Yunlong Wang1,2,3, Xiong Luo1,2,4,*, Jing Zhang1,2,3, Zhigang Zhao1, Jun Zhang5
Intelligent Automation & Soft Computing, Vol.26, No.5, pp. 961-971, 2020, DOI:10.32604/iasc.2020.010128
Abstract K-means is a simple and commonly used algorithm, which is widely
applied in many fields due to its fast convergence and distinctive performance. In
this paper, a novel algorithm is proposed to help K-means jump out of a local
optimum on the basis of several ideas from evolutionary computation, through
the use of random and evolutionary processes. The experimental results show
that the proposed algorithm is capable of improving the accuracy of K-means
and decreasing the SSE of K-means, which indicates that the proposed algorithm
can prevent K-means from falling into the local optimum to some extent. More >
Login
Register
