Published Paper Details:

In recent years, the shift toward online work has increased significantly, especially after the COVID-19 pandemic. While working remotely provides flexibility, it has also led to higher stress levels due to continuous screen usage, workload pressure, and reduced social interaction. This paper presents a stress analysis and care prediction system designed for online workers. The system observes user behavior through facial expressions, typing patterns, and physiological signals to understand stress levels in real time. A combination of deep learning and machine learning techniques is used to improve the system's performance. The model is implemented using a Raspberry Pi setup, making it practical for real-world usage. Compared to traditional methods, this approach focuses on multiple inputs instead of relying on a single parameter, which helps in achieving better accuracy. The system also provides feedback to users so they can take necessary actions to manage their stress. Overall, this work aims to provide a simple and effective solution to support the well-being of people working in digital environments.