Abstract
Automated emotion classification becomes more and more important, as intelligent software systems can better serve users, when they can reliably assess their emotional state and adapt interactive applications accordingly and in real-time. EEG-based brain-computer interfaces (BCI) provide the individual data that can be exploited for emotion classification. However, AI-based emotion classification on EEG-data typically requires computationally intensive training and powerful hardware when the results are needed in real-time. A survey of the related work has shown that not many real-time solutions exist for energy-efficient hardware.
In this paper we present an approach for finding a global best channel set universally suitable for all subjects with high classification accuracy. In our research we used Russel’s emotion model and the DEAP data set. By applying a total of six nature-based swarm channel selection algorithms and one classical selection algorithm, the different algorithms could be compared with each other. The resulting reduced channel set consists of only 7 channels.
With the set it is possible to classify emotions in real-time using low-level energy-efficient hardware. Emotion classification on the Raspberry Pi only takes between 82 and 93ms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ekman, P.: Emotions revealed. BMJ 328, 0405184 (2004). https://doi.org/10.1136/SBMJ.0405184
Gilbert, D.T.: Stumbling on happiness. Vintage Books, New York (2007)
Keltner, D., Lerner, J.S.: Emotion. Handbook of. Social Psychology. (2010). https://doi.org/10.1002/9780470561119.SOCPSY001009
Oatley, K.: Best Laid Schemes: The Psychology of the Emotions (1992)
Kim, S.-H., Yang, H.-J., Nguyen, N.A.T., Prabhakar, S.K., Lee, S.-W.: WeDea: a new EEG-based framework for emotion recognition. IEEE J. Biomed. Health Inform. 26, 264–275 (2022). https://doi.org/10.1109/JBHI.2021.3091187
Pothula, P.K., Marisetty, S., Rao, M.: A real-time seizure classification system using computer vision techniques. SysCon 2022 - 16th Annual IEEE International Systems Conference, Proceedings (2022). https://doi.org/10.1109/SYSCON53536.2022.9773923
Li, W.-C., Yang, C.-J., Liu, B.-T., Fang, W.-C.: A real-time affective computing platform integrated with ai system-on-chip design and multimodal signal processing system. In: 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 522–526. IEEE (2021). https://doi.org/10.1109/EMBC46164.2021.9630979
Leite, D., Frigeri, V., Medeiros, R.: Adaptive gaussian fuzzy classifier for real-time emotion recognition in computer games. In: 2021 IEEE Latin American Conference on Com-putational Intelligence, LA-CCI 2021 (2021). https://doi.org/10.48550/arxiv.2103.03488
Huang, H., et al.: An EEG-based brain computer interface for emotion recognition and its application in patients with disorder of consciousness. IEEE Trans. Affect Comput. 12, 832–842 (2021). https://doi.org/10.1109/TAFFC.2019.2901456
Kim, S.-H., Yang, H.-J., Nguyen, N.A.T., Lee, S.-W.: AsEmo: automatic approach for EEG-based multiple emotional state identification. IEEE J Biomed. Health Inform. 25, 1508–1518 (2021). https://doi.org/10.1109/JBHI.2020.3032678
Bandara, S.K., Jayalath, B.P., Wijesinghe, U.C., Bandara, S.K., Haddela, P.S., Wick-ramasinghe, L.M.: EEG based real-time system for video advertisement recommendation. In: 21st International Conference on Advances in ICT for Emerging Regions, ICter 2021 - Proceedings, pp. 201–206 (2021). https://doi.org/10.1109/ICTER53630.2021.9774791
Khateeb, M., Anwar, S.M., Alnowami, M.: Multi-domain feature fusion for emotion classification using DEAP dataset. IEEE Access. 9, 12134–12142 (2021). https://doi.org/10.1109/ACCESS.2021.3051281
Wang, K.Y., Huang, Y. de, Ho, Y.L., Fang, W.C.: A customized convolutional neural network design using improved softmax layer for real-time human emotion recognition. In: Proceedings 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2019, pp. 102–106 (2019). https://doi.org/10.1109/AICAS.2019.8771616
Yang, C.J., Li, W.C., Wan, M.T., Fang, W.C.: Real-time EEG-based affective computing using on-chip learning long-term recurrent convolutional network. In: Proceedings - IEEE In-ternational Symposium on Circuits and Systems. 2021-May (2021). https://doi.org/10.1109/ISCAS51556.2021.9401588
Li, W.-C., Yang, C.-J., Fang, W.-C.: A real-time emotion recognition system based on an AI system-on-chip design. In: 2020 International SoC Design Conference (ISOCC), pp. 29–30. IEEE (2020). https://doi.org/10.1109/ISOCC50952.2020.9333072
Val-Calvo, M., Alvarez-Sanchez, J.R., Ferrandez-Vicente, J.M., Fernandez, E.: Affective robot story-telling human-robot interaction: exploratory real-time emotion estimation analysis using facial expressions and physiological signals. IEEE Access. 8, 134051–134066 (2020). https://doi.org/10.1109/ACCESS.2020.3007109
Alakus, T.B., Gonen, M., Turkoglu, I.: Database for an emotion recognition system based on EEG signals and various computer games – GAMEEMO. Biomed. Signal Process Control. 60,(2020)
Gonzalez, H.A., Muzaffar, S., Yoo, J., Elfadel, I.M.: An inference hardware accelerator for EEG-based emotion detection. In: Proceedings - IEEE International Symposium on Circuits and Systems. 2020-October (2020). https://doi.org/10.1109/ISCAS45731.2020.9180728/VIDEO
Aslam, A.R., Altaf, M.A.: bin: an on-chip processor for chronic neurological disorders assistance using negative affectivity classification. IEEE Trans. Biomed. Circuits Syst. 14, 838–851 (2020). https://doi.org/10.1109/TBCAS.2020.3008766
Wundt, W.: Grundzuge der Physiologischen Psychologie. Am. J. Psychol. 6, 298 (1894). https://doi.org/10.2307/1410982
Russell, J.A.: A circumplex model of affect. J. Pers. Soc. Psychol. 39, 1161–1178 (1980). https://doi.org/10.1037/h0077714
Koelstra, S., et al.: DEAP: a database for emotion analysis; using physiological signals. IEEE Trans. Affect Comput. 3, 18–31 (2012). https://doi.org/10.1109/T-AFFC.2011.15
Balic, S., Kleybolte, L., Märtin, C.: A Swarm Intelligence Approach: Combination of Different EEG-channel optimization techniques to enhance emotion recognition. In: Kurosu, M. (eds.) Human-Computer Interaction. Technological Innovation. HCII 2022. Lecture Notes in Computer Science, vol. 13303, pp. 303–317. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-05409-9_23
Developers, T.: TensorFlow (2022). https://doi.org/10.5281/ZENODO.7604251
Harris, C.R., et al.: Array programming with NumPy. Nature 585, 357–362 (2020). https://doi.org/10.1038/s41586-020-2649-2
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kleybolte, L.A., Märtin, C. (2023). A Novel EEG-Based Real-Time Emotion Recognition Approach Using Deep Neural Networks on Raspberry Pi. In: Kurosu, M., Hashizume, A. (eds) Human-Computer Interaction. HCII 2023. Lecture Notes in Computer Science, vol 14012. Springer, Cham. https://doi.org/10.1007/978-3-031-35599-8_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-35599-8_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35598-1
Online ISBN: 978-3-031-35599-8
eBook Packages: Computer ScienceComputer Science (R0)