摘要
针对K_means聚类算法对初始参数较敏感且相对容易出现局部最优解的问题,提出基于布谷鸟算法优化的K_means聚类算法,并将优化后的K_means聚类算法与条件均值填充算法相结合,递归地填充缺失数据。实验结果表明:与传统算法相比,基于布谷鸟算法优化K_means聚类的缺失数据填充算法具有更好的效果。
Aiming at the problem that K_means clustering algorithm is sensitive to initial parameters and relatively easy to appear local optimal solution,a K_means clustering algorithm based on cuckoo algorithm is proposed,and the optimized K_means clustering algorithm is combined with conditional mean filling algorithm.Recursively fill in missing data.The experimental results show that the missing data filling algorithm based on K_means clustering optimized by cuckoo algorithm has better effect than the traditional algorithm.
作者
林枫
蔡延光
蔡颢
张丽
Lin Feng;Cai Yanguang;Cai Hao;Zhang Li(School of Automation,Guangdong University of Technology,Guangzhou,Guangdong 510006,China;Department of Health Science and Technology,Aalborg University,Aalborg 9220,Denmark)
出处
《自动化与信息工程》
2020年第6期13-17,27,共6页
Automation & Information Engineering
基金
国家自然科学基金(61074147)
广东省自然科学基金(S2011010005059)
广东省教育部产学研结合项目(2012B091000171,2011B090400460)
广东省科技计划项目(2012B050600028,2014B010118004,2016A050502060)
广州市花都区科技计划项目(HD14ZD001)
广州市科技计划项目(201604016055)
广州市天河区科技计划项目(2018CX005)。
