Intelligent Leukaemia Diagnosis with Bare-Bones PSO based Feature Optimization

Srisukkham, Worawut, Zhang, Li, Neoh, Siew Chin, Todryk, Stephen and Lim, Chee Peng (2017) Intelligent Leukaemia Diagnosis with Bare-Bones PSO based Feature Optimization. Applied Soft Computing, 56. pp. 405-419. ISSN 1568-4946

[img]
Preview
Text
1-s2.0-S1568494617301485-main.pdf - Published Version
Available under License Creative Commons Attribution 4.0.

Download (1MB) | Preview
[img] Text
journal_optimized_ProfLim.pdf - Accepted Version
Restricted to Repository staff only

Download (1MB) | Request a copy
Official URL: https://doi.org/10.1016/j.asoc.2017.03.024

Abstract

In this research, we propose an intelligent decision support system for acute lymphoblastic leukaemia (ALL) diagnosis using microscopic images. Two Bare-bones Particle Swarm Optimization (BBPSO) algorithms are proposed to identify the most significant discriminative characteristics of healthy and blast cells to enable efficient ALL classification. The first BBPSO variant incorporates accelerated chaotic search mechanisms of food chasing and enemy avoidance to diversify the search and mitigate the premature convergence of the original BBPSO algorithm. The second BBPSO variant exhibits both of the abovementioned new search mechanisms in a subswarm-based search. Evaluated with the ALL-IDB2 database, both proposed algorithms achieve superior geometric mean performances of 94.94% and 96.25%, respectively, and outperform other metaheuristic search and related methods significantly for ALL classification.

Item Type: Article
Uncontrolled Keywords: Feature selection, Bare-bones particle swarm optimization, acute lymphoblastic leukaemia classification
Subjects: B800 Medical Technology
G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Faculties > Health and Life Sciences > Applied Sciences
Depositing User: Becky Skoyles
Date Deposited: 27 Mar 2017 15:19
Last Modified: 31 Jul 2021 13:34
URI: http://nrl.northumbria.ac.uk/id/eprint/30210

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics