Cuckoo Search Algorithm Inspired by Artificial Bee Colony and Its Application

Cuckoo search algorithm with advanced levy flight strategy, can greatly improve algorithm's searching ability and increase the diversity of population. But it also has some problems. We improve them in this paper. First, in order to address the randomness of levy flight fluctuating significantly in the later and its poor convergence performance, we combine artificial bee colony algorithm with cuckoo search algorithm since artificial bee colony algorithm considers the group learning and cognitive ability, individuals learn from each other in the iterative process, which improves the local search ability of the later, and can find the optimal solution more quickly. Second, we use mutation operation to create the worst nest's position so as to increase the diversity of the population. Then put forward the ABC-M-CS algorithm and use the thought of K-means to cluster UCI data. The experimental results on UCI data sets indicate that ABC-M-CS algorithm has the fastest convergence speed, highest accuracy and stability.