Employee Well-Being: Deep Learning Approaches to Stress Detection

Year : 2025 | Volume : 12 | Issue : 01 | Page : 52 58
    By

    Jigar Dave,

  • Khushbu Juneja,

  1. Assistant Professor, Faculty of Computer Application, Noble University, Bamangam, Junagadh, Gujarat, India
  2. Assistant Professor, Faculty of Computer Application, Noble University, Bamangam, Junagadh, Gujarat, India

Abstract

Stress has become a major concern for employee health, productivity, and overall well-being in today’s fast-paced work environment. It is a growing global issue, affecting both individual employees and the productivity of organizations. Work-related stress occurs when the demands of a job surpass an individual’s ability to manage, whether because of long hours, overwhelming responsibilities, or other pressures. Factors such as conflicts with coworkers or supervisors, constant changes, and job insecurity (e.g., potential layoffs) also contribute to stress. According to the National Health and Safety Commission, work-related stress is a leading cause of prolonged absenteeism. This research work introduces a proposed AI-driven system designed to monitor and manage workplace stress levels for employees. By utilizing advanced machine learning algorithms, this system offers real-time stress evaluations and customized strategies for managing stress. The study proposes a framework to detect and analyze emotional stress and anxiety through video-recorded facial expressions. To systematically induce fluctuations in emotional states (neutral, relaxed, and stressed/anxious), an experimental protocol was developed with various external and internal stimuli. The analysis focused overtime on involuntary and semi-voluntary facial expressions to objectively measure emotional responses. Key features examined include eye movements, mouth activity, head motion, and questionnaire responses, with some measured via camera-based photoplethysmography. A feature selection process identified the most reliable indicators, followed by a classification model to differentiate between neutral, stressed/anxious, and relaxed states. Self-reported ranking transformations were also incorporated. Additionally, this AI system provides managers with insights into overall team stress levels, enabling informed decisions to improve the workplace environment. Core elements of the framework include continuous monitoring, personalized feedback, and adaptability to individual stress triggers and responses. The AI’s learning capability ensures ongoing refinement, making its stress management strategies increasingly effective over time. By implementing this AI system, organizations can proactively address workplace stress, fostering employee well-being, enhancing productivity, and reducing absenteeism. This study discusses the framework’s design, underlying AI algorithms, data privacy considerations, and the potential impact on organizational culture and employee health.

Keywords: Employee well-being, stress management, workplace stress, DL, facial expression recognition

[This article belongs to Journal of Mobile Computing, Communications & Mobile Networks ]

How to cite this article:
Jigar Dave, Khushbu Juneja. Employee Well-Being: Deep Learning Approaches to Stress Detection. Journal of Mobile Computing, Communications & Mobile Networks. 2025; 12(01):52-58.
How to cite this URL:
Jigar Dave, Khushbu Juneja. Employee Well-Being: Deep Learning Approaches to Stress Detection. Journal of Mobile Computing, Communications & Mobile Networks. 2025; 12(01):52-58. Available from: https://journals.stmjournals.com/jomccmn/article=2025/view=195354


References

  1. Giannakakis G, Pediaditis M, Manousos D, Kazantzaki E, Chiarugi F, Simos PG, Marias K, Tsiknakis M. Stress and anxiety detection using facial cues from videos. Biomed Signal Process Control. 2017 Jan 1; 31: 89–101.
  2. Zhang H, Feng L, Li N, Jin Z, Cao L. Video-based stress detection through deep learning. Sensors. 2020 Sep 28; 20(19): 5552.
  3. Li R, Liu Z. Stress detection using deep neural networks. BMC Med Inform Decis Mak. 2020 Dec; 20(Suppl 11): 285.
  4. Segerstrom SC, Miller GE. Psychological stress and the human immune system: a meta-analytic study of 30 years of inquiry. Psychol Bull. 2004 Jul; 130(4): 601–630.
  5. Steptoe A, Kivimäki M. Stress and cardiovascular disease: an update on current knowledge. Annu Rev Public Health. 2013 Mar 18; 34(1): 337–54.
  6. Panicker SS, Gayathri P. A survey of machine learning techniques in physiology based mental stress detection systems. Biocybern Biomed Eng. 2019 Apr 1; 39(2): 444–69.
  7. Zhang J, Yin H, Zhang J, Yang G, Qin J, He L. Real-time mental stress detection using multimodality expressions with a deep learning framework. Front Neurosci. 2022 Aug 5; 16: 947168.
  8. Mishra V, Sen S, Chen G, Hao T, Rogers J, Chen CH, Kotz D. Evaluating the reproducibility of physiological stress detection models. Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies (IMWUT). 2020 Dec 17; 4(4): 1–29.
  9. Levine GN. Psychological stress and heart disease: fact or folklore? Am J Med. 2022 Jun 1; 135(6): 688–96.
  10. Zhang J, Mei X, Liu H, Yuan S, Qian T. Detecting negative emotional stress based on facial expression in real time. In 2019 IEEE 4th international conference on signal and image processing (ICSIP). 2019 Jul 19; 430–434.
  11. Harik Anisa. Scientific Review and Research System as per United Nations Perspectives and Charters. India: RCS Publication; 2015; 18–39.
Regular Issue Subscription Review Article
Volume 12
Issue 01
Received 20/12/2024
Accepted 06/01/2025
Published 24/01/2025
Publication Time 35 Days
406

Login


My IP

PlumX Metrics