La Trobe
TEC_VLPSO.pdf (1.22 MB)
Download file

Variable-length particle swarm optimization for feature selection on high-dimensional classification

Download (1.22 MB)
journal contribution
posted on 18.01.2021, 05:51 by Binh TranBinh Tran, Bing Xue, Mengjie Zhang
With a global search mechanism, particle swarm optimization (PSO) has shown promise in feature selection (FS). However, most of the current PSO-based FS methods use a fix-length representation, which is inflexible and limits the performance of PSO for FS. When applying these methods to high-dimensional data, it not only consumes a significant amount of memory but also requires a high computational cost. Overcoming this limitation enables PSO to work on data with much higher dimensionality which has become more and more popular with the advance of data collection technologies. In this paper, we propose the first variable-length PSO representation for FS, enabling particles to have different and shorter lengths, which defines smaller search space and therefore, improves the performance of PSO. By rearranging features in a descending order of their relevance, we facilitate particles with shorter lengths to achieve better classification performance. Furthermore, using the proposed length changing mechanism, PSO can jump out of local optima, further narrow the search space and focus its search on smaller and more fruitful area. These strategies enable PSO to reach better solutions in a shorter time. Results on ten high-dimensional datasets with varying difficulties show that the proposed variable-length PSO can achieve much smaller feature subsets with significantly higher classification performance in much shorter time than the fixed-length PSO methods. The proposed method also outperformed the compared non-PSO FS methods in most cases.

Funding

This work was supported in part by the Marsden Fund of New Zealand Government under Contract VUW1509 and Contract VUW1615, in part by the Huawei Industry Fund under Grant E2880/3663, and in part by the University Research Fund at Victoria University of Wellington under Grant 209862/3580 and Grant 213150/3662.

History

Publication Date

30/06/2019

Journal

IEEE Transactions on Evolutionary Computation

Volume

23

Issue

3

Pagination

15p. (p. 473-487)

Publisher

IEEE

ISSN

1089-778X

Rights Statement

The Author reserves all moral rights over the deposited text and must be credited if any re-use occurs. Documents deposited in OPAL are the Open Access versions of outputs published elsewhere. Changes resulting from the publishing process may therefore not be reflected in this document. The final published version may be obtained via the publisher’s DOI. Please note that additional copyright and access restrictions may apply to the published version.