Article: A differential evolution algorithm to optimise the combination of classifier and cluster ensembles Journal: International Journal of Bio-Inspired Computation (IJBIC) 2015 Vol.7 No.2 pp.111 - 124 Abstract: Unsupervised models can provide supplementary soft constraints to help classify new data since similar instances are more likely to share the same class label. In this context, this paper reports on a study on how to make an existing algorithm, named C³E (from consensus between classification and clustering ensembles), more convenient by automatically tuning its main parameters. The C³E algorithm is based on a general optimisation framework that takes as input class membership estimates from existing classifiers, and a similarity matrix from a cluster ensemble operating solely on the new (target) data to be classified, in order to yield a consensus labelling of the new data. To do so, two parameters have to be defined a priori by the user: the relative importance of classifier and cluster ensembles, and the number of iterations of the algorithm. We propose a differential evolution (DE) algorithm, named dynamic DE (D²E), which is a computationally efficient alternative for optimising such parameters. D²E provides better results than DE by dynamically updating its control parameters. Moreover, competitive results were achieved when comparing D²E with three state-of-the-art algorithms. Inderscience Publishers - linking academia, business and industry through research

Title: A differential evolution algorithm to optimise the combination of classifier and cluster ensembles

Authors: Luiz F.S. Coletta; Eduardo Raul Hruschka; Ayan Acharya; Joydeep Ghosh

Addresses: Department of Computer Science, University of Sao Paulo (USP), 400 Trabalhador Sao-carlense ave, 13560-970 Sao Carlos, SP, Brazil ' Department of Computer Science, University of Sao Paulo (USP), 400 Trabalhador Sao-carlense ave, 13560-970 Sao Carlos, SP, Brazil ' Department of Electrical and Computer Engineering, University of Texas (UT), Austin, TX 78712, USA ' Department of Electrical and Computer Engineering, University of Texas (UT), Austin, TX 78712, USA

Abstract: Unsupervised models can provide supplementary soft constraints to help classify new data since similar instances are more likely to share the same class label. In this context, this paper reports on a study on how to make an existing algorithm, named C³E (from consensus between classification and clustering ensembles), more convenient by automatically tuning its main parameters. The C³E algorithm is based on a general optimisation framework that takes as input class membership estimates from existing classifiers, and a similarity matrix from a cluster ensemble operating solely on the new (target) data to be classified, in order to yield a consensus labelling of the new data. To do so, two parameters have to be defined a priori by the user: the relative importance of classifier and cluster ensembles, and the number of iterations of the algorithm. We propose a differential evolution (DE) algorithm, named dynamic DE (D²E), which is a computationally efficient alternative for optimising such parameters. D²E provides better results than DE by dynamically updating its control parameters. Moreover, competitive results were achieved when comparing D²E with three state-of-the-art algorithms.

Keywords: classification; clustering; cluster ensembles; differential evolution; optimisation; classifiers; similarity matrix; consensus labelling; data labelling.

DOI: 10.1504/IJBIC.2015.069288

International Journal of Bio-Inspired Computation, 2015 Vol.7 No.2, pp.111 - 124

Received: 03 Dec 2013
Accepted: 14 Mar 2014
Published online: 09 May 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: A differential evolution algorithm to optimise the combination of classifier and cluster ensembles

Keep up-to-date