Paper Info
Title
Particle swarm optimisation failure prediction based on fitness landscape characteristics
Abstract
Particle swarm optimisation (PSO) algorithms have been successfully used to solve many complex real-world optimisation problems. Since their introduction in 1995, the focus of research in PSOs has largely been on the algorithmic side with many new variations proposed on the original PSO algorithm. Relatively little attention has been paid to the study of problems with respect to PSO performance. The aim of this study is to investigate whether a link can be found between problem characteristics and algorithm performance for PSOs. A range of benchmark problems are numerically characterised using fitness landscape analysis techniques. Decision tree induction is used to develop failure prediction models for seven different variations on the PSO algorithm. Results show that for most PSO models, failure could be predicted to a fairly high level of accuracy. The resulting prediction models are not only useful as predictors of failure, but also provide insight into the algorithms themselves, especially when expressed as fuzzy rules in terms of fitness landscape features.
Year
DOI
Venue
2014
10.1109/SIS.2014.7011789
Swarm Intelligence
Keywords
Field
DocType
decision trees,failure analysis,fuzzy set theory,particle swarm optimisation,PSO algorithms,decision tree induction,failure prediction models,fitness landscape analysis techniques,fitness landscape characteristics,fuzzy rules,particle swarm optimisation failure prediction
Particle swarm optimization,Decision tree,Mathematical optimization,Fitness landscape,Fuzzy logic,Prediction algorithms,Linear programming,Artificial intelligence,Predictive modelling,Engineering,Machine learning
Conference
Citations 
PageRank 
References 
8
0.46
15
Authors
2
Name
Order
Citations
PageRank
Katherine Malan116212.77
Andries P. Engelbrecht266061.64