• Arpita Kadam
• Farhan Ahmad
• Prof. Poonam Lad
• Asmit Deshmukh
• Sarthak More

The productivity of any workplace and the success of an organization are affected by an employee’s mental health and stress. This project showcases MindTrack, an AI solution that combines facial recognition, emotion recognition, and sentiment analysis to monitor employees in real time. The employee’s webcam is used for facial recognition during attendance, and at the same time, a convolutional neural network (CNN) based ResNet-50 model and Deepface was applied to classify facial expressions such as happiness, sadness, anger, and tiredness for automated attendance solutions. To get more accurate stress detection, the system also analyzes employee feedback using sentiment analysis and behavioral indicators like typing speed and self-mood ratings. If MindTrack detects a continuous nega- tive feeling of employees, then a wellness intervention system is activated, which offers suggestions such as motivational videos, short breaks, and company training, etc. This method turns old attendance systems into dynamic employee support platforms, allowing companies to identify stress early, enhance well-being, and build a healthier work environment. Index Terms—stress detection, facial recognition, emotion de- tection, sentiment analysis, behavioral analysis, employee well- being, real-time monitoring

stress detection, facial recognition, emotion detection, sentiment analysis, behavioral analysis, employee well- being, real-time monitoring

"MindTrack: A Multimodal AI System for Proactive Employee Stress Detection and Well-being Support", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 3, page no.f121-f127, March-2026, Available :http://www.jetir.org/papers/JETIR2603516.pdf

"MindTrack: A Multimodal AI System for Proactive Employee Stress Detection and Well-being Support", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 3, page no. ppf121-f127, March-2026, Available at : http://www.jetir.org/papers/JETIR2603516.pdf