GEML: A Grammatical Evolution, Machine Learning Approach to Multi-class Classification

Fitzgerald, Jeannie and Azad, R. Muhammad Atif and Ryan, Conor (2016) GEML: A Grammatical Evolution, Machine Learning Approach to Multi-class Classification. In: Computational Intelligence. IJCCI 2015. Studies in Computational Intelligence, 669 . Springer, pp. 113-134. ISBN 978-3-319-48504-1

Preview

Text OA GEML-A-Grammatical.pdf - Published Version Download (480kB)

Abstract

In this paper, we propose a hybrid approach to solving multi-class problems which combines evolutionary computation with elements of traditional machine learning. The method, Grammatical Evolution Machine Learning (GEML) adapts machine learning concepts from decision tree learning and clustering methods and integrates these into a Grammatical Evolution framework. We investigate the effectiveness of GEML on several supervised, semi-supervised and unsupervised multi-class problems and demonstrate its competitive performance when compared with several well known machine learning algorithms. The GEML framework evolves human readable solutions which provide an explanation of the logic behind its classification decisions, offering a significant advantage over existing paradigms for unsupervised and semi-supervised learning. In addition we also examine the possibility of improving the performance of the algorithm through the application of several ensemble techniques.

Item Type:	Book Section
Identification Number:	10.1007/978-3-319-48506-5_7
Dates:	Date Event 2016 Published
Uncontrolled Keywords:	Multi-class classification; Grammatical evolution; Evolutionary computation; Machine learning
Subjects:	CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science
Divisions:	Faculty of Computing, Engineering and the Built Environment Faculty of Computing, Engineering and the Built Environment > College of Computing
Depositing User:	Ian Mcdonald
Date Deposited:	16 Mar 2017 12:32
Last Modified:	22 Mar 2023 12:01
URI:	https://www.open-access.bcu.ac.uk/id/eprint/4068

Actions (login required)

View Item