机构地区: 华东理工大学信息科学与工程学院
出 处: 《计算机工程》 2007年第4期125-127,共3页
摘 要: 针对K均值聚类算法在全局优化中的不足,提出了基于粒子群的K均值(PSO-KM)聚类算法。粒子群优化算法作为一种基于群智能方法的演化计算技术,有很好的全局搜索能力。通过理论分析及实验证明,该算法有较好的全局收敛性,能有效地克服传统的K均值算法易陷入局部极小值的缺点。对KDD-99数据集的仿真实验结果表明,该算法在入侵检测中能获得令人满意的检测率和误检率。 With the deficiency of global search ability for K-means clustering algorithm, K-means algorithm based on particle swarm optimization (PSO-KM) is proposed. As an evolutionary computation technique based on swarm intelligence particle swarm optimization (PSO) algorithm has high global search ability, the analysis and experiment show PSO-KM could avoid local optima and has relatively good global convergence. Experiment over network connection that records from KDD CUP 1999 data set is implemented to evaluate the proposed method. The results clearly show the outstanding performance of the proposed method.
领 域: [自动化与计算机技术] [自动化与计算机技术]