Journal
CONNECTION SCIENCE
Volume 25, Issue 2-3, Pages 151-160Publisher
TAYLOR & FRANCIS LTD
DOI: 10.1080/09540091.2013.854735
Keywords
evolutionary computation; data mining; particle swarm optimization; artificial fish swarm algorithm; modified fruit fly optimization algorithm; general regression neural network
Ask authors/readers for more resources
Evolutionary computation is a computing mode established by practically simulating natural evolutionary processes based on the concept of Darwinian Theory, and it is a common research method. The main contribution of this paper was to reinforce the function of searching for the optimised solution using the fruit fly optimization algorithm (FOA), in order to avoid the acquisition of local extremum solutions. The evolutionary computation has grown to include the concepts of animal foraging behaviour and group behaviour. This study discussed three common evolutionary computation methods and compared them with the modified fruit fly optimization algorithm (MFOA). It further investigated the ability of the three mathematical functions in computing extreme values, as well as the algorithm execution speed and the forecast ability of the forecasting model built using the optimised general regression neural network (GRNN) parameters. The findings indicated that there was no obvious difference between particle swarm optimization and the MFOA in regards to the ability to compute extreme values; however, they were both better than the artificial fish swarm algorithm and FOA. In addition, the MFOA performed better than the particle swarm optimization in regards to the algorithm execution speed, and the forecast ability of the forecasting model built using the MFOA's GRNN parameters was better than that of the other three forecasting models.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available