Using an Enhanced Feed-Forward BP Network for Predictive Model Building From Students’ Data
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 presen...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis
2015
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/12850/ http://umpir.ump.edu.my/id/eprint/12850/ http://umpir.ump.edu.my/id/eprint/12850/ http://umpir.ump.edu.my/id/eprint/12850/1/Using%20an%20Enhanced%20Feed%20Forward%20BP%20Network%20for%20Predictive%20Model%20Building%20from%20Students%20Data.pdf |
| id |
ump-12850 |
|---|---|
| recordtype |
eprints |
| spelling |
ump-128502018-05-18T01:32:11Z http://umpir.ump.edu.my/id/eprint/12850/ Using an Enhanced Feed-Forward BP Network for Predictive Model Building From Students’ Data Ajiboye, Adeleke Raheem Ruzaini, Abdullah Arshah Qin, Hongwu QA75 Electronic computers. Computer science Z665 Library Science. Information Science ZA4450 Databases 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. Taylor & Francis 2015-11 Article PeerReviewed application/pdf en http://umpir.ump.edu.my/id/eprint/12850/1/Using%20an%20Enhanced%20Feed%20Forward%20BP%20Network%20for%20Predictive%20Model%20Building%20from%20Students%20Data.pdf 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 http://dx.doi.org/10.1080/10798587.2015.1079364 DOI: 0.1080/10798587.2015.1079364 |
| repository_type |
Digital Repository |
| institution_category |
Local University |
| institution |
Universiti Malaysia Pahang |
| building |
UMP Institutional Repository |
| collection |
Online Access |
| language |
English |
| topic |
QA75 Electronic computers. Computer science Z665 Library Science. Information Science ZA4450 Databases |
| spellingShingle |
QA75 Electronic computers. Computer science Z665 Library Science. Information Science ZA4450 Databases Ajiboye, Adeleke Raheem Ruzaini, Abdullah Arshah Qin, Hongwu Using an Enhanced Feed-Forward BP Network for Predictive Model Building From Students’ Data |
| description |
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. |
| format |
Article |
| author |
Ajiboye, Adeleke Raheem Ruzaini, Abdullah Arshah Qin, Hongwu |
| author_facet |
Ajiboye, Adeleke Raheem Ruzaini, Abdullah Arshah Qin, Hongwu |
| author_sort |
Ajiboye, Adeleke Raheem |
| title |
Using an Enhanced Feed-Forward BP Network for Predictive Model Building From Students’ Data |
| title_short |
Using an Enhanced Feed-Forward BP Network for Predictive Model Building From Students’ Data |
| title_full |
Using an Enhanced Feed-Forward BP Network for Predictive Model Building From Students’ Data |
| title_fullStr |
Using an Enhanced Feed-Forward BP Network for Predictive Model Building From Students’ Data |
| title_full_unstemmed |
Using an Enhanced Feed-Forward BP Network for Predictive Model Building From Students’ Data |
| title_sort |
using an enhanced feed-forward bp network for predictive model building from students’ data |
| publisher |
Taylor & Francis |
| publishDate |
2015 |
| url |
http://umpir.ump.edu.my/id/eprint/12850/ http://umpir.ump.edu.my/id/eprint/12850/ http://umpir.ump.edu.my/id/eprint/12850/ http://umpir.ump.edu.my/id/eprint/12850/1/Using%20an%20Enhanced%20Feed%20Forward%20BP%20Network%20for%20Predictive%20Model%20Building%20from%20Students%20Data.pdf |
| first_indexed |
2023-09-18T22:14:49Z |
| last_indexed |
2023-09-18T22:14:49Z |
| _version_ |
1777415266662088704 |