k-Means Clustering Algorithm Based on Improved Artificial Bee Colony Algorithm

HE Siyun;GAO Jianling;CHEN Lan;College of Big Data and Information Engineering,Guizhou University;Archive of Guizhou University;  

Improved Artificial Bee Colony( ABC) algorithm was proposed to improve k-means clustering algorithm to overcome k-means' disadvantage of sensitive to initial clustering centers. Max distance product algorithm used in initializing source can get high quality source; adding dynamical search range factor can accelerate convergence speed. This algorithm can initialize a high fitness source when giving up a local optimum solution,the effectiveness of this algorithm was enhanced by searching outliers. The results show this algorithm proposed has accelerated convergence speed and improved accuracy.

【Fund】： 贵州省科学技术基金项目(黔科合J字[2015]2045);; 贵州省档案局科研项目(2015D001);; 贵州大学研究生创新基金项目(研理工2017014)
【CateGory Index】： TP18;TP311.13

Download(CAJ format) Download(PDF format)

CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.