Prediksi Lama Studi Mahasiswa Menggunakan Jaringan Syaraf Tiruan Metode Backpropagation

Abstract

In improving the quality of a university, the role of students is very important, where students are expected to graduate on the right time. Of course, this condition is facilitated by the existence of a system for predicting the length of students study. This system is needed by students to find out whether students graduated on time or not. This system is implemented with length of Matlab 2016a software, by using the Backpropagation Method. This system predicts length of students study time based on input variables that have been provided. Then system processes with the Backpropagation Method and displays results, such as in the form of graduating on time or late. A total of 110 data of Electrical Engineering Department, Faculty of Engineering, University of Riau Academic Year 2010 to 2014 are used in this study, consisting of 77 training data and 33 test data. The final result of this study is that the system can be used to predict the length of study of time students with a research level of 93%.
Keywords : backpropagation