Research on internet information mining based on agent algorithm
Research on internet information mining based on agent algorithm
复制标题
DOI：
10.1016/j.future.2018.04.040
复制
发表时间：
2018-09-01
影响因子：
7.5
通讯作者：
Zou, Yuntao
中科院分区：
文献类型：
--
作者：
Wu, Shaofei;Wang, Mingqing;Zou, Yuntao
随着信息技术特别是网络技术的飞速发展，人们收集、存储和传输数据的能力不断提高。数据以爆炸性的方式爆炸。与此形成鲜明对比的是，为决策提供有价值数据的能力非常差。数据挖掘是本文研究的最基本的问题。为了克服传统聚类算法k-均值聚类初始聚类中心难以确定的缺点，对k-均值算法进行了改进。在确定初始K-时，改进收敛因子，达到全局最优，从而实现聚类中心的确定。通过使用改进的k-means算法对犯罪数据进行逼近，验证了该方法的有效性。(C)2018爱思唯尔B. V.保留所有权利。
With the rapid development of information technology, especially network technology, people's ability to collect, store and transmit data are increasing. The data have exploded in an explosive manner. In sharp contrast, the ability to make valuable data for decision making is very poor. In this paper, data mining is the most basic problem. In order to overcome the shortcomings of the traditional clustering algorithm for k-means clustering, it is difficult to determine the initial clustering center and the k-means algorithm is improved. When determining the initial K-, the convergence factor is improved and the global optimum is achieved, so as to realize the determination of clustering center. By using improved k-means algorithm to approximate the criminal data, the validity of this method is verified. (C) 2018 Elsevier B.V. All rights reserved.