EEG-Based Multi-Class Emotion Recognition using Hybrid  LSTM Approach

M d Momenul Haque; Subrata Kumer Paul; Rakhi Rani Paul; Mursheda Nusrat Della; M d Kamrul Islam; Sultan Fahim

doi:10.55524/ijircst.2023.11.3.1

Authors

M d Momenul Haque Department of CSE, Bangladesh Army University of Engineering & Technology (BAUET), Qadirabad, Dayarampur, Natore-6431, Rajshahi, Bangladesh Author
Subrata Kumer Paul Department of CSE, Bangladesh Army University of Engineering & Technology (BAUET), Qadirabad, Dayarampur, Natore-6431, Rajshahi, Bangladesh Author
Rakhi Rani Paul Department of CSE, Bangladesh Army University of Engineering & Technology (BAUET), Qadirabad, Dayarampur, Natore-6431, Rajshahi, Bangladesh Author
Mursheda Nusrat Della Department of CSE, Bangladesh Army University of Engineering & Technology (BAUET), Qadirabad, Dayarampur, Natore-6431, Rajshahi, Bangladesh Author
M d Kamrul Islam Department of CSE, Rabindra Maitree University (RMU), Kushtia-7000, Bangladesh Author
Sultan Fahim Department of CSE, Bangladesh Army University of Engineering & Technology (BAUET), Qadirabad, Dayarampur, Natore-6431, Rajshahi, Bangladesh Author

DOI:

https://doi.org/10.55524/ijircst.2023.11.3.1

Keywords:

EEG Signal, Hybrid LSTM, Emotion Recognition, Brainwave

Abstract

motion recognition is a crucial task in human-computer interaction, psychology, and neuroscience. Electroencephalogram (EEG)-based multi-class emotion recognition is a novel approach that aims to identify and classify human emotions by analysing EEG signals. Traditional methods of emotion recognition often face challenges in accurately identifying and classifying human emotions due to their complexity and subjectivity. EEG based emotion recognition provides a direct and objective measure of three emotional states (positive, neutral, and negative), making it a promising tool for emotion recognition. The proposed hybrid LSTM approach combines the strengths of different traditional machine learning algorithms: Gaussian Naive Bayes (GNB), Support Vector Machine (SVM), Logistic Regression (LR), and Decision Tree (DT). The approach was tested on the EEG brainwave dataset, and LSTM achieved an accuracy of 95%, while the proposed hybrid LSTM-GNB, LSTM-SVM, LSTM-LR, and LSTM-DT models achieved 65%, 96%, 97%, and 96% accuracy, respectively. The contribution of this study is the development of a hybrid LSTM approach that combines the strengths of two different algorithms, resulting in higher accuracy for multi-class emotion recognition using EEG signals. The results demonstrate the potential of the hybrid LSTM approach for real-world applications such as emotion based human-computer interaction and mental health diagnosis.

Downloads

Download data is not yet available.

References

Paul, R. R., Paul, S. K., & Hamid, Md. E. (2022). A 2D Convolution Neural Network Based Method for Human Emotion Classification from Speech Signal. In 2022 25th International Conference on Computer and Information Technology (ICCIT). 2022 25th International Conference on Computer and Information Technology (ICCIT). IEEE. https://doi.org/10.1109/iccit57492.2022.10054811

Subrata Kumer Paul, Rakhi Rani Paul, Nishimura, M., & Hamid, Md. E. (2020). Throat to Acoustic Speech Mapping for Spectral Parameter Correction using Artificial Neural Network Approach. In Proceedings of International Exchange and Innovation Conference on Engineering & Sciences

(IEICES) (Vol. 6, pp. 238–242). Kyushu University. https://doi.org/10.5109/4102497

Zhang, J., Yin, Z., Chen, P., & Nichele, S. (2020). Emotion recognition using multi-modal data and machine learning techniques: A tutorial and review. In Information Fusion (Vol. 59, pp. 103–126). Elsevier BV. https://doi.org/10.1016/j.inffus.2020.01.011

Paul, S. K., & Paul, R. R. (2021). Speech Command Recognition System using Deep Recurrent Neural Networks. In 2021 5th International Conference on Electrical Engineering and Information Communication Technology (ICEEICT). 2021 5th International Conference on Electrical Engineering and Information Communication Technology (ICEEICT). IEEE. https://doi.org/10.1109/iceeict53905.2021.9667795

Hancer, E., & Subasi, A. (2022). EEG-based emotion recognition using dual tree complex wavelet transform and random subspace ensemble classifier. In Computer Methods in Biomechanics and Biomedical Engineering (pp. 1–13). Informa UK Limited. https://doi.org/10.1080/10255842.2022.2143714

Alotaibi, F. M., & Fawad. (2023). An AI-Inspired Spatio Temporal Neural Network for EEG-Based Emotional Status. In Sensors (Vol. 23, Issue 1, p. 498). MDPI AG. https://doi.org/10.3390/s23010498

Oh, S. L., Vicnesh, J., Ciaccio, E. J., Yuvaraj, R., & Acharya, U. R. (2019). Deep Convolutional Neural Network Model for Automated Diagnosis of Schizophrenia Using EEG Signals. In Applied Sciences (Vol. 9, Issue 14, p. 2870). MDPI AG. https://doi.org/10.3390/app9142870

Subrata Kumer Paul & Rakhi Rani Paul, “Speech Recognition of Throat Microphone using MFCC Approach”, International Research Journal of Engineering and Technology (IRJET), Volume: 07 Issue: 05, May 2020, pp: 1940-1943

Nath, D., Anubhav, Singh, M., Sethia, D., Kalra, D., & Indu, S. (2020). A Comparative Study of Subject-Dependent and Subject-Independent Strategies for EEG-Based Emotion Recognition using LSTM Network. In Proceedings of the 2020 the 4th International Conference on Compute and Data Analysis. ICCDA 2020: 2020 The 4th International Conference on Compute and Data Analysis. ACM. https://doi.org/10.1145/3388142.3388167

Paul, S. K., & Paul, R. R. (2020). Effective Pitch Estimation using Canonical Correlation Analysis. In 2020 2nd International Conference on Advanced Information and Communication Technology (ICAICT). 2020 2nd International Conference on Advanced Information and Communication Technology (ICAICT). IEEE. https://doi.org/10.1109/icaict51780.2020.9333460

Zaman, S. M. T., Paul, S. K., Paul, R. R., & Hamid, Md. E. (2021). Detecting Diabetes in Human Body using Different Machine Learning Techniques. In 2021 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2). 2021 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2). IEEE. https://doi.org/10.1109/ic4me253898.2021.9768501

Paul, S. K., Paul, R. R., Nishimura, M., & Hamid, Md. E. (2021). Throat Microphone Speech Enhancement Using Machine Learning Technique. In Learning and Analytics in Intelligent Systems (pp. 1–11). Springer International Publishing. https://doi.org/10.1007/978-3-030-65407-8_1

Haque, Md. M., Kumer Paul, S., Paul, R. R., Ekramul Hamid, Md., Fahim, S., & Islam, S. (2022). A Comprehensive Study on Ethereum Blockchain-based Digital Marketplace using NFT Smart Contract Infrastructure. In 2022 25th International Conference on Computer and Information Technology (ICCIT). 2022 25th International Conference on Computer and Information Technology (ICCIT). IEEE. https://doi.org/10.1109/iccit57492.2022.10056108

Haque, Md. M., Paul, S. K., Paul, R. R., Rashidul Hasan, M. A. F. M., Fahim, S., & Islam, S. (2022). A Blockchain-Based Secure Payment System for Vehicle Fuel Filling Station. In 2022 25th International Conference on Computer and Information Technology (ICCIT). 2022 25th International Conference on Computer and Information Technology (ICCIT). Paper Publisher: IEEE. https://doi.org/10.1109/iccit57492.2022.10055001