Please use this identifier to cite or link to this item:
Title: Novel particle swarm optimization algorithms with applications to healthcare data analysis
Authors: Liu, Weibo
Advisors: Wang, Z
Liu, X
Keywords: Evolutionary computation;Deep learning;Data analysis;NHS;Clustering, classification
Issue Date: 2020
Publisher: Brunel University London
Abstract: Optimization problem is a fundamental research topic which has been receiving increasing interest according to its application potential in almost all real-world systems including engineering systems, large-scaled complex networks, healthcare management systems and so on. A large number of heuristic algorithms have been developed with the purpose of effectively solving the optimization problems during the past few decades. Served as a powerful family of heuristic algorithms, the particle swarm optimization (PSO) algorithm has been successfully employed in a variety of practical applications in dealing with optimization problems. The PSO algorithm has exhibited more competitive performance than many popular evolutionary computation approaches because of its easy implementation, fast convergence and comprehensive ability of converging to a satisfactory solution. Nevertheless, there is still much room to improve the PSO algorithm in terms of both the convergence rate and the population diversity. To summarize, there are three challenging problems in developing new variant PSO algorithms with hope to further improve the convergence rate of the PSO algorithm and maintain the population diversity: 1) how to adjust the control parameters of the PSO algorithm; 2) how to achieve the balance between the local search and the global search during the evolution process; and 3) how to guarantee the search ability of the particles and avoid premature convergence. In this thesis, we address the above mentioned challenging problems and aim to design effective variant PSO algorithms with applications in intelligent data analysis. It should be pointed out that all the developed PSO algorithms in this thesis have been evaluated by comparing with some currently popular variant PSO algorithms. • With the aim to improve the convergence rate of the optimizer, an adaptive weighting PSO algorithm is put forward where a sigmoid-function-based weighting strategy is introduced to adjust the acceleration coefficients. With this weighting strategy, the distances from the particle to the global best position and from the particle to its personal best position are both taken into consideration, thereby having the distinguishing feature of enhancing the convergence rate. • As with other evolutionary computation approaches, the modification of parameters is an efficient method for improving the search ability of the algorithm. We present a randomised PSO algorithm where Gaussian white noise with adjustable intensity is utilized to randomly perturb the acceleration coefficients in order to explore and exploit the problem space thoroughly. • To further develop a novel PSO algorithm with promising search ability, we propose a randomly occurring distributedly delayed particle swarm optimization (RODDPSO) algorithm which demonstrates competitive performance in seeking the optimal solution. The randomly occurring distributed time delays not only contribute to a thorough exploration of the search space but also achieve a proper balance between the local exploitation and the global exploration. • To fully investigate the application potential of the developed PSO algorithms, we apply the RODDPSO algorithm to intelligent data analysis (including data clustering and classification problems). We optimize the initial cluster centroids of the K-means clustering algorithm and the hyperparameters of the deep neural network by using the RODDPSO algorithm. The developed PRODDPSO-based algorithms are successfully employed in patients’ triage categorization and patient attendance disposal problems with satisfactory performance
Description: This thesis was submitted for the award of Doctor of Philosophy and was awarded by Brunel University London.
Appears in Collections:Computer Science
Dept of Computer Science Theses

Files in This Item:
File Description SizeFormat 
FulltextThesis.pdf2.18 MBAdobe PDFView/Open

Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.