Emotion-To-Motion: A Wearable EEG–GSR Biofeedback System For Emotion-Aware Meditation

Prapawit Intun

doi:10.29284/aacbjq54

Authors

Prapawit Intun Participatory Citizen Lab. Bangkok, Thailand

DOI:

https://doi.org/10.29284/aacbjq54

Keywords:

Biofeedback, electroencephalography (EEG), galvanic skin response (GSR), meditation.

Abstract

This paper presents Emotion-to-Motion, a wearable biofeedback system that translates physiological signals into real-time visual and kinetic feedback to support meditation and self-reflection. The experimental setup combines a consumer-grade EEG headband (Muse 2) and a wrist-worn galvanic skin response (GSR) sensor. During five-minute meditation sessions, the system streams brain activity and skin conductance, performs basic signal cleaning, extracts window-level features related to arousal and attentional state, and estimates user condition in real time. A machine learning model classifies each 5-second window into one of five states: calm, focused, excited, stressed, or neutral.

The inferred state and raw signals are displayed through a web-based dashboard that supports live monitoring and session review. In parallel, each detected state is mapped to a short text prompt that drives a depth-map-inspired generative visual pattern. The visual layer is coupled to an Arduino-controlled linear actuator, which moves upward or downward according to the recognized state, closing the loop between sensing, on-screen representation, and physical motion. A pilot study suggests that the end-to-end pipeline can operate reliably over full sessions and that embodied motion cues help participants notice and reflect on fluctuations in their internal state. The paper details the system architecture, the feature-based classification pipeline, and the command-filtering logic used to stabilize actuator behavior for a meditation context, and discusses applications in biofeedback training, interactive art, and emotion-aware installation or spatial prototypes.

References

[1] Y. Zhao, Y. Jiang, X. Liu, Q. Xu, L. Zhao, and Y. Peng, “Workload electroencephalogram characteristics in cognitive tasks based on intra- and inter-hemispheric asymmetry,” IEEE Access, vol. 11, pp. 42377–42388, 2023.

[2] O. E. Krigolson, C. Williams, A. Norton, C. Hassall, L. J. Colino, and K. R. Krigolson, “Evaluating the feasibility of a consumer-grade wearable EEG headband for assessing meditation and mindfulness in a real-world head-to-head comparison with established laboratory equipment,” Front. Neurosci., vol. 15, p. 634147, 2021.

[3] I. Daly, D. Nicolaou, S. J. Nasuto, and K. Warwick, “A review, current challenges, and future possibilities on emotion recognition using machine learning and physiological signals,” IEEE Access, vol. 7, pp. 140990–141020, 2019.

[4] J. A. Russell, “A circumplex model of affect,” J. Pers. Soc. Psychol., vol. 39, no. 6, pp. 1161–1178, Dec. 1980.

[5] P. Remis-Serna, M. A. Ramírez-Moreno, J. de J. Lozoya-Santos, M. Cebral-Loureda, and C. S. Vélez-Saboyá, “A systematic review of technology-aided stress management systems: Automatic measurement, detection and control,” IEEE Access, vol. 11, pp. 106352–106374, 2023.

[6] E. Gkintoni, A. Aroutzidis, H. Antonopoulou, and C. Halkiopoulos, “From neural networks to emotional networks: A systematic review of EEG-based emotion recognition in cognitive neuroscience and real-world applications,” Brain Sci., vol. 15, no. 2, p. 186, 2025.

[7] M. A. Blanco-Ríos, M. O. Candela-Leal, C. Orozco-Romo, P. Remis-Serna, C. S. Vélez-Saboyá, J. de Jesús Lozoya-Santos, M. Cebral-Loureda, and M. A. Ramírez-Moreno, “Real-time EEG-based emotion recognition for neurohumanities: Perspectives from principal component analysis and tree-based algorithms,” Front. Hum. Neurosci., vol. 18, Art. no. 1319574, 2024.

[8] D. Girardi, F. Lanubile, and N. Novielli, “Emotion detection using noninvasive low cost sensors,” in Proc. 7th Int. Conf. Affective Comput. Intell. Interact. (ACII), San Antonio, TX, USA, 2017, pp. 125–130.

[9] J. M. Gavhane, G. Shirke, S. Modak, J. Prasad, and S. Raman, “AI-driven emotion recognition meets EEG for next-generation mental well-being,” 2025. [Online]. Available: https://www.researchgate.net/publication/389753730

[10] M. A. Becerra, C. Duque-Mejia, A. Castro-Ospina, L. Serna-Guarín, C. Mejía, and E. Duque-Grisales, “EEG-based biometric identification and emotion recognition: An overview,” Computers, vol. 14, no. 8, p. 299, 2025.

[11] M. J. A. Awan, O. Mazhar, O. Mazhar, A. Y. Zappa, and R. Masood, “AIoT for human emotion recognition: Potentials, challenges, and healthcare applications,” Comput. Sci. Rev., vol. 52, Art. no. 100683, 2024.

[12] K. Klęczek, A. Rice, and M. Alimardani, “Robots as mental health coaches: A study of emotional responses to technology-assisted stress management tasks using physiological signals,” Sensors, vol. 24, no. 13, p. 4301, 2024.