Autosoft Journal

Online Manuscript Access


Using an Enhanced Feed-Forward BP Network for Predictive Model Building from Students2019 Data


Authors



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 students2019 data for prediction purposes.


Keywords


Pages

Total Pages: 7
Pages: 169-175

DOI
10.1080/10798587.2015.1079364


Manuscript ViewPdf Subscription required to access this document

Obtain access this manuscript in one of the following ways


Already subscribed?

Need information on obtaining a subscription? Personal and institutional subscriptions are available.

Already an author? Have access via email address?


Published

Volume: 22
Issue: 2
Year: 2015

Cite this document


References

Ampazis, N., and S.J. Perantonis. "Two Highly Efficient Second-Order Algorithms for Training Feedforward Networks." IEEE Transactions on Neural Networks 13.5 (2002): 1064-1074. Crossref. Web. https://doi.org/10.1109/TNN.2002.1031939

Andina D. Intelligent Automation & Soft Computing

Baylari, Ahmad, and Gh.A. Montazer. "Design a Personalized e-Learning System Based on Item Response Theory and Artificial Neural Network Approach." Expert Systems with Applications 36.4 (2009): 8013-8021. Crossref. Web. https://doi.org/10.1016/j.eswa.2008.10.080

Beale M. H. Neural Network Toolbox User’s Guide

Chauhan, Nikunj, V. Ravi, and D. Karthik Chandra. "Differential Evolution Trained Wavelet Neural Networks: Application to Bankruptcy Prediction in Banks." Expert Systems with Applications 36.4 (2009): 7659-7665. Crossref. Web. https://doi.org/10.1016/j.eswa.2008.09.019

Cohn D. Machine learning

https://doi.org/10.3906/elk-1202-89

Han, Fei, Hai-Fen Yao, and Qing-Hua Ling. "An Improved Extreme Learning Machine Based on Particle Swarm Optimization." Lecture Notes in Computer Science (2012): 699-704. Crossref. Web. https://doi.org/10.1007/978-3-642-24553-4_92

Han J. Data mining concepts and techniques

Hinton, Geoffrey et al. "Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups." IEEE Signal Processing Magazine 29.6 (2012): 82-97. Crossref. Web. https://doi.org/10.1109/MSP.2012.2205597

Issanchou, Sébastien, and Jean-Pierre Gauchi. "Computer-Aided Optimal Designs for Improving Neural Network Generalization." Neural Networks 21.7 (2008): 945-950. Crossref. Web. https://doi.org/10.1016/j.neunet.2008.05.012

Kantardzic, Mehmed. "Data Mining." (2011): n. pag. Crossref. Web. https://doi.org/10.1002/9781118029145

Tin-Yau Kwok, and Dit-Yan Yeung. "Constructive Algorithms for Structure Learning in Feedforward Neural Networks for Regression Problems." IEEE Transactions on Neural Networks 8.3 (1997): 630-645. Crossref. Web. https://doi.org/10.1109/72.572102

Lye, Chun-Teck et al. "Predicting Pre-University Student”s Mathematics Achievement." Procedia - Social and Behavioral Sciences 8 (2010): 299-306. Crossref. Web. https://doi.org/10.1016/j.sbspro.2010.12.041

Narayan, S., G.A. Tagliarini, and E.W. Page. "Enhancing MLP Networks Using a Distributed Data Representation." IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics) 26.1 (1996): 143-149. Crossref. Web. https://doi.org/10.1109/3477.484446

Negnevitsky M. Artificial intelligence a guide to intelligent systems

Quah, Jon T.S., and M. Sriganesh. "Real-Time Credit Card Fraud Detection Using Computational Intelligence." Expert Systems with Applications 35.4 (2008): 1721-1732. Crossref. Web. https://doi.org/10.1016/j.eswa.2007.08.093

Rumelhart D. E. Cognitive modeling

Simard, D., L. Nadeau, and H. Kröger. "Fastest Learning in Small-World Neural Networks." Physics Letters A 336.1 (2005): 8-15. Crossref. Web. https://doi.org/10.1016/j.physleta.2004.12.078

Stanley, Kenneth O., and Risto Miikkulainen. "Evolving Neural Networks through Augmenting Topologies." Evolutionary Computation 10.2 (2002): 99-127. Crossref. Web. https://doi.org/10.1162/106365602320169811

Temurtas, Hasan, Nejat Yumusak, and Feyzullah Temurtas. "A Comparative Study on Diabetes Disease Diagnosis Using Neural Networks." Expert Systems with Applications 36.4 (2009): 8610-8615. Crossref. Web. https://doi.org/10.1016/j.eswa.2008.10.032

Thammasiri, Dech et al. "A Critical Assessment of Imbalanced Class Distribution Problem: The Case of Predicting Freshmen Student Attrition." Expert Systems with Applications 41.2 (2014): 321-330. Crossref. Web. https://doi.org/10.1016/j.eswa.2013.07.046

Thiele, Tamara et al. "Predicting Students” Academic Performance Based on School and Socio-Demographic Characteristics." Studies in Higher Education 41.8 (2014): 1424-1446. Crossref. Web. https://doi.org/10.1080/03075079.2014.974528

Witten I. H. Data mining practical machine learning tools and techniques

Yam, J.Y.F., and T.W.S. Chow. "Feedforward Networks Training Speed Enhancement by Optimal Initialization of the Synaptic Coefficients." IEEE Transactions on Neural Networks 12.2 (2001): 430-434. Crossref. Web. https://doi.org/10.1109/72.914538

Yu H. The Industrial Electronics Handbook

Zhang, Chunlin, Ju Jiang, and Mohamed Kamel. "Intrusion Detection Using Hierarchical Neural Networks." Pattern Recognition Letters 26.6 (2005): 779-791. Crossref. Web. https://doi.org/10.1016/j.patrec.2004.09.045

JOURNAL INFORMATION


ISSN PRINT: 1079-8587
ISSN ONLINE: 2326-005X
DOI PREFIX: 10.31209
10.1080/10798587 with T&F
IMPACT FACTOR: 0.652 (2017/2018)
Journal: 1995-Present




CONTACT INFORMATION


TSI Press
18015 Bullis Hill
San Antonio, TX 78258 USA
PH: 210 479 1022
FAX: 210 479 1048
EMAIL: tsiepress@gmail.com
WEB: http://www.wacong.org/tsi/