Forecasting Number of Students Applicant for Courses by Artificial Neural Networks


Jafar Pouramini - Department of Computer Engineering and Information Technology, Payame Noor University(PNU), Iran.


Forecasting the number of students who are going to take a special course in next semester in Computer Engineering field at Payam Noor University is the subject. To do this, many neural network structures have been tested with MATLAB software by existing data and were compared to real data, networks like feedforward backpropagation 3 and 4-layared, RBF network, etc. To achieve a network with optimum structure, various parameters and criteria like MAE, MSE and MSEREG, have been examined. At last, a 3-layered feedback neural network in the form of 20-n-1 was chosen for this problem. Comparing experiential results with real data, it is shown that the obtained model can effectively forecast enrolments of students. So it can be used for forecasting tasks especially when a forecast with high accuracy is needed.