOTION RECOGNITION USING GALVANIC SKIN RESPONSE (GSR) SIGNAL

RAMOS UKAR, YAKOBUS (2022) EMOTION RECOGNITION USING GALVANIC SKIN RESPONSE (GSR) SIGNAL. [Final Year Project Report] (Unpublished)

	PDF Ramos Ukar Anak Yakobus 24pgs.pdf Download (977kB)
	PDF (Please get the password by email to repository@unimas.my , or call ext: 082-583914/3973/3933) Ramos Ukar Anak Yakobus ft.pdf Restricted to Registered users only Download (1MB)

Abstract

This project uses a galvanic skin response (GSR) signal to describe emotion recognition. Human beings can express thousands of emotions. Differentiated features and classification can recognize various mood disorders. Physiological signals also play a vital role in emotion recognition as they are not controllable and are of immediate response type. The main purpose of this project is to acquire skin conductance of GSR by performing GSR signal classification for emotion recognition using the various classifier. Machine learning applications penetrate more and more spheres of everyday life. Recent studies show promising results in analysing other physiological signals using machine learning to access emotional states. Commonly, specific emotion is invoked by playing effective videos or sounds. However, there is no canonical way for emotional state interpretation. In this project, the main materials are GSR data signals collected from ASCERTAIN database and MATLAB software. The classified affective GSR signals with labels were obtained from the arousal seven-point emotional scale approach using machine learning algorithms. Features and class labels can import into the Classification Learner application in MATLAB software to train and test various classifiers. A comparison of GSR signal classification of the different classifiers has shown that the highest accuracy was achieved using k-nearest neighbours (KNN) and Ensemble classifiers with 97.9% emotion detection. The advantage of this project shows the importance of label selection in emotion recognition tasks. Moreover, the obtained dataset must be suitable for machine learning algorithms. Acquired results may help select proper GSR signals with emotional labels for further dataset pre-processing and feature extraction.

Actions (For repository members only: login required)

View Item