lensen2016Particle.pdf (290.21 kB)

Particle swarm optimisation representations for simultaneous clustering and feature selection

Download (290.21 kB)
conference contribution
posted on 06.10.2020 by Andrew Lensen, Bing Xue, Mengjie Zhang
© 2016 IEEE. Clustering, the process of grouping unlabelled data, is an important task in data analysis. It is regarded as one of the most difficult tasks due to the large search space that must be explored. Feature selection is commonly used to reduce the size of a search space, and evolutionary computation (EC) is a group of techniques which are known to give good solutions to difficult problems such as clustering or feature selection. However, there has been relatively little work done on simultaneous clustering and feature selection using EC methods. In this paper we compare medoid and centroid representations that allow particle swarm optimisation (PSO) to perform simultaneous clustering and feature selection. We propose several new techniques which improve clustering performance and ensure valid solutions are generated. Experiments are conducted on a variety of real-world and synthetic datasets in order to analyse the effectiveness of the PSO representations across several different criteria. We show that a medoid representation can achieve superior results compared to the widely used centroid representation.

History

Preferred citation

Lensen, A., Xue, B. & Zhang, M. (2017, February). Particle swarm optimisation representations for simultaneous clustering and feature selection. In 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016 2016 IEEE Symposium Series on Computational Intelligence (SSCI), Athens, GREECE (pp. 1-8). IEEE. https://doi.org/10.1109/SSCI.2016.7850124

Conference name

2016 IEEE Symposium Series on Computational Intelligence (SSCI)

Conference Place

Athens, GREECE

Conference start date

06/12/2016

Conference finish date

09/12/2016

Title of proceedings

2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016

Publication or Presentation Year

09/02/2017

Pagination

1-8

Publisher

IEEE

Publication status

Published

Exports