Frontend + API + Models based on genetic algorithms to solve timetabling problems
Technological advancements have significantly impacted various sectors, including education, where optimizing resources is crucial. Timetabling, the process of scheduling classes, exams, and events in educational settings, presents as a wildly recognized challenge (even with it's own competitions to solve this problem) due to the need to satisfy multiple constraints and preferences. Therefore, effective timetabling is vital as it influences the daily operations of educational institutions and the experiences of students and teachers. This project explores the effectiveness of different timetabling algorithms—genetic algorithms, local search algorithms, and randomized approaches—in optimizing school schedules. Through comparative analysis and with interactive visualization, the study examines how these algorithms can enhance resource utilization, reduce idle periods, and meet the preferences of students and teachers. AI-driven timetabling aligns with contemporary educational policies, promoting strategic time management and potentially improving educational outcomes and stakeholder satisfaction.
- Make
- Docker
make service-init
make api-init
make frontend-init