Constrained dynamic rule induction learning |
| |
| Affiliation: | 1. Applied Business and Computing, NMIT, Auckland;2. Center of Computational Intelligence, School of Computer Science and Informatics, De Montfort University, Leicester, UK;1. Department of Computer Science, Faculty of Computing, Universiti Teknologi Malaysia, 81310 Skudai, Johor, Malaysia;2. School of Leadership, Management and Information Systems, University of Technology Sydney, Australia;1. Federal Institute of Rio Grande do Norte - IFRN, Campus EaD, Av. Senador Salgado Filho 1559, Tirol, CEP: 59015-000, Natal, RN, Brazil;2. IFRN - Campus Natal Zona Norte, Rua Brusque 2926, Potengi, CEP 59112-490, Natal, RN, Brazil;3. Federal University of Rio Grande do Norte - UFRN, Department of Computer Engineering and Automation - DCA, Campus Universitrio, Lagoa Nova, CEP: 59078-900, Natal, RN, Brazil;4. Lancaster University, Data Science Group, School of Computing and Communications, Lancaster LA1 4WA, United Kingdom;5. Chair of Excellence, Carlos III University, Madrid, Spain;1. Departamento de Engenharia de Teleinformática, Universidade Federal do Ceará, Campus do Pici s/n, Bloco 725, 60455-970, Fortaleza, CE, Brazil;2. Curso de Tecnologia em Manutenção Industrial, Instituto Federal de Educação, Ciência e Tecnologia do Ceará, Av. Parque Central s/n, Distrito Industrial I, 61939-140, Maracanaú, CE, Brazil;3. Curso de Engenharia da Computação, Universidade Federal do Ceará, Campus de Sobral, Bloco I - Engenharias, Rua Estanislau Frota s/n, Mucambinho, 62010-560, Sobral, CE, Brazil;4. Curso de Engenharia Elétrica, Universidade Federal do Ceará, Campus de Sobral, Bloco I - Engenharias, Rua Estanislau Frota s/n, Mucambinho, 62010-560, Sobral, CE, Brazil;1. Department of Electronics & Communication Engineering, National Institute of Technology Patna, Bihar, (800005), India;2. PDPM Indian Institute of Information Technology Design and Manufacturing Jabalpur 482011, MP (India);3. Department of Electrical Engineering, Indian Institute Technology Roorkee, Uttrakhand 247667, India;1. Discipline of Electrical Engineering, Indian Institute of Technology Indore, Indore, 453552, India;2. Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore 599489, Singapore |
| |
| Abstract: | One of the known classification approaches in data mining is rule induction (RI). RI algorithms such as PRISM usually produce If-Then classifiers, which have a comparable predictive performance to other traditional classification approaches such as decision trees and associative classification. Hence, these classifiers are favourable for carrying out decisions by users and therefore they can be utilised as decision making tools. Nevertheless, RI methods, including PRISM and its successors, suffer from a number of drawbacks primarily the large number of rules derived. This can be a burden especially when the input data is largely dimensional. Therefore, pruning unnecessary rules becomes essential for the success of this type of classifiers. This article proposes a new RI algorithm that reduces the search space for candidate rules by early pruning any irrelevant items during the process of building the classifier. Whenever a rule is generated, our algorithm updates the candidate items frequency to reflect the discarded data examples associated with the rules derived. This makes items frequency dynamic rather static and ensures that irrelevant rules are deleted in preliminary stages when they don't hold enough data representation. The major benefit will be a concise set of decision making rules that are easy to understand and controlled by the decision maker. The proposed algorithm has been implemented in WEKA (Waikato Environment for Knowledge Analysis) environment and hence it can now be utilised by different types of users such as managers, researchers, students and others. Experimental results using real data from the security domain as well as sixteen classification datasets from University of California Irvine (UCI) repository reveal that the proposed algorithm is competitive in regards to classification accuracy when compared to known RI algorithms. Moreover, the classifiers produced by our algorithm are smaller in size which increase their possible use in practical applications. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
