An improved adaptive cuckoo search algorithm based on the population feature and iteration information. (28th February 2020)

• Record Type: Journal Article
• Authors: Chaochuan, Jia; Ting, Yang; Chuanjiang, Wang; Binghui, Fan; Fugui, He
• Is Part Of: International journal of communication networks and distributed systems. Volume 24:Number 3(2020)
• Page Start: 233
• Page End: 248
• Publication Date: 2020-02-28
• Subjects: cuckoo search -- optimisation algorithm -- adaptive strategy -- support vector machine -- SVM -- classification; Computer networks -- Periodicals; Telecommunication systems -- Periodicals; Electronic data processing -- Distributed processing -- Periodicals; 004.6
• Languages: English
• ISSNs: 1754-3916

Abstract

Cuckoo search (CS) is widely used to solve many optimisation problem, which is a biologically inspired the brood parasitic behaviour of a type of cuckoos and the Lévy flights behaviour of some animals. However, it has been demonstrated to easily get trapped into local optimal solutions and slow convergence speed. Therefore, an improved adaptive cuckoo search (IACS) optimisation algorithm is proposed in this article. Two adaptive strategies based on the population feature and iteration information feedback which are integrated into the CS algorithm to adjust the parameters pa and α 0 . We compared the proposed algorithm to CS and five variants on the 30 benchmark functions proposed in CEC 2014. In addition, the proposed algorithm and CS are integrated into support vector machine (SVM) for classification. Experimental results certify that the modified algorithm is superior to the CS for most optimisation problems and has better performance than the other variants of CS algorithm.