基于神经网络的中超联赛球队实力水平聚类方法研究  

Study on the Level Clustering Method of Team Strength in Super League Based on Neural Network

作　　者：兰兆青[1] 吴炎兵 李京玲[3] LAN Zhao-qing;WU Yan-bing;LI Jing-ling(School of Arts and Sciences,Shanxi Agricultural University,Taigu Shanxi,030801;School of Physical Education,Shanxi Agricultural University,Taigu Shanxi,030801;School of water conservancy science and Engineering,Taiyuan University of Technology Taiyuan Shanxi,030006)

机构地区：[1]山西农业大学文理学院,山西太谷030801 [2]山西农业大学体育学院,山西太谷030801 [3]太原理工大学水利科学与工程学院,山西太原030001

出　　处：《山西大同大学学报（自然科学版）》2020年第3期93-96,共4页Journal of Shanxi Datong University(Natural Science Edition)

基　　金：山西农业大学科技创新基金[20142-16];山西省自然科学基金青年项目[201601D202070]。

摘　　要：为了在足球比赛中更准确、快速地寻找种子队,客观对球队分组,提出一种基于自组织特征映射网络和模糊聚类分析相结合的聚类方法。运用该方法将中超联赛的16支球队聚成四类作为评价标准,任选两支球队对该聚类方法进行测试,并与球队比赛成绩对照。结果发现:所提的聚类方法是合理的,可以客观地反映出参赛球队的实力和水平,有效地进行球队赛前水平评估和球队分组。In order to find the seed teams more accurately and quickly in football matches and group the teams objectively,this pa⁃per presents a clustering method based on self organizing feature map network and fuzzy clustering analysis.By using this method,16 teams in Chinese Super League are grouped into four categories,and the results of clustering are taken as evaluation criteria,and two teams are chosen to test the clustering method by comparing the test results with the team competition results,it is concluded that the clustering method proposed in this paper is reasonable,and can objectively reflect the strength and level of the participating teams,and effectively carry out the team pre-competition level evaluation and team grouping.

关 键 词：自组织特征映射网络 模糊聚类分析 中超足球联赛水平聚类 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] G843[自动化与计算机技术—控制科学与工程]