A Computerized Approach for Emotion Recognition from EEG Signals Using Gazelle-Whale Optimization and Attention-Based Improved DCNN-BILSTM

International Journal of Electrical and Electronics Engineering

© 2024 by SSRG - IJEEE Journal

Volume 11 Issue 3

Year of Publication : 2024

Authors : T. Manoj Prasath, R. Vasuki

10.14445/23488379/IJEEE-V11I3P117

How to Cite?

T. Manoj Prasath, R. Vasuki, "A Computerized Approach for Emotion Recognition from EEG Signals Using Gazelle-Whale Optimization and Attention-Based Improved DCNN-BILSTM," SSRG International Journal of Electrical and Electronics Engineering, vol. 11,  no. 3, pp. 209-219, 2024. Crossref, https://doi.org/10.14445/23488379/IJEEE-V11I3P117

Abstract:

The use of Electroencephalogram (EEG) signals for emotion recognition has demonstrated remarkable success across diverse fields such as medicine, security, and human-computer interaction. Recent advancements in Deep Learning (DL) techniques have substantially enhanced classification precision compared to traditional signal processing and Machine Learning (ML) approaches. This work focuses on developing a computerized methodology to effectively recognize emotions from EEG signals, emphasizing the crucial processes of feature extraction, feature selection and emotion classification. Traditional approaches in emotion recognition from EEG signals face challenges in achieving high accuracy. The motivation behind this work is to harness the benefits of Deep Learning (DL) for optimal emotion recognition. The proposed methodology aims to address existing limitations and improve the efficacy of emotion recognition systems. Gaussian smoothing filters are applied to the EEG brainwave dataset to reduce artifacts, ensuring a cleaner input for subsequent processing. Features are extracted using Empirical Mode Decomposition (EMD), providing enhanced spatial accuracy and temporal resolution in representing emotional states. A hybrid Gazelle-Whale Optimization approach is employed to select optimal features, improving the efficiency of subsequent classification stages. Attention-based Improved Deep Convolutional Neural Network (DCNN) coupled with Bidirectional Long Short-Term Memory (Bi-LSTM) networks is utilized for accurate emotion classification. This combination integrates the strengths of DL in capturing intricate patterns within EEG signals. The integrated deep learning techniques and optimization strategies lead to more accurate and reliable emotional state classifications. The outcomes for the proposed topology demonstrate a high accuracy of 98.28%, F1 score of 97.54%, recall measuring 98.28% and precision scoring of 98.12%, respectively.

Keywords:

Electroencephalogram, Empirical Mode Decomposition, Gazelle-Whale Optimization (GWO), DCNN- Bi-LSTM, Gaussian smoothing filters.

References:

[1] Rania Alhalaseh, and Suzan Alasasfeh, “Machine-Learning-Based Emotion Recognition System Using EEG Signals,” Computers, vol. 9, no. 4, pp. 1-15, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[2] M. Kalpana Chowdary, J. Anitha, and D. Jude Hemanth, “Emotion Recognition from EEG Signals Using Recurrent Neural Networks,” Electronics, vol. 11, no. 15, pp. 1-20, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Javier Marín-Morales et al., “Affective Computing in Virtual Reality: Emotion Recognition from Brain and Heartbeat Dynamics Using Wearable Sensors,” Scientific Reports, vol. 8, no. 1, pp. 1-15, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Murside Degirmenci et al., “Emotion Recognition from EEG Signals by Using Empirical Mode Decomposition,” 2018 Medical Technologies National Congress (TIPTEKNO), Magusa, Cyprus, pp. 1-4, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Pragati Patel, Raghunandan R., and Ramesh Naidu Annavarapu, “EEG-Based Human Emotion Recognition Using Entropy as a Feature Extraction Measure,” Brain Informatics, vol. 8, pp. 1-13, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Wei Li et al., “A Novel Spatio-Temporal Field for Emotion Recognition Based on EEG Signals,” IEEE Sensors Journal, vol. 21, no. 23, pp. 26941-26950, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Tran-Dac-Thinh Phan et al., “EEG-Based Emotion Recognition by Convolutional Neural Network with Multi-Scale Kernels,” Sensors, vol. 21, no. 15, pp. 1-13, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Ahmed S. Eltrass, and Noha H. Ghanem, “A New Automated Multi-Stage System of Non-Local Means and Multi-Kernel Adaptive Filtering Techniques for EEG Noise and Artifacts Suppression,” Journal of Neural Engineering, vol. 18, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[9] P.V.V.S. Srinivas, and Pragnyaban Mishra, “A Novel Framework for Facial Emotion Recognition with Noisy and de Noisy Techniques Applied in Data Pre-Processing,” International Journal of System Assurance Engineering and Management, pp. 1-11, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Haoshi Zhang et al., “A Robust Extraction Approach of Auditory Brainstem Response Using Adaptive Kalman Filtering Method,” IEEE Transactions on Biomedical Engineering, vol. 69, no. 12, pp. 3792-3802, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Souvik Phadikar, Nidul Sinha, and Rajdeep Ghosh, “Automatic Eyeblink Artifact Removal from EEG Signal Using Wavelet Transform with Heuristically Optimized Threshold,” IEEE Journal of Biomedical and Health Informatics, vol. 25, no. 2, 475-484, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Md. Rabiul Islam et al., “Emotion Recognition from EEG Signal Focusing on Deep Learning and Shallow Learning Techniques,” IEEE Access, vol. 9, pp. 94601-94624, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Patricia Becerra-Sánchez, Angelica Reyes-Munoz, and Antonio Guerrero-Ibañez, “Feature Selection Model Based on EEG Signals for Assessing the Cognitive Workload in Drivers,” Sensors, vol. 20, no. 20, pp. 1-25, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Yong Jiao et al., “Multi-View Multi-Scale Optimization of Feature Representation for EEG Classification Improvement,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 28, no. 12, pp. 2589-2597, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Manosij Ghosh et al., “A Wrapper-Filter Feature Selection Technique Based on Ant Colony Optimization,” Neural Computing and Applications, vol. 32, pp. 7839-7857, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Min Li et al., “Computer-Aided Diagnosis and Staging of Pancreatic Cancer Based on CT Images,” IEEE Access, vol. 8, pp. 141705- 141718, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Xiahan Chen et al., “Combined Spiral Transformation and Model-Driven Multi-Modal Deep Learning Scheme for Automatic Prediction of TP53 Mutation in Pancreatic Cancer,” IEEE Transactions on Medical Imaging, vol. 40, no. 2, pp. 735-747, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Xin Chai et al., “A Fast, Efficient Domain Adaptation Technique for Cross-Domain Electroencephalography (EEG)-Based Emotion Recognition,” Sensors, vol. 17, no. 5, pp. 1-21, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Jingxia Chen, Dongmei Jiang, and Yanning Zhang, “A Common Spatial Pattern and Wavelet Packet Decomposition Combined Method for EEG-Based Emotion Recognition,” Journal of Advanced Computational Intelligence and Intelligent Informatics, vol. 23, no. 2, pp. 274-281, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Heng Cui et al., “EEG-Based Emotion Recognition Using an End-to-End Regional-Asymmetric Convolutional Neural Network,” Knowledge-Based Systems, vol. 205, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Arjun, Aniket Singh Rajpoot, and Mahesh Raveendranatha Panicker, “Subject Independent Emotion Recognition Using EEG Signals Employing Attention Driven Neural Networks,” Biomedical Signal Processing and Control, vol. 75, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Yixin Wang et al., “EEG Based Emotion Recognition with Similarity Learning Network,” 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany, pp. 1209-1212, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Omid Bazgir, Zeynab Mohammadi, and Seyed Amir Hassan Habibi, “Emotion Recognition with Machine Learning Using EEG Signals,” 2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME), Qom, Iran, pp. 29-30, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Xue-han Wang et al., “EEG Emotion Recognition Using Dynamical Graph Convolutional Neural Networks and Broad Learning System,” 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Madrid, Spain, pp. 1240-1244, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Smith K. Khare, and Varun Bajaj, “Time-Frequency Representation and Convolutional Neural Network-Based Emotion Recognition,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 7, pp. 2901-2909, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Debarshi Nath et al., “A Comparative Study of Subject-Dependent and Subject-Independent Strategies for EEG-Based Emotion Recognition Using LSTM Network,” Proceedings of the 2020 the 4th International Conference on Compute and Data Analysis, pp. 142- 147, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Aya Hassouneh, A.M. Mutawa, and M. Murugappan, “Development of a Real-Time Emotion Recognition System Using Facial Expressions and EEG Based on Machine Learning and Deep Neural Network Methods,” Informatics in Medicine Unlocked, vol. 20, pp. 1-9, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Shtwai Alsubai, “Emotion Detection Using Deep Normalized Attention-Based Neural Network and Modified-Random Forest,” Sensors, vol. 23, no. 1, pp. 1-19, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Aseel Mahmoud et al., “A CNN Approach for Emotion Recognition via EEG,” Symmetry, vol. 15, no. 10, pp. 1-19, 2023.
[CrossRef] [Google Scholar] [Publisher Link]