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

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

Downloads

Published

2023-05-30

Issue

Vol. 11 No. 3 (2023): International Journal of Innovative Research in Computer Science and Technology(May ) 2023

Section

Articles

How to Cite

EEG-Based Multi-Class Emotion Recognition using Hybrid LSTM Approach . (2023). International Journal of Innovative Research in Computer Science & Technology, 11(3), 1–6. https://doi.org/10.55524/ijircst.2023.11.3.1
Crossref
Scopus
Google Scholar
Europe PMC