Complex predictive models obtain very high predictive performance; however, it is difficult to explain their complex mathematical design. Rule extraction techniques help to understand their designs by generating structures like decision list. BruteDL algorithm generates decision list from a dataset, and also addresses the overlapping rule problem of most decision list learners. However; it does not harness the power of complex predictive model. It also performs poorly with small dataset. Hence, this work aimed to create rule extraction technique by extending BruteDL and to address its poor performance with small dataset. A rule extraction technique named BruteDL-RET (Brute Decision List-Rule Extraction Technique) was modeled and implemented. A finite state automaton was used to model the technique. A functionality to generate supporting training set was included. Artificial Neural Networks (ANN) is chosen as the complex predictive model which serves as the oracle because it decides the class of each example. Decision list was generated using both the predictive model and the dataset it was trained with. The implementation was done using Java programming language. We prove that on the average BruteDL-RET is able to generate more accurate rules than BruteDL. We report on the performance of our model using dataset of UCI repository.
| Published in | American Journal of Applied Mathematics (Volume 4, Issue 6) |
| DOI | 10.11648/j.ajam.20160406.20 |
| Page(s) | 330-339 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2017. Published by Science Publishing Group |
Predictive Models, Rule Extraction Techniques, Dataset, Artificial Neural Networks, Oracle
| [1] | Martens D., Huysmans J., Setiono R., Vanthienen J. and Baesens B. (2008). Rule Extraction from Support Vector Machines: An Overview of Issues and Application in credit scoring. Studies in Computational Intelligence (SCI) 80, 33–63 (2008) |
| [2] | Rikard, K. (2009). Predictive techniques and methods for decision support in situations with poor data quality. University of Boras, School of Business and Informatics, University of Skovde, informatics Research Center, University of Orebro, School of Science and Technology. Örebro University, 2009., 112 p. |
| [3] | Breton R., Paradis, S. and Roy, J. (2002). Command Decision Support Interface (CODSI) for human factors and display concept validation, International Conference on Information Fusion pp. 1284–1291. |
| [4] | Arnott, D., Graham, P., Peter, o’Donnell and Gemma, D. (2004). An analysis of decision support systems research: Preliminary Results. Decision Support in an Uncertain and Complex World: The IFIP TC8/WG8.3 International conference. |
| [5] | Craven M. (1996). Extracting comprehensible models from trained neural networks. University of Wisconsin-Madison. Published by University of Wisconsin-Madison Department of Computer Sciences |
| [6] | William, A. Young II, Gary, R. W., Maimuna, H. R. and Harry, S. W. II (2011). An investigation of TREPAN utilizing a continuous oracle model, Int. J. Data Analysis Techniques and Strategies, Vol. 3, No. 4. |
| [7] | Johan, H., Bart, B. and Jan, V. (2006). Using Rule Extraction to Improve the Comprehensibility of Predictive Models, Katholieke Universiteit Leuven Department of Decision Sciences and Information Management. |
| [8] | Quinlan J. R. (1986). Simplifying Decision Trees. Massachusetts Institute of Technology, Artificial Intelligence Laboratory. |
| [9] | RC Chakraborty (2010). Artificial Intelligence–Introduction. http://www.myreaders.info/html/artificial_intelligence.html, received in 2014 |
| [10] | Russell, S. and Norvig, P. (2003). Artificial Intelligence, A modern approach. Pearson Education, Inc., Upper Saddle River; New Jersey. |
| [11] | Kevin, P. M. (2012). Machine Learning–A Probabilistic Perspective. Published by MIT Press, Cambridge, Massachusetts, London, England. |
| [12] | Mohammed, J. Z. and Wagner, M. Jr. (2014). Data Mining and Analysis, Fundamental Concepts and Algorithms. Published by Cambridge University Press 2014. |
| [13] | Peter Clark and Tim Niblett (1989): The CN2 Induction Algorithm. italicThe Turing Institute, 36 North Hanover Street, Glasgow, G1 2AD, U. K. Machine Learning 3: 261-283. |
| [14] | Segal, R. and Etzioni, O. (1994). Learning Decision Lists Using Homogeneous Rules. Department of Computer Science and Engineering, University of Washington. |
| [15] | Prem Nath, https://premnath321.com/author/premnath321/, downloaded in October, 2015 |
| [16] | Christos S. and Dimitrios S., http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/report.html#An Example to illustrate the above teaching procedure), downloaded in October, 2015. |
APA Style
Bolanle F. Oladejo, Rukayat Ayomide Erinfolami. (2017). Modelling of an Extended Brutedl Algorithm for Rule Extraction. American Journal of Applied Mathematics, 4(6), 330-339. https://doi.org/10.11648/j.ajam.20160406.20
ACS Style
Bolanle F. Oladejo; Rukayat Ayomide Erinfolami. Modelling of an Extended Brutedl Algorithm for Rule Extraction. Am. J. Appl. Math. 2017, 4(6), 330-339. doi: 10.11648/j.ajam.20160406.20
AMA Style
Bolanle F. Oladejo, Rukayat Ayomide Erinfolami. Modelling of an Extended Brutedl Algorithm for Rule Extraction. Am J Appl Math. 2017;4(6):330-339. doi: 10.11648/j.ajam.20160406.20
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ajam.20160406.20,
author = {Bolanle F. Oladejo and Rukayat Ayomide Erinfolami},
title = {Modelling of an Extended Brutedl Algorithm for Rule Extraction},
journal = {American Journal of Applied Mathematics},
volume = {4},
number = {6},
pages = {330-339},
doi = {10.11648/j.ajam.20160406.20},
url = {https://doi.org/10.11648/j.ajam.20160406.20},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajam.20160406.20},
abstract = {Complex predictive models obtain very high predictive performance; however, it is difficult to explain their complex mathematical design. Rule extraction techniques help to understand their designs by generating structures like decision list. BruteDL algorithm generates decision list from a dataset, and also addresses the overlapping rule problem of most decision list learners. However; it does not harness the power of complex predictive model. It also performs poorly with small dataset. Hence, this work aimed to create rule extraction technique by extending BruteDL and to address its poor performance with small dataset. A rule extraction technique named BruteDL-RET (Brute Decision List-Rule Extraction Technique) was modeled and implemented. A finite state automaton was used to model the technique. A functionality to generate supporting training set was included. Artificial Neural Networks (ANN) is chosen as the complex predictive model which serves as the oracle because it decides the class of each example. Decision list was generated using both the predictive model and the dataset it was trained with. The implementation was done using Java programming language. We prove that on the average BruteDL-RET is able to generate more accurate rules than BruteDL. We report on the performance of our model using dataset of UCI repository.},
year = {2017}
}
TY - JOUR T1 - Modelling of an Extended Brutedl Algorithm for Rule Extraction AU - Bolanle F. Oladejo AU - Rukayat Ayomide Erinfolami Y1 - 2017/01/16 PY - 2017 N1 - https://doi.org/10.11648/j.ajam.20160406.20 DO - 10.11648/j.ajam.20160406.20 T2 - American Journal of Applied Mathematics JF - American Journal of Applied Mathematics JO - American Journal of Applied Mathematics SP - 330 EP - 339 PB - Science Publishing Group SN - 2330-006X UR - https://doi.org/10.11648/j.ajam.20160406.20 AB - Complex predictive models obtain very high predictive performance; however, it is difficult to explain their complex mathematical design. Rule extraction techniques help to understand their designs by generating structures like decision list. BruteDL algorithm generates decision list from a dataset, and also addresses the overlapping rule problem of most decision list learners. However; it does not harness the power of complex predictive model. It also performs poorly with small dataset. Hence, this work aimed to create rule extraction technique by extending BruteDL and to address its poor performance with small dataset. A rule extraction technique named BruteDL-RET (Brute Decision List-Rule Extraction Technique) was modeled and implemented. A finite state automaton was used to model the technique. A functionality to generate supporting training set was included. Artificial Neural Networks (ANN) is chosen as the complex predictive model which serves as the oracle because it decides the class of each example. Decision list was generated using both the predictive model and the dataset it was trained with. The implementation was done using Java programming language. We prove that on the average BruteDL-RET is able to generate more accurate rules than BruteDL. We report on the performance of our model using dataset of UCI repository. VL - 4 IS - 6 ER -
Email: