AI-Based Employee Healthcare and Well-Being Monitoring System with Personalized Break Recommendations

15 Sep

Authors: Assistant Professor R.Baby, S.Subashini, T.Kalpana, S.Jothipriyan, K.A.Athila, R.Arul Stenin

Abstract: Sitting for long periods without moving at computer workstations is now a common part of office jobs, and it is closely linked to higher stress, tiredness, muscle and bone problems, and increased risks for heart and metabolic health over time. Traditional workplace wellness programs often respond only after problems arise, are the same for everyone, and don't consider how each employee actually works day to day, which makes them less effective. This paper introduces an AI-powered system that monitors employees' health and well-being by tracking how they use their work systems, like how long they stay active, when they take breaks, and how they interact with tools. It also includes optional data from wearable devices and information employees share about how they feel, to help identify signs of tiredness and stress. The system uses these signs to create custom pop-up messages on the employee's screen. These messages remind them to do easy health activities, like standing and stretching after sitting for a certain amount of time, or drinking water at set times for staying hydrated. A system that combines simple rules with machine learning adjusts when and how long breaks are given based on each worker's usual habits, instead of using the same schedule for everyone. A feedback loop lets the system learn from suggestions that are accepted, skipped, or rejected, helping it decrease alert fatigue over time and make the alerts more relevant. The early check of the design shows that this system can help cut down on long periods of sitting, promote better drinking habits, and make people feel more positive, all without affecting how much work they can get done. The paper also talks about the system design, the method used in the algorithm, how it is better than current solutions, and what could be done next, like keeping data private while processing it on the device and making better use of wearable devices.

DOI: https://doi.org/10.5281/zenodo.22768926