Effect of Using Neural Networks in GA-Based School Timetabling

Abstract:- The school timetabling problem is a specific kind of timetabling problems. It is characterized by similar sets of subjects used among schools in different years, and by great extent of human factor involved. This particularity lets us to hope existing timetables to be useful information for actual timetabling process, and neural networks to be a suitable technique to assist it. This paper describes experiments on using neural networks as part of the fitness function of a GA-based school timetabling system, the model of what has been proposed by the author earlier. The experimental results show ability of neural networks to be applied for timetable evaluation, as well as reveal various side effects of using neural networks within GA-based school timetabling