MindArc: On-Device AI for Digital Wellbeing and Habit Formation

References

[1] S. D. Ristianto, A. Putri, and Y. Rosmansyah, “Personalized Gamifica-tion: A Technological Approach for Student Education—A Systematic Literature Review,” IEEE Access, 2025.

[2] D. A. Rohani, A. Springer, V. Hollis, J. E. Bardram, and S. Whittaker, “Recommending Activities for Mental Health and Well-being: Insights from Two User Studies,” IEEE Transactions on Emerging Topics in Computing, vol. 9, no. 1, pp. 1–11, 2021.

[3] F. T. Achal, M. S. Ahmmed, and T. T. Aurpa, “Severity Detection of Problematic Smartphone Usage (PSU) and its Effect on Human Lifestyle using Machine Learning,” in Proc. IEEE 8th Int. Conf. Convergence in Technology (I2CT), 2023.

[4] G. Martis and R. McConville, “Federated Mental Wellbeing Assessment Using Smartphone Sensors Under Unreliable Participation,” IEEE Ac-cess, 2025.

[5] S. Gedam and S. Paul, “A Review on Mental Stress Detection Using Wearable Sensors and Machine Learning Techniques,” IEEE Access, vol. 9, pp. 84045–84066, 2021.

[6] J. A. Francisco and P. S. Rodrigues, “Computer Vision Based on a Modular Neural Network for Automatic Assessment of Physical Therapy Rehabilitation Activities,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 31, pp. 2174–2183, 2023.

[7] V. Skaramagkas, I. Kyprakis, G. S. Karanasiou, D. I. Fotiadis, and M. Tsiknakis, “A Review on Deep Learning for Quality of Life Assessment Through the Use of Wearable Data,” IEEE Open Journal of Engineering in Medicine and Biology, vol. 6, pp. 261–268, 2025.

[8] T. B. Durmaz, J. L. Fuertes, and R. Imbert, “Influence of Gamification Elements on Explicit Motive Dispositions,” IEEE Access, vol. 10, pp. 118058–118071, 2022.

[9] Pew Research Center, “Teens and Smartphones: Key Findings,” Pew Research Center, Washington, D.C., 2024. [Online]. Available: https://www.pewresearch.org

[10] Centers for Disease Control and Prevention, “Screen Time and Health Outcomes in Adolescents,” CDC National Center for Health Statistics, Atlanta, GA, 2023.

[11] L. Braghieri, R. Levy, and A. Makarin, “Social Media and Mental Health,” American Economic Review, vol. 112, no. 11, pp. 3660–3693, 2022.

[12] J. Fogg, “A Behavior Model for Persuasive Design,” in Proc. 4th Int. Conf. Persuasive Technology (Persuasive), Claremont, CA, USA, 2009.

[13] K. Rahmani, R. Ren, and J. Sharifi, “Optimized Gamification for Digital Behavior Change Interventions: A Randomized Study,” Journal of Medical Internet Research, vol. 26, e51234, 2024.

[14] National Institutes of Health, “Digital Behavior Change Interventions and Habit Formation: A Systematic Review,” NIH National Library of Medicine, Bethesda, MD, 2024.

[15] I. A. Zualkernan et al., “Real-Time Biomechanical Squat and Exercise Posture Analysis Using ML Kit,” International Journal of Advanced Computer Science and Applications (IJACSA), vol. 14, no. 3, 2023.

[16] Google Developers, “ML Kit Pose Detection API,” Google LLC, Mountain View, CA, 2024. [Online]. Available: https://developers.google.com/ml-kit/vision/pose-detection

[17] L. Deci and R. M. Ryan, Intrinsic Motivation and Self-Determination in Human Behavior. New York, NY, USA: Plenum Press, 1985.

@article{1716250,
      author = {T R Chandrasagar, Richie Antony, Kiran K Kannan, Stewart Lalu, Asst. Prof. Adeena K D},
      title = {MindArc: On-Device AI for Digital Wellbeing and Habit Formation},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {10},
      pages = {1063-1072},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1716250.pdf},
      abstract = {Excessive smartphone usage degrades productivity and mental wellbeing, while existing digital wellbeing solutions provide limited enforcement and inadequate privacy safeguards. MindArc is an on-device digital wellbeing framework integrating real-time app restriction, usage analytics, activity-based unlocking, and gamified feedback. The system’s three-layer architecture leverages Android AccessibilityService for reliable foreground app interception, ML Kit Pose Detection for real-time exercise quantification, and Room-backed persistence for offline-first operation. A four-phase finite state machine with exponential moving average smoothing drives pushup and squat repetition counting. Reward mechanisms link verified physical and cognitive effort directly to screen-time grants, promoting sustained behavioral change. Experimental results validate reliable enforcement, accurate tracking, low latency, and minimal battery overhead, confirming effective digital self-regulation.},
      keywords = {Digital Wellbeing, Screen Time Management, Accessibility Service, Pose Detection, Gamification, Android, ML Kit, Behavior Change, Habit Formation},
      month = {April},
      doi = {https://doi.org/10.64388/IREV9I10-1716250}
  }