Sohaib Latif1*, Fang Xianwen1 and Li-Li Wang2
1Anhui University of Science and Technology, Huainan, China
2The Key Laboratory of Embedded System and Service Computing Ministry of
Education (Tongji University), Shanghai, China
*Corresponding Author: Sohaib Latif, Anhui University of Science and Technology, Huainan, China.
Received: June 15, 2020; Published: June 30, 2020
The unknown factors always prevail in developing countries like Pakistan, due to these factors the annual education performance could not show the expected results. The proper implementation of advanced machine learning tools can help to highlight the cause of low performance in the education field. The study aims to address this issue by proposing a new 3-level classifier model for decision support that can identify the reasons for failure by training the neural network which provides reliable results. For experiment purpose, a dataset of 1011 respondents of graduate-level students of "English" and "Physics", used to analyze where the C4.5 algorithm provides maximum accuracy of 83.2%, 88.8%, 83.1% and 89.8%. The study also presents a prototype of the javabased software to implement the proposed model of a 3-level classifier. The Java-based software uses the Waikato Environment for Knowledge Analysis (WEKA) machine learning toolkits with Java Virtual Machine (JVM) to produce reliable results. The enhanced and fully featured java-based software would provide 88.8% accuracy in the decision support system to identify the gray areas of the education sector of Pakistan.
Keywords: Neural Network; Real-World Data Mining; Decision Tree; Education System of Pakistan
Citation: Sohaib Latif., et al. “Implementation of the Machine Learning Tools on Improving the Decision Support System for Pakistan’s Education”. Acta Scientific Computer Sciences 2.7 (2020): 09-14.
Copyright: © 2020 Sohaib Latif., et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.