摘要
针对K-means算法对初始聚类中心敏感、算法容易收敛于局部解等问题,运用了增加飞行时间因子的粒子群算法,提高粒子群算法性能.利用改进的粒子群算法与K-means算法相结合,提高了基于粒子群算法的K-means算法性能.数值试验验证了提出算法的收敛性,且最优解的精度优于K-means算法、PSO算法和PSO-K算法.
Considering K-means algorithm was sensitive to the initial cluster centers and easy to converge to local solution and other issues, we increased flight time factor to improve particle swarm algorithm performance. The improved particle swarm algorithm and K-means algorithm were combined to improve the performance of K-means algorithm based on particle swarm optimi- zation. Numerical experiments verified the proposed convergence of the algorithm, and the opti- mal solution accuracy was better than K-means algorithm, PSO algorithm and PSO-K algorithm.
出处
《山东理工大学学报(自然科学版)》
CAS
2015年第5期16-20,共5页
Journal of Shandong University of Technology:Natural Science Edition
基金
国家自然科学基金资助项目(61370207)