【摘要】 在入侵数据定位优化检测中,由于多源数据库是由多个异构数据库构成的,相同的入侵数据在不同的异构数据库中会发生变异,传统的入侵数据定位方法没有考虑多源数据库的复杂性,从而降低了入侵数据定位的准确性。提出采用聚类粒子群算法的入侵数据定位方法。利用聚类算法对入侵数据特征进行聚类,获得入侵数据特征的聚类中心,将所有聚类中心进行实数编码,构成初始粒子种群,以入侵数据分类的目标函数为目标,利用粒子群算法进行寻优,最终实现入侵数据的准确定位。仿真结果表明,改进算法能够提高多源数据库中的入侵数据定位的准确性和效率。更多还原

【Abstract】 Multi-source database is composed of multiple heterogeneous databases,the invasion of the same data in different heterogeneous database will mutate.Traditional intrusion data locating methods did not consider the complexity of the multi-source databases,which reduces the invasion of positioning accuracy of the data.A kind of intrusion data clustering locating method based on particle swarm algorithm is put forward.Clustering algorithm is used to analyse the intrusion data clustering,get the invasion characteristics of the data clustering center,all the clustering centers are coded with real number,and initial population particles are formed.The intrusion data classification is selected as the objective function,the particle swarm optimization(pso) algorithm is used to serch optimization,and the intrusion data accurate positioning is realized.Simulation results show that the proposed algorithm can improve the accuracy and efficiency of multi-source intrusion data location in the database.更多还原