STRESS MANAGEMENT BASED WORK SCHEDULER

Authors:

Mrs. D. Gayatri¹, P. Reshma², K. Keerthi³, S. Siddharth⁴, D. Nagendra⁵

^1,2,3,4,5MVGR College of Engineering, Vizianagaram, India

Abstract— Educational institutions struggle to create efficient timetables. They need to balance academic requirements, faculty availability, and limited resources. Traditional scheduling methods are slow and prone to mistakes. This often results in class overlaps, uneven workloads, faculty burnout, and wasted resources. To solve these problems, this project suggests a smart timetable generation system that automates scheduling. It also focuses on making sure resources are used well and faculty are cared for. The system uses a modified Genetic Algorithm designed for academic scheduling. It takes into account semester-specific time slots and smart lab placements through complete slot blocking to keep continuity. A simplified penalty-based fitness function optimizes schedules while reducing conflicts and workload imbalances. Besides generating timetables, the system has a rule-based stress management module. This module monitors faculty workloads and spots potential stress issues. It offers proactive suggestions through a chat interface, which helps balance schedules and boosts faculty productivity. Additionally, the solution features a Power BI- based analytics dashboard. It provides real-time insights into how well the timetable works, how faculty workload is distributed, and how resources are used through interactive visuals like heat maps. Overall, the proposed system improves scheduling efficiency, cuts down on administrative work, supports faculty well-being, and fosters data- driven decisions in educational institutions.

KEYWORDS— Personality Prediction, Machine Learning Models, Big Five Model (OCEAN), Term Frequency Inverse Document Frequency (TF-IDF), Natural Language Processing (NLP).