Multi-Kernel Temporal and Spatial Convolution for EEG-Based Emotion Classification
Abstract
:1. Introduction
1.1. Background
1.2. Research Gap
1.3. Motivation and Contribution
2. Related Works
2.1. Feature Extraction and Classification
2.2. End-to-End Convolutional Neural Networks
3. Proposed Method
3.1. Multi-Kernel Temporal Processing
3.2. Remaining Modules
3.2.1. Spatial Processing
3.2.2. Channel Recalibration
3.2.3. Classification
4. Experiments and Results
4.1. Experiment Setting
4.1.1. Datasets
4.1.2. Baseline and Existing Models
4.1.3. Comparison Approaches
4.2. SEED Experiments and Results
4.3. DEAP Experiments and Results
4.4. Ablation Study
5. Discussion
5.1. Classification Performance
5.2. Architectures and Design Choices
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Al-Nafjan, A.N.; Hosny, M.I.; Al-Ohali, Y.; Al-Wabil, A. Review and Classification of Emotion Recognition Based on EEG Brain-Computer Interface System Research: A Systematic Review. Appl. Sci. 2017, 7, 1239. [Google Scholar] [CrossRef] [Green Version]
- Millan, J.d.R.; Rupp, R.; Müller-Putz, G.; Murray-Smith, R.; Giugliemma, C.; Tangermann, M.; Vidaurre, C.; Cincotti, F.; Kübler, A.; Leeb, R.; et al. Combining Brain–Computer Interfaces and Assistive Technologies: State-of-the-Art and Challenges. Front. Neurosci. 2010, 4, 161–175. [Google Scholar] [CrossRef] [PubMed]
- Jamil, N.; Belkacem, A.N.; Ouhbi, S.; Lakas, A. Noninvasive Electroencephalography Equipment for Assistive, Adaptive, and Rehabilitative Brain–Computer Interfaces: A Systematic Literature Review. Sensors 2021, 21, 4754. [Google Scholar] [CrossRef]
- Tangermann, M.W.; Krauledat, M.; Grzeska, K.; Sagebaum, M.; Vidaurre, C.; Blankertz, B.; Müller, K.R. Playing Pinball with Non-Invasive BCI. In Proceedings of the 21st International Conference on Neural Information Processing Systems, Vancouver, BC, Canada, 8–10 December 2008; Curran Associates Inc.: Red Hook, NY, USA, 2008. NIPS’08. pp. 1641–1648. [Google Scholar]
- Singh, A.K.; Wang, Y.K.; King, J.T.; Lin, C.T. Extended Interaction With a BCI Video Game Changes Resting-State Brain Activity. IEEE Trans. Cogn. Dev. Syst. 2020, 12, 809–823. [Google Scholar] [CrossRef]
- Rached, T.S.; Perkusich, A. Emotion Recognition Based on Brain-Computer Interface Systems. In Brain-Computer Interface Systems; Fazel-Rezai, R., Ed.; IntechOpen: Rijeka, Croatia, 2013; Chapter 13. [Google Scholar] [CrossRef] [Green Version]
- Torres, E.P.; Torres, E.A.; Hernández-Álvarez, M.; Yoo, S.G. EEG-Based BCI Emotion Recognition: A Survey. Sensors 2020, 20, 5083. [Google Scholar] [CrossRef]
- Acharya, U.R.; Molinari, F.; Subbhuraam, V.S.; Chattopadhyay, S.; Kh, N.; Suri, J. Automated diagnosis of epileptic EEG using entropies. Biomed. Signal Process. Control 2012, 7, 401–408. [Google Scholar] [CrossRef] [Green Version]
- Asadzadeh, S.; Yousefi Rezaii, T.; Beheshti, S.; Delpak, A.; Meshgini, S. A systematic review of EEG source localization techniques and their applications on diagnosis of brain abnormalities. J. Neurosci. Methods 2020, 339, 108740. [Google Scholar] [CrossRef]
- van Vliet, M.; Robben, A.; Chumerin, N.; Manyakov, N.V.; Combaz, A.; Van Hulle, M.M. Designing a brain-computer interface controlled video-game using consumer grade EEG hardware. In Proceedings of the 2012 ISSNIP Biosignals and Biorobotics Conference: Biosignals and Robotics for Better and Safer Living (BRC), Manaus, Brazil, 9–11 January 2012; pp. 1–6. [Google Scholar] [CrossRef]
- Klimesch, W. EEG alpha and theta oscillations reflect cognitive and memory performance: A review and analysis. Brain Res. Rev. 1999, 29, 169–195. [Google Scholar] [CrossRef]
- Schmidt, L.A.; Trainor, L.J. Frontal brain electrical activity (EEG) distinguishes valence and intensity of musical emotions. Cogn. Emot. 2001, 15, 487–500. [Google Scholar] [CrossRef]
- Huang, D.; Guan, C.; Ang, K.K.; Zhang, H.; Pan, Y. Asymmetric spatial pattern for EEG-based emotion detection. In Proceedings of the International Joint Conference on Neural Networks (IJCNN), San Diego, CA, USA, 17–21 June 1990; IEEE: Piscataway, NJ, USA; pp. 1–7. [Google Scholar] [CrossRef] [Green Version]
- Jatupaiboon, N.; Pan-ngum, S.; Israsena, P. Emotion classification using minimal EEG channels and frequency bands. In Proceedings of the 10th international Joint Conference on Computer Science and Software Engineering (JCSSE), Khon Kaen, Thailand, 29–13 May 2013; IEEE: Piscataway, NJ, USA, 2013; pp. 21–24. [Google Scholar] [CrossRef]
- Schirrmeister, R.T.; Springenberg, J.T.; Fiederer, L.D.J.; Glasstetter, M.; Eggensperger, K.; Tangermann, M.; Hutter, F.; Burgard, W.; Ball, T. Deep learning with convolutional neural networks for EEG decoding and visualization. Hum. Brain Mapp. 2017, 38, 5391–5420. [Google Scholar] [CrossRef] [Green Version]
- Lawhern, V.J.; Solon, A.J.; Waytowich, N.R.; Gordon, S.M.; Hung, C.P.; Lance, B.J. EEGNet: A compact convolutional neural network for EEG-based brain–computer interfaces. J. Neural Eng. 2018, 15, 056013. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Jenke, R.; Peer, A.; Buss, M. Feature Extraction and Selection for Emotion Recognition from EEG. IEEE Trans. Affect. Comput. 2014, 5, 327–339. [Google Scholar] [CrossRef]
- Chanel, G.; Kierkels, J.J.; Soleymani, M.; Pun, T. Short-term emotion assessment in a recall paradigm. Int. J.-Hum.-Comput. Stud. 2009, 67, 607–627. [Google Scholar] [CrossRef]
- Bos, D.O. EEG-based emotion recognition. Influ. Vis. Audit. Stimuli 2006, 56, 1–17. [Google Scholar]
- Ramoser, H.; Muller-Gerking, J.; Pfurtscheller, G. Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Trans. Rehabil. Eng. 2000, 8, 441–446. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Ang, K.K.; Chin, Z.Y.; Wang, C.; Guan, C.; Zhang, H. Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b. Front. Neurosci. 2012, 6, 39. [Google Scholar] [CrossRef] [Green Version]
- Zheng, W.L.; Lu, B.L. Investigating Critical Frequency Bands and Channels for EEG-based Emotion Recognition with Deep Neural Networks. IEEE Trans. Auton. Ment. Dev. 2015, 7, 162–175. [Google Scholar] [CrossRef]
- Li, M.; Lu, B.L. Emotion classification based on gamma-band EEG. In Proceedings of the 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Minneapolis, MN, USA, 2–6 September 2009; pp. 1223–1226. [Google Scholar] [CrossRef]
- Candra, H.; Yuwono, M.; Chai, R.; Handojoseno, A.; Elamvazuthi, I.; Nguyen, H.T.; Su, S. Investigation of window size in classification of EEG-emotion signal with wavelet entropy and support vector machine. In Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy, 25–19 August 2015; pp. 7250–7253. [Google Scholar] [CrossRef] [Green Version]
- Shu, L.; Xie, J.; Yang, M.; Li, Z.; Li, Z.; Liao, D.; Xu, X.; Yang, X. A review of emotion recognition using physiological signals. Sensors 2018, 18, 2074. [Google Scholar] [CrossRef] [Green Version]
- Hu, J.; Shen, L.; Sun, G. Squeeze-and-Excitation Networks. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 42, 2011–2023. [Google Scholar] [CrossRef] [Green Version]
- Koelstra, S.; Mühl, C.; Soleymani, M.; Lee, J.S.; Yazdani, A.; Ebrahimi, T.; Pun, T.; Nijholt, A.; Patras, I. DEAP: A Database for Emotion Analysis Using Physiological Signals. IEEE Trans. Affect. Comput. 2011, 3, 18–31. [Google Scholar] [CrossRef] [Green Version]
- Abadi, M.; Agarwal, A.; Barham, P.; Brevdo, E.; Chen, Z.; Citro, C.; Corrado, G.S.; Davis, A.; Dean, J.; Devin, M.; et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. 2015. Available online: tensorflow.org (accessed on 28 September 2022).
- Keras. 2015. Available online: https://github.com/fchollet/keras (accessed on 28 September 2022).
- Emsawas, T.; Kimura, T.; Fukui, K.i.; Numao, M. Comparative Study of Wet and Dry Systems on EEG-Based Cognitive Tasks. In Proceedings of the International Conference on Brain Informatics, Padua, Italy, 19 September 2020; Springer: Cham, Switzerland; pp. 309–318. [Google Scholar]
- Hagad, J.L.; Kimura, T.; Fukui, K.i.; Numao, M. Learning subject-generalized topographical EEG embeddings using deep variational autoencoders and domain-adversarial regularization. Sensors 2021, 21, 1792. [Google Scholar] [CrossRef] [PubMed]
SEED-2 Classes | SEED-3 Classes | DEAP-Valence | DEAP-Arousal | |||||
---|---|---|---|---|---|---|---|---|
Models | Subj. Dep. | Subj. Indep. | Subj. Dep. | Subj. Indep. | Subj. Dep. | Subj. Indep. | Subj. Dep. | Subj. Indep. |
Chance Level | 50.0 ± 0.0 | 50.0 ± 0.0 | 33.3 ± 0.0 | 33.3 ± 0.0 | 56.6 ± 9.2 | 56.6 ± 9.2 | 58.9 ± 15.5 | 58.9 ± 15.5 |
KNN | 70.5 ± 12.3 | 72.0 ± 7.8 | 52.5 ± 12.7 | 43.7 ± 8.0 | 55.9 ± 6.9 | 52.9 ± 5.2 | 61.6 ± 11.0 | 53.0 ± 10.7 |
RF | 87.0 ± 7.7 | 73.4 ± 8.5 | 71.7 ± 9.5 | 52.7 ± 6.9 | 55.6 ± 7.3 | 51.1 ± 3.6 | 61.8 ± 10.6 | 50.0 ± 7.5 |
FCN | 77.4 ± 11.9 | 66.1 ± 10.1 | 56.5 ± 13.6 | 46.4 ± 8.4 | 54.8 ± 6.4 | 53.9 ± 6.6 | 60.8 ± 10.9 | 50.6 ± 13.2 |
Deep ConvNet | 94.8 ± 3.4 | 72.0 ± 7.8 | 85.0 ± 4.5 | 51.1 ± 7.4 | 76.6 ± 3.4 | 47.5 ± 7.0 | 78.6 ± 4.6 | 51.8 ± 13.0 |
Shallow ConvNet | 91.2 ± 7.4 | 74.0 ± 8.5 | 82.1 ± 7.7 | 54.4 ± 7.4 | 76.0 ± 6.9 | 49.1 ± 7.7 | 78.9 ± 6.7 | 51.0 ± 14.7 |
EEGNet | 89.1 ± 3.6 | 70.1 ± 9.5 | 76.3 ± 15.1 | 47.8 ± 9.7 | 79.2 ± 6.3 | 49.3 ± 7.2 | 82.1 ± 6.9 | 51.4 ± 10.3 |
MultiT-S ConvNet | 95.2 ± 3.2 | 75.1 ± 8.4 | 86.0 ± 5.3 | 54.6 ± 6.8 | 77.6 ± 5.8 | 52.6 ± 8.8 | 82.2 ± 6.5 | 51.5 ± 10.4 |
No. of Temp. Filter | No. of Spat. Filter | No. of Temp-Spat Filter | Trainable Parameters | Acc.(%) | |
---|---|---|---|---|---|
Deep ConvNet | 24 | 24 | 48 + 96 + 192 = 336 | 182,497 | 72.04 * |
Deep ConvNet (+) | 12 × 4 = 48 | 12 | 24 + 48 + 96 = 168 | 73,777 | 73.96 * |
Shallow ConvNet | 40 | 40 | 101,281 | 73.96 | |
Shallow ConvNet (+) | 20 × 4 = 80 | 20 | 101,721 | 73.19 | |
EEGNet | 32 | 64 | 64 | 13,537 | 70.15 |
EEGNet (+) | 16 × 4 = 64 | 32 | 32 | 16,177 | 74.00 ** |
MultiT-S ConvNet | 24 × 4 = 96 | 64 | 30,313 | 75.13 |
MultiT-S ConvNet | vs. Deep ConvNet | vs. Shallow ConvNet | vs. EEGNet | |
---|---|---|---|---|
Accuracy (%) | 71.9 | +2.2 | +2.3 | +3.7 |
Minimum freq. covered | 5 Hz | 40 Hz | 17 Hz | 2 Hz |
Number of Trainable Parameters | 30,313 | −152,184 | −43,464 | +14,136 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Emsawas, T.; Morita, T.; Kimura, T.; Fukui, K.-i.; Numao, M. Multi-Kernel Temporal and Spatial Convolution for EEG-Based Emotion Classification. Sensors 2022, 22, 8250. https://doi.org/10.3390/s22218250
Emsawas T, Morita T, Kimura T, Fukui K-i, Numao M. Multi-Kernel Temporal and Spatial Convolution for EEG-Based Emotion Classification. Sensors. 2022; 22(21):8250. https://doi.org/10.3390/s22218250
Chicago/Turabian StyleEmsawas, Taweesak, Takashi Morita, Tsukasa Kimura, Ken-ichi Fukui, and Masayuki Numao. 2022. "Multi-Kernel Temporal and Spatial Convolution for EEG-Based Emotion Classification" Sensors 22, no. 21: 8250. https://doi.org/10.3390/s22218250
APA StyleEmsawas, T., Morita, T., Kimura, T., Fukui, K.-i., & Numao, M. (2022). Multi-Kernel Temporal and Spatial Convolution for EEG-Based Emotion Classification. Sensors, 22(21), 8250. https://doi.org/10.3390/s22218250