Emotion-Adaptive Smart Lighting Using Real-Time EEG Feedback
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V3I3P115Keywords:
Affective Computing, Brain-computer Interface, Convolutional Neural Network, Correlated Color Temperature, Differential Entropy, EEG Emotion Recognition, Edge AI, Human-centric Lighting, Independent Component Analysis, Russell Circumplex Model, Smart Lighting, Valence-arousal ModelAbstract
By combining affective neuroscience, electroencephalography (EEG) technology with brain computer interface (BCI) and intelligent solid state lighting systems, a new paradigm for emotion-adaptive, real-time, closed-loop environments emerges. This paper reviews the latest research on emotion recognition by processing EEG signals and discusses the possibility of its application in smart lighting control systems whose response is based on the occupant's detected emotional state. The ocular artefact removal efficacies of the signal preprocessing pipelines using wavelet enhanced independent component analysis (ICA) are higher than 90% [5] and the classification accuracy of the differential entropy (DE) feature extraction and linear discriminant analysis (LDA) is up to 92.3% on benchmark datasets [1]. The convolutional neural network (CNN) architectures, deployed on edge AI platforms based on field-programmable gate array (FPGA), can achieve real-time inference performance of 16ms and complete system response time of less than 50ms [3]. Correlated color temperature (CCT) and illuminance (0–1,000 lx) are mapped bidirectionally to the 2D space of the valence–arousal space of emotions formulated in the Russell Circumplex Model of Affect [11] to facilitate “grading” light transitions from one emotion to another across 6 primary emotions. Preliminary results show that adaptive lighting conditions led to average increases of 27% in mood scores, 18% in creativity indices and 24% decreases in self-reported stress compared to static lighting conditions [7]. The results as a whole create a sound and scientifically valid blueprint for intelligent, human-centric light systems that promote occupant wellbeing, productivity and emotional regulation.
References
[1] Chen, D.-W., Miao, R., Yang, W.-Q., Liang, Y., Chen, H.-H., Huang, L., Deng, C.-J., & Han, N. (2019). A feature extraction method based on differential entropy and linear discriminant analysis for emotion recognition. Sensors, 19(7), 1631.
[2] Cupkova, D., Kajati, E., Mocnej, J., Papcun, P., Koziorek, J., & Zolotova, I. (2019). Intelligent human-centric lighting for mental wellbeing improvement. International Journal of Distributed Sensor Networks, 15(9), 1–13.
[3] Fang, W.-C., Wang, K.-Y., Fahier, N., Ho, Y.-L., & Huang, Y.-D. (2019). Development and validation of an EEG-based real-time emotion recognition system using edge AI computing platform with convolutional neural network system-on-chip design. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 9(4), 645–657.
[4] Huang, H., Xie, Q., Pan, J., He, Y., Wen, Z., Yu, R., & Li, Y. (2019). An EEG-based brain computer interface for emotion recognition and its application in patients with disorder of consciousness. IEEE Transactions on Affective Computing, 12(4), 832–842.
[5] Issa, M. F., & Juhasz, Z. (2019). Improved EOG artifact removal using wavelet enhanced independent component analysis. Brain Sciences, 9(12), 355.
[6] Koelstra, S., Mühl, C., Soleymani, M., Lee, J.-S., Yazdani, A., Ebrahimi, T., Pun, T., Nijholt, A., & Patras, I. (2012). DEAP: A database for emotion analysis using physiological signals. IEEE Transactions on Affective Computing, 3(1), 18–31.
[7] Lan, L., Hadji, S., Xia, L., & Lian, Z. (2020). The effects of light illuminance and correlated color temperature on mood and creativity. Building Simulation, 14(3), 463–475.
[8] Liu, J., Wu, G., Luo, Y., Qiu, S., Yang, S., Li, W., & Bi, Y. (2020). EEG-based emotion classification using a deep neural network and sparse autoencoder. Frontiers in Systems Neuroscience, 14, Article 43.
[9] Pan, J., Xie, Q., Huang, H., He, Y., Sun, Y., Yu, R., & Li, Y. (2018). Emotion-related consciousness detection in patients with disorders of consciousness through an EEG-based BCI system. Frontiers in Human Neuroscience, 12, Article 198.
[10] Picard, R. W. (1997). Affective computing. MIT Press.
[11] Russell, J. A. (1980). A circumplex model of affect. Journal of Personality and Social Psychology, 39(6), 1161–1178.
[12] Shu, L., Xie, J., Yang, M., Li, Z., Li, Z., Liao, D., Xu, X., & Yang, X. (2018). A review of emotion recognition using physiological signals. Sensors, 18(7), 2074.
[13] Zhang, Y., Chen, J., Tan, J. H., Chen, Y., Chen, Y., Li, D., Yang, L., Su, J., Huang, X., & Che, W. (2020). An investigation of deep learning models for EEG-based emotion recognition. Frontiers in Neuroscience, 14, Article 622759.
[14] Zheng, W.-L., & Lu, B.-L. (2015). Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks. IEEE Transactions on Autonomous Mental Development, 7(3), 162–175.
[15] Zheng, W.-L., Zhu, J.-Y., & Lu, B.-L. (2019). Identifying stable patterns over time for emotion recognition from EEG. IEEE Transactions on Affective Computing, 10(3), 417–429.
