Using an Enhanced Feed-Forward BP Network for Predictive Model Building From Students’ Data

Ajiboye, Adeleke Raheem and Ruzaini, Abdullah Arshah and Qin, Hongwu (2015) Using an Enhanced Feed-Forward BP Network for Predictive Model Building From Students’ Data. Intelligent Automation and Soft Computing, 2015. pp. 1-7. ISSN 1079-8587. (Published)

[img] PDF
Using an Enhanced Feed Forward BP Network for Predictive Model Building from Students Data.pdf
Restricted to Repository staff only

Download (1MB) | Request a copy

Abstract

Feed-forward, Back Propagation (BP) Network is a network structure capable of modeling the class prediction as a nonlinear combination of the inputs. The network has proven its suitability in solving several complex tasks, most especially when trained with appropriate algorithms. This study presents an enhancement of this network with a view to boosting its prediction accuracy. The paper proposed a modification of the data partitioning function in the regular feed-forward network. A predictive model is constructed based on the proposed partition, while the second model is based on the partition of the existing network. Both models are trained and simulated with sets of untrained data. The mean absolute error is computed for both models and their error values are compared. Comparison of their results shows that the enhanced network consistently delivers higher accuracy and generalized better than the existing network in its regular structure; as there was a decrease in error from 0.261 to 0.016. The enhanced network has also shown its suitability in the fittings of models from students’ data for prediction purposes.

Item Type: Article
Uncontrolled Keywords: prediction; data partitioning; feed-forward network; back-propagation; data mining
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Z Bibliography. Library Science. Information Resources > Z665 Library Science. Information Science
Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4450 Databases
Faculty/Division: Faculty of Computer System And Software Engineering
Depositing User: PM. Dr. Ruzaini Abdullah Arshah
Date Deposited: 12 Apr 2016 08:34
Last Modified: 18 May 2018 01:32
URI: http://umpir.ump.edu.my/id/eprint/12850
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item