# **Soccer Teamwork Evaluation Models**
# 足球团队合作评价模型
- <u>2020MCM-ICM ProblemD</u>
- ***Finalist*** 方案
> 2020年美国大学生数学建模竞赛ICM-D题 特等奖提名
>
> ## [GitHub仓库](https://github.com/HITMCMTeam/2020MCM-ICM)
>
> ## CSDN博客(中文版)
>
> - [2020美赛F奖论文(一):摘要、绪论和模型准备](https://blog.csdn.net/gzn00417/article/details/105813943)
> - [2020美赛F奖论文(二):传球网络模型(PNM)的建立和影响因子分析](https://blog.csdn.net/gzn00417/article/details/105813807)
> - [2020美赛F奖论文(三):足球团队指标和基于机器学习的球队表现预测](https://blog.csdn.net/gzn00417/article/details/105838230)
> - [2020美赛F奖论文(四):模拟退火算法驱动的结构策略设计](https://blog.csdn.net/gzn00417/article/details/105838880)
> - [2020美赛F奖论文(五):结合团队动力学的模型拓展、模型评价](https://blog.csdn.net/gzn00417/article/details/105839549)
![Certificate](https://img-blog.csdnimg.cn/20200428143915600.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2d6bjAwNDE3,size_16,color_FFFFFF,t_70)
## ***Summary***
- This paper proposes a method, with graph theory, probability theory and calculus, to build machine learning models based on data analysis, which aims at providing strategies for soccer coach's lineup arrangement and players' training.
> *本文利用图论,概率论和微积分的方法,利用数据分析和建立机器学习模型,为足球教练的阵容安排和球员训练提供策略。*
- Firstly, the Pass Network Model can be established according to the graph theory, whose edge-weights are evaluation of coordination degree of each dyadic configurations. Pass Evaluate Index is designed for evaluate a single pass, and the summation of each pass can be defined as the edge-weights of PNM. For analysis, the adjacency matrix of N participating players within a period. Several outstanding M configurations can be found by the sort of M-element combination with the key of the sum of the sub-complete graph edge weights. What’s more, investigation of the influence of time on pass density depends on the constructed and approximate function of time and pass.
> *Firstly,根据图论,在球员之间建立传球网络,并建立单次传球的价值评价模型,用于评价两两球员间传球的配合程度,即传球网络的边权。建立在一定时间范围内所有参与比赛的N个球员的邻接矩阵,通过以M个点的子完全图边权之和为排序关键字找出若干组优秀的M元组合。同时建立基于时间尺度的价值模型,用于评价时间对传球效率的影响。*
- Secondly, performance indicators that reflect successful teamwork can be divided into dynamic indicators and static indicators. Static indicators include player position arrangement and line-up with which player season heatmap models and player position models can be established while the dynamic indicators include opponents’ strength, side, coach, passes, defense, attack and fail. etc. After visualized analysis of the correlation between the dynamic indicators extracted after data cleaning, and with the setting label by the goal difference, the random forest classifier, a machine learning model, is used as a evaluation model of dynamic indicators. After the Grid Search used for tuning parameters, and cross-validation, the accuracy of the model achieving 80% approximately.
> *Secondly,我们将反映成功团队合作的绩效指标划分为静态指标和动态指标。静态指标包括球员位置安排和球队阵型(line-up),我们建立球员赛季热点模型和球员分布模型。动态指标包括opponents,side,coach,passes,defence,attack and fail等。对经过数据清洗动态指标之间通过可视化进行相关性分析后,以净胜球分类作为比赛样本标签,以随机森林分类器作为机器学习的模型,用网格搜索调优参数,建立动态指标评价模型,进行交叉验证,达到了80%的准确率。*
- Thirdly, the study focuses on the role of static indicators in the performance of the team and establishes different players' value evaluation models in different positions which comprehensively consider the player’s positions and technical statistical data evaluation. To optimize the value of 11-person permutation, we choose simulated annealing (SA) algorithm which searches the global optimal solution in cousin points in the same minimized search tree after the local optimal solution has attained. The model finally gave the best starting lineup formation. In addition, we also consider the following three secondary factors: tacit understanding between players, home and away influence, and coaching arrangements. All analysis above can be concluded as comprehensive suggestion to the coach.
> *Thirdly,通过上述中建立的模型进行观察分析,我们着重研究静态指标对球队的胜利起到的关键作用,综合考虑球员位置和技术数据评价模型,建立不同球员在不同位置价值评价模型。通过模拟退火算法,优化11人排列组合的考虑,在局部最优解的父级搜索树进行搜索全局最优解,最终给出价值最优的首发阵容阵型图。此外我们还考虑以下三个次要影响因素:球员间默契度,主客场影响和教练安排。给教练提出的综合建议。*
- Finally, we use the case of the Huskies to explain group dynamics. And use the conclusions obtained by the Huskies to build a model to explain how to design a more effective team and supplement the team performance indicators.
> *Finally,我们用哈士奇球队的案例来解释群体动力学。并用哈士奇球队建立模型得到的结论来说明如何设计更有效的团队,并对团队绩效指标进行补充。*
<u>**Key words:**</u> *Network; Graph theory; Calculus; Machine learning; Random forest classifier; Simulated annealing; Heat map; Group dynamics*
# 0 *Content*
## 1 Introduction 3
- 1.1 Background 3
- 1.2 Problem Restatement 3
## 2 Preparation of the Models 3
- 2.1 Processing Tools 3
- 2.2 Data Cleaning 4
## 3 Establishment of PNM and Analysis of Influence Factors 4
- 3.1 Pass Evaluation Index (PEI) 4
- 3.2 Pass Network Model (PNM) and Recognition of Network Pattern 6
- 3.3 Fluctuation of Passing State at The Time 6
## 4 Soccer Team Indexes and Performance Prediction Based on ML 7
- 4.1 Static Index (SI) 8
- 4.2 Dynamic Index (DI) 9
- 4.2.1 Data Cleaning and Feature Engineering 9
- 4.2.2 Visualization Analysis 9
- 4.2.3 RFC Establishment, Optimization, and Training 12
## 5 Design of Structural Strategies Driven by SA 13
- 5.1 Position Evaluation Engineering (PEE) 13
- 5.2 Optimization of Permutation and Combination Based on SA Algorithm 14
- 5.3 Other Structural Strategy Factors 15
- 5.4 Structural Strategy Conclusion 16
## 6 Model Extension Combined with Group Dynamics 16
- 6.1 Group and Soccer Team 17
- 6.1.1 Group Cohesiveness 17
- 6.1.2 Group Standard and Group Pressure 17
- 6.1.3 Individual Motivation and Group Goals 17
- 6.1.4 Leadership and Group Performance 18
- 6.1.5 Group Structure 18
- 6.2 Other influence factor of successful teamwork 18
## 7 Evaluation 18
- 7.1 Strength 18
- 7.2 Weakness 19
## 8 Reference 19
> # 0 *目录*
>
> ## 1 绪论 3
>
> - 1.1 背景 3
> - 1.2 问题重述 3
>
> ## 2 模型准备 3
>
> - 2.1 预处理工具 3
> - 2.2 数据清洗 4
>
> ## 3 传球网络模型(PNM)的建立和影响因子分析 4
>
> - 3.1 传球评价指标 (PEI) 4
> - 3.2 传球网络模型(PNM)构建及识别网络模式 6
> - 3.3 时间尺度上传球状态波动 6
>
> ## 4 足球团队指标和基于机器学习的球队表现预测 7
>
> - 4.1 静态指标 (SI) 8
> - 4.2 动态指标 (DI) 9
> - 4.2.1 数据清洗和特�
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
【资源说明】 1、该资源内项目代码都是经过测试运行成功,功能正常的情况下才上传的,请放心下载使用。 2、适用人群:主要针对计算机相关专业(如计科、信息安全、数据科学与大数据技术、人工智能、通信、物联网、数学、电子信息等)的同学或企业员工下载使用,具有较高的学习借鉴价值。 3、不仅适合小白学习实战练习,也可作为大作业、课程设计、毕设项目、初期项目立项演示等,欢迎下载,互相学习,共同进步!
资源推荐
资源详情
资源评论
收起资源包目录
2020年美国大学生数学建模竞赛 Finalist奖完整源码+说明.zip (284个子文件)
模拟退火算法的原理及算法在优化问题上的应用_庞峰.caj 4.95MB
stylesheet.css 1KB
fullevents.csv 4.28MB
passingevents.csv 1.83MB
(temp)Score.csv 4KB
PlayerData.csv 4KB
Total.csv 3KB
matches.csv 1KB
matchesNEW.csv 1KB
events.csv 913B
(temp)Score1.csv 902B
Match7.csv 656B
Match21.csv 650B
Match5.csv 640B
Match4.csv 637B
Match10.csv 629B
Match1.csv 622B
Match24.csv 620B
Match26.csv 617B
Match36.csv 614B
Match6.csv 608B
Match31.csv 605B
Match3.csv 604B
Match34.csv 604B
Match27.csv 599B
Match37.csv 599B
Match35.csv 599B
Match14.csv 598B
Match19.csv 598B
Match13.csv 598B
Match15.csv 598B
Match38.csv 593B
Match30.csv 588B
Match23.csv 584B
Match29.csv 578B
Match33.csv 578B
Match22.csv 577B
Match28.csv 569B
Match20.csv 565B
Match11.csv 556B
Match18.csv 550B
Match8.csv 547B
Match17.csv 546B
Match9.csv 539B
Match12.csv 526B
(temp)Score2.csv 521B
Match25.csv 518B
Match2.csv 514B
Match32.csv 486B
1.csv 486B
Match16.csv 419B
美赛论文.docx 1.51MB
567.docx 1.46MB
校对.docx 1.04MB
5.2.docx 748KB
5.1.docx 418KB
5.3.docx 263KB
SA.docx 226KB
Form.docx 183KB
Model4.docx 137KB
2020美赛参赛步骤及注意事项.docx 22KB
Evaluation.docx 18KB
README翻译.docx 17KB
MCM-ICM_Summary.docx 15KB
Summary.docx 15KB
团体动力学part1.docx 14KB
Restatement.docx 14KB
Q4MindMap.emmx 12KB
Match1.html 9KB
sheet001.html 8KB
tabstrip.html 771B
matches.ipynb 1.21MB
Pass.ipynb 629KB
processing.ipynb 425KB
normal.ipynb 174KB
Q4MindMap.jpg 1.14MB
result.jpg 240KB
SimulatedAnnealing.jpg 207KB
1.jpg 28KB
README.md 9KB
p1.md 1KB
p3.md 1014B
p2.md 788B
Judge.md 701B
p4.md 1B
2008495.pdf 7.59MB
基于GraphX传球网络的传球质量量化研究_廖彬.pdf 2.26MB
基于Gephi的足球比赛传球关系网络可视化分析_辜山.pdf 1.6MB
基于GraphX的传球网络构建及分析研究_张陶.pdf 1.41MB
足球比赛表现研究方法和评价指标体系研究_赵刚.pdf 1.24MB
2020_MCM_Problem_A.pdf 691KB
D题翻译:团队合作策略.pdf 427KB
A题翻译:向北移动.pdf 422KB
E题翻译:淹溺在塑料中.pdf 303KB
基于协同效应的团队合作激励因素研究_魏光兴.pdf 250KB
2020_ICM_Problem_D.pdf 148KB
Certificate of Achievement.pdf 145KB
2020_ICM_Problem_E.pdf 141KB
团队创造力数学模型的研究_丁志华.pdf 139KB
SimulatedAnnealing.pdf 90KB
共 284 条
- 1
- 2
- 3
资源评论
龙年行大运
- 粉丝: 1001
- 资源: 3854
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- lab7_02.c
- 基于 SpringCloud 和 Vue3 的OA系统
- 软考高级项目管理师-项目采购管理思维导图
- WordsVector (1).ipynb
- yolov7 车牌检测 车牌识别 中文车牌识别 检测 支持双层车牌 支持12种中文车牌
- 20240429_112025.m4a
- "麦嘟学编程"似乎是一个与编程学习相关的品牌或社区名称,它可能是一个在线教育平台、博客、论坛或社交媒体群组等,旨在帮助人们学习编
- OpenCV(Open Source Computer Vision Library)是一个开源的计算机视觉和机器学习软件库,由
- Redis入门基础篇+源码(springboot、maven)
- ChatGPT-4是由OpenAI开发的人工智能模型,是GPT(Generative Pre-trained Transform
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功