Automatic Timetable Generation using Neural Networks Trained by Genetic Algorithms

Scheduling is a crucial task in various real-life situations, including educational institutions where creating a feasible timetable is a complex challenge due to numerous constraints. The educational timetable scheduling problem is NP-hard, making it a difficult problem to solve optimally within reasonable time frames. Traditional methods like Genetic Algorithms (GAs) and Evolutionary Algorithms (EAs) have been applied to this problem with varying degrees of success. In this paper, we introduce a novel approach for automatic timetable generation using neural networks trained by genetic algorithms. Our method leverages the strengths of neural networks in pattern recognition and GAs in optimization to effectively handle the constraints and complexities of timetable scheduling. Experimental results demonstrate a significant improvement in scheduling accuracy and computational efficiency. We compare the performance of our proposed method with traditional GAs and demonstrate that the neural network approach trained by GAs achieves superior results in terms of speed and solution quality. This research paves the way for more efficient and intelligent scheduling systems in educational environments.