BCI based EEG Signals for Emotion Classification
K. Saranya1, S. Jayanthy2
1K. Saranya, Assistant Professor, Department of Computer Science and Engineering, Kumaraguru College of Technology, Coimbatore (Tamil Nadu), India.
2Dr. S. Jayanthy, Professor, Department of Electronics and Communication Engineering, Sri Ramakrishna Engineering College, Coimbatore (Tamil Nadu), India.
Manuscript received on 14 December 2018 | Revised Manuscript received on 25 December 2018 | Manuscript Published on 09 January 2019 | PP: 385-389 | Volume-7 Issue-4S November 2018 | Retrieval Number: E1997017519/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© 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: The human brain which is the central processing unit of the human machine is responsible for multiple tasks such as perception, cognition, attention, emotion, memory and action. In human life emotions significantly affect one’s wellbeing. Providing methodologies to access to human emotions would be a key for successful human machine interaction. Understanding Brain Computer Interface (BCI) techniques to identify the emotions also help in aiding people to interact with the world like a common man. Many techniques were devised to identify the human emotions of which usage of EEG signals to classify the emotions as happiness, fear, anger and sadness were found promising. These emotions are evoked by many means such as showing subjects pictures of smile and cry facial expressions, by hearing to emotionally mixed audios or by watching videos and at time combination of these. This paper is a survey of all the optimized methods to filter the EEG signal and comparative study of the various classification methods used to classify the emotions is carried out and a multimodal classification technique which makes use of EEG signals and at the same time efficiency is measured with Natural Language Processing(NLP) is proposed for improving the accuracy.
Keywords: EEG Signal, Emotion Classification, BCI, Multimodal, NLP.
Scope of the Article: Classification