EEG-based Emotion Recognition Using Hybrid CNN and LSTM Classification

Chakravarthi, Bhuvaneshwari, Ng, Sin-Chun ORCID logoORCID: https://orcid.org/0000-0002-2972-530X, Ezilarasan, M.R. and Leung, Man-Fai (2022) EEG-based Emotion Recognition Using Hybrid CNN and LSTM Classification. Frontiers in Computational Neuroscience. ISSN 1662-5188

[img]
Preview
Text
Published Version
Available under the following license: Creative Commons Attribution.

Download (3MB) | Preview
Official URL: https://doi.org/10.3389/fncom.2022.1019776

Abstract

Emotions are a mental state that is accompanied by a distinct physiologic rhythm, as well as physical, behavioral, and mental changes. In the latest days, physiological activity has been used to study emotional reactions. This study describes the EEG signals, the brain wave pattern, and emotion analysis all of these are interrelated and based on the consequences of human behavior and PTSD. Post-Traumatic Stress Disorder effects for long-term illness are associated with considerable suffering, impairment, and social/emotional impairment. PTSD is connected to subcortical responses to injury memories, thoughts, and emotions and alterations in brain circuitry. Predominantly EEG signals are the way of examining the electrical potential of the human feelings cum expression for every changing 22 phenomenon that the individual faces. When going through literature there are some lacunae while analyzing emotions. There exist some reliability issues and also masking of real emotional behavior by the victims. Keeping this research gap and hindrance faced by the previous researchers the present study aims to fulfill the requirements, the efforts can be made to overcome this problem, and the proposed automated CNN-LSTM with ResNet-152 algorithm. Compared with the existing techniques, the proposed techniques achieved a higher level of accuracy of 98% by applying the hybrid deep learning algorithm

Item Type: Journal Article
Keywords: deep learning, electroencephalography, emotion recognition, neural networks, machine learning
Faculty: Faculty of Science & Engineering
SWORD Depositor: Symplectic User
Depositing User: Symplectic User
Date Deposited: 29 Sep 2022 15:02
Last Modified: 10 Oct 2022 09:53
URI: https://arro.anglia.ac.uk/id/eprint/707963

Actions (login required)

Edit Item Edit Item