Multi Class Emotion Classification using PSD and CNN

Emotion identification based on electroencephalography (EEG) data has become a popular area of study in human-machine interactions. Conventional machine learning techniques employ carefully created classifiers using hand-made features that may be restricted to domain expertise. We suggested a convolutional neural network (CNN) model to automatically extract the spatiotemporal information from power spectral density (PSD) features extracted from EEG signals, motivated by the exceptional performance of deep learning techniques in recognition tests. The proposed model achieves a high accuracy rate of 90% using the preprocessing method with baseline signals, for the four-class classification task in the SEED_IV dataset. We have achieved a standard deviation of 4.3% in multiple trials

CNN, EEG, emotion recognition, PSD, SEED_IV

1. R. W. Picard. Affective Computing. Cambridge, MA: MIT Press, 1997. [Google Scholar] [Crossref]

2. Xiang. Li, Dawei. Song, Peng. Zhang, Yazhou. Zhang, Yuexian. Hou, and Bin. Hu, “Exploring EEG features in cross-subject emotion recognition,” Frontiers in Neuroscience, 12:162, 2018. [Google Scholar] [Crossref]

3. C. Niemic, “Studies of emotion: A theoretical and empirical review of psychophysiological studies of emotion.” Journal of Undergraduate Research, 2004. [Google Scholar] [Crossref]

4. H. Mohamed, B. Zaidan and A. A. Zaidan, “A systematic review for human EEG brain signals based emotion classification, feature extraction, brain condition, group comparison,” Journal of Medical systems, vol.42, pp. 162, 2018, doi: 10.1007/s10916-018-1020-8. [Google Scholar] [Crossref]

5. Duan R.-N, Wang X.-W, Lu B.-L. EEG-based emotion recognition in listening music by using support vector machine and linear dynamic system[C]// International Conference on Neural Information Processing. Springer. [S.l.]: [s.n.], 2012: 468–475. [Google Scholar] [Crossref]

6. Casella G, Fienberg S, Olkin I. Time Series Analysis and Its Applications - With R Examples [J]. Journal of the American Statistical Association, 2006, 97(458): 656–657. [Google Scholar] [Crossref]

7. Schirrmeister R.T, Springenberg J.T, Fiederer L.D.J, Glasstetter M, Eggensperger K, Tangermann M, Hutter F, Burgard W, Ball T. “Convolutional neural networks for deep learning in EEG decoding and visualization,” 2017; 38:5391–420; Hum Brain Mapp. [Google Scholar] [Crossref]

8. W. L. Zheng and B. L. lu, “Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks,” IEEE Transaction on Autonomous mental development, vol. 7, no. 3, pp. 162-175, 2015. [Google Scholar] [Crossref]

9. P. Zhong, Di Wang and C. Miao, “EEG-based emotion recognition using regularized graph neural network,” IEEE transaction on Affective Computing, vol.11, no.2, pp. 99-111, 2020. [Google Scholar] [Crossref]

10. T. Song, W. Zheng, P. Song and Z. Cui’ “EEG emotion recognition using dynamical graph convolutional neural networks,” IEEE transactions on Affective Computing, vol. 11, no. 3, pp. 532-541, 2020. [Google Scholar] [Crossref]

11. Jinpeng Li, Z. Zhang and H. He, “Implementation of EEG emotion recognition system based on hierarchical convolutional neural network,” International conference on Brain inspired Cognitive Systems, Nov. 2016. [Google Scholar] [Crossref]

12. Y. Li, W. Zheng, Y. Zong, T. Zhang and X. Zhou, “A bi-hemisphere domain adversarial neural network model for EEG emotion recognition,” IEEE transaction on Affective Computing, vol. 12, no. 2, pp. 494-504, 2021. [Google Scholar] [Crossref]

13. Nandini K. Bhandari, and Manish Jain, “EEG Emotion Recognition using Convolution Neural Network,” 4th International Conference on Machine Intelligence and Signal Processing, NIT Raipur, 12-14 March, 2022. [Google Scholar] [Crossref]

14. https://bcmi.sjtu.edu.cn/home/seed/seed-iv.html [Google Scholar] [Crossref]

15. S. Noshadi, V. Abootalebai, M. T. Sadeghi, and M. S. Shahvazian, “Selection of an efficient feature space for EEG-based mental task discrimination,” Bio cybernetics and biomedical Eng., vol. 34, no. 3, pp. 159-168, 2014. [Google Scholar] [Crossref]

16. LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015). https://doi.org/10.1038/nature14539 [Google Scholar] [Crossref]

17. P. Amini, S. A. Zahiri Motlagh and M. Nezhadpour, "A Large-Scale Infrastructure for Serious Games Services," 2nd National and 1st International Digital Games Research Conference: Trends, Technologies, and Applications (DGRC), Tehran, Iran, pp. 27-33, 2018. [Google Scholar] [Crossref]

18. S. Ioffe and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift", 2015. [Google Scholar] [Crossref]

19. T. Sledevic, "Adaptation of Convolution and Batch Normalization Layer for CNN Implementation on FPGA," 2019 Open Conference of Electrical, Electronic and Information Sciences (eStream), Vilnius, Lithuania, 2019, pp. 1-4, doi: 10.1109/eStream.2019.8732160. [Google Scholar] [Crossref]

20. W.L. Zheng, W. Liu, Y. Lu, B. L. Lu and A. Cichocki, “EmotionMerer: A multimodal framework for recognizing human emotions,” IEEE transactions on Cybernetics, vol. 49, no. 3, pp. 1110-1122, 2019. [Google Scholar] [Crossref]

21. J. A. Suykens and J. Vandewalle, “Least squares support vector machine classifiers,” Neural Processing Letters, vol. 9, no. 3, pp. 293-300, 1999. [Google Scholar] [Crossref]

22. L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5-32, 2001. [Google Scholar] [Crossref]

23. B. Thompson, “Canonical correlation analysis,” Encyclopedia of Statistics in Behavioral Science, 2005. [Google Scholar] [Crossref]

24. W. Zheng, “Multichannel EEG-based emotion recognition via group sparse canonical correlation analysis,” IEEE transaction on Cognitive and development systems, vol. 9, no. 3, pp. 281-290, 2017 [Google Scholar] [Crossref]

25. Y. Li, W. Zheng, Z. Cui, Y. Zong and S. Ge, “EEG emotion recognition based on graph regularized sparse linear regression,” Neural Processing Letters, pp. 1-17, 2018. [Google Scholar] [Crossref]

26. M. Defferrard, X. Bresson and P. Vandergheynst, “Convolutional neural networks on graphs with fast localized spectral filtering,” Conference on Neural information processing systems (NIPS), pp. 3844-3852, 2016. [Google Scholar] [Crossref]

27. Y. Ganin, E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F.Laviolette, M. Marchand and V. Lampitsky, “Domain-adversarial training of neural networks,” journal of Machine Learning Research, vol.17, no. 59, pp. 1-35, 2016. [Google Scholar] [Crossref]

28. Y. Li, W. Zheng, Z. Cui, T. Zhang and Y. Zong, “A novel neural network model based on cerebral hemispheric asymmetry for EEG emotion recognition,” International joint Conference on Artificial intelligence, pp. 1561-1567, 2018. [Google Scholar] [Crossref]

29. Y. Li, L.Wang, T. Song, W. Zheng, Y. Zong, “A novel Bi-hemispheric discrepancy model for EEG emotion recognition,” IEEE transaction on Cognitive and Development systems, vol. 13, no. 2, pp. 354-367, 2021. [Google Scholar] [Crossref]

30. T. Song, W. Zheng, P. Song and Z. Cui’ “EEG emotion recognition using dynamical graph convolutional neural networks,” IEEE transactions on Affective Computing, vol. 11, no. 3, pp. 532-541, 2020 [Google Scholar] [Crossref]

• A Study to Assess the Impact of a Nurse-Led Educational Intervention on Knowledge Regarding Oral Health Among Primigravida in Selected Hospitals of Navi Mumbai
• Attitude towards Mathematics and Science in Relation to STEM Career Aspirations among Senior Secondary School Students
• AI-Driven Personalized Learning in Educational Systems: A Framework for Adaptive Learning and Decision Support
• Institutionalizing Indigenous Peoples Education in Philippine Basic Education: Development of the Integrated Institutionalization Framework for Indigenous Peoples Education (IIF-IPEd)
• Toward an Integrated Theory of Enterprise Risk Management: A Multi-Theoretical Conceptual Framework