Michael Willis
Object recognition using enhanced particle swarm optimization.
Willis, Michael; Zhang, Li; Liu, Han; Xie, Hailun; Mistry, Kamlesh
Authors
Li Zhang
Han Liu
Hailun Xie
Kamlesh Mistry
Abstract
The identification of the most discriminative features in an explainable AI decision-making process is a challenging problem. This research tackles such challenges by proposing Particle Swarm Optimization (PSO) variants embedded with novel mutation and sampling iteration operations for feature selection in object recognition. Specifically, five PSO variants integrating different mutation and sampling strategies have been proposed to select the most discriminative feature subsets for the classification of different objects. A mutation strategy is firstly proposed by randomly flipping the particle positions in some dimensions to generate new feature interactions. Moreover, instead of embarking the position updating evolution in PSO, the proposed PSO variants generate offspring solutions through a sampling mechanism during the initial search process. Two offspring generation sampling schemes are investigated, i.e. the employment of the personal and global best solutions obtained using the mutation mechanism, respectively, as the starting positions for the subsequent search process. Subsequently, several machine learning algorithms are used in conjunction with the proposed PSO variants to perform object classification. As evidenced by the empirical results, the proposed PSO variants outperform the original PSO algorithm, significantly, for feature optimization.
Citation
WILLIS, M., ZHANG, L., LIU, H., XIE, H. and MISTRY, L. 2020. Object recognition using enhanced particle swarm optimization. In Proceedings of 2020 International conference machine learning and cybernetics (ICMLC 2020), 4 December 2020, [virtual conference]. Piscataway: IEEE [online], pages 241-246. Available from: https://doi.org/10.1109/ICMLC51923.2020.9469584
Conference Name | 2020 International conference on machine learning and cybernetics (ICMLC 2020) |
---|---|
Conference Location | [virtual conference] |
Start Date | Dec 4, 2020 |
Acceptance Date | Nov 15, 2020 |
Online Publication Date | Dec 2, 2020 |
Publication Date | Jul 5, 2021 |
Deposit Date | Jul 27, 2021 |
Publicly Available Date | Jul 27, 2021 |
Publisher | IEEE Institute of Electrical and Electronics Engineers |
Pages | 241-246 |
Series ISSN | 2160-1348 |
ISBN | 9780738124261 |
DOI | https://doi.org/10.1109/icmlc51923.2020.9469584 |
Keywords | Feature selection; Object recognition; Optimization |
Public URL | https://rgu-repository.worktribe.com/output/1385946 |
Files
WILLIS 2020 Object recognition (AAM)
(411 Kb)
PDF
Copyright Statement
You might also like
Multi-head attention-based long short-term memory for depression detection from speech.
(2021)
Journal Article
Deep recurrent neural networks with attention mechanisms for respiratory anomaly classification.
(2021)
Conference Proceeding