Gross Enrolment Ratio Prediction using Artificial Neural Network
Hussain. J1, Rosangliana. D2, Vanlalruata3
1Hussain. J*, Department of Mathematics and Computer Science, Mizoram University, Aizawl, India.
2Rosangliana. D, Department of Mathematics and Computer Science, Mizoram University, Aizawl, India.
3Vanlalruata, Department of Mathematics and Computer Science, Mizoram University, Aizawl, India.
Manuscript received on January 05, 2020. | Revised Manuscript received on January 25, 2020. | Manuscript published on January 30, 2020. | PP: 5006-5011 | Volume-8 Issue-5, January 2020. | Retrieval Number: E6873018520/2020©BEIESP | DOI: 10.35940/ijrte.E6873.018520
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The present paper deals with Gross Enrolment Ratio (GER) prediction in higher education within the state of Mizoram, India. The data used in this study are obtained from the yearly report of All India Survey on Higher Education (AISHE), published by Ministry of Human Resource Development (MHRD), Govt. of India and Statistical Handbook of various years published by Dept. of Economics & Statistics, Govt. of Mizoram. In this study, a soft computing technique known as Artificial Neural Network (ANN) is implemented for prediction of GER in higher education. The data obtained are analyzed and categorized into two classes known as the input and target data. The input data represent the years from 1968 to 2017. The target data represents the enrolment details corresponding to the input year such as, male enrolment, female enrolment, eligible population and GER. After generating these input data and target data, an ANN is used for building a model. The model has been trained and tested using 530260 student enrolment data for the period of 50 years. In order to obtain an accurate GER prediction, the accuracy of four architectures of ANN known as Back Propagation (BP), Radial Basis (RB), Recurrent Neural Network (RNN), and Feed Forward Neural Network (FFNN) are compared. The comparison is carried out by performing a prediction on the known data set. It is found that BP Neural Network with 50 hidden neurons and a learning rate of 0.1 gives the best prediction accuracy. Therefore, to predict the future GER, a BP neural network is implemented in this study. The main focus of this study is to analyze the pattern of enrolment and to predict future GER, as GER is a primary indicator for the status of higher education. The result obtained may help policymakers to take suitable decision to increase GER in higher education within the state of Mizoram so as to contribute to the govt. of India’s target of 30% by the year 2020.
Keywords: GER prediction; Neural Network; Back Propagation; Student Enrolment Prediction; Classification; Soft Computing; Forecasting.
Scope of the Article: Classification.