基于随机森林和灰色GM（1,1）对四人雪车成绩分析及米兰冬奥会混合预测研究
|
徐嘉欣，尹一全
|
1.烟台南山学院体育学院，山东烟台，265713；2.北京体育大学中国冰雪运动学院，北京，100084
|
摘要：为提高我国男子四人雪车项目的竞技表现提供理论参考，本研究提出了一种融合随机森林回归与灰色GM(1,1)模型的混合预测方法。基于2010-2022年四届冬奥会男子四人雪车项目前三名单轮成绩数据，结合赛道物理参数，构建赛道难度系数与加权指标，利用随机森林量化赛道特征对成绩的影响，并通过灰色模型捕捉成绩的长期趋势。研究结果显示，赛道垂直落差与弯道数量对成绩影响最为显著，灰色模型预测的平均相对误差为2.88%，关联度为0.833，方差比为0.307，满足一级精度标准。最终预测2026年米兰冬奥会男子四人雪车前三名最优轮次成绩分别为58.66秒、60.72秒和60.99秒。该方法有效解决了小样本条件下冬季项目成绩预测的难题，为我国雪车项目备战米兰冬奥会提供了科学依据，并为同类冰雪竞速项目提供了可借鉴的方法论框架。
关健词：随机森林；灰色GM(1,1)模型；四人雪车；成绩预测；米兰冬奥会
|
Performance Analysis of Four-man Bobsleigh and Hybrid Prediction for Milan Winter Olympics Based on Random Forest and Grey GM(1,1) Model
|
Jiaxin Xu,Yiquan Yin
1.School of Physical Education, Yantai Nanshan University，Yantai Shandong 265713，China；；2.China Snow and Ice Sports College, Beijing Sport University，Beijing 100084，China
|
Abstract：To provide a theoretical reference for improving the competitive performance of China's four-man bobsleigh team, this study proposes a hybrid prediction method integrating random forest regression and the grey GM(1,1) model. Based on the single-run time data of the top three athletes in the four Winter Olympics from 2010 to 2022, combined with track physical parameters, a track difficulty coefficient and a weighted index were constructed. The random forest model was used to quantify the influence of track characteristics on performance, while the grey model captured long-term performance trends. The results show that vertical drop and number of curves were the most significant factors affecting performance. The grey model achieved a mean relative error of 2.88%, a relational degree of 0.833, and a variance ratio of 0.307, meeting the first-class accuracy standard. The predicted optimal run times for the top three in the 2026 Milan Winter Olympics are 58.66 s, 60.72 s, and 60.99 s, respectively. This method effectively addresses the challenge of predicting performance in winter sports with small sample sizes, providing a scientific basis for China's bobsleigh preparation and a methodological reference for similar ice and snow racing sports.
Keywords : Random Forest；Grey GM(1,1) Model；Four-man Bobsleigh；Performance Prediction；Milan Winter Olympics
参考文献
[1] International Bobsleigh & Skeleton Federation. Pre-homologation of Cortina d’Ampezzo’s Sliding Centre concludes successfully[EB/OL]. (2025-03-28)[2025-04-22].
[2] 石慧敏, 章东迎, 章永辉. 奥运奖牌可以被预测吗？——基于可解释机器学习视角[J]. 上海体育学报, 2024, 48(4): 26-36. doi:10.16099/j.sus.2023.10.27.0002.
[3] 尹一全, 邱森, 孟庆军, 等. 钢架雪车运动员竞赛成绩的影响因素研究[J]. 北京体育大学学报, 2020, 43(12): 130-141.
[4] 冬奥播报丨女子单人雪车怀明明第6 创中国该项目冬奥参赛最好成绩[N/OL]. 人民网, 2022-02-14[2024-06-20]. http://ent.people.com.cn/n1/2022/0214/c1012-32351778.html.
[5] Sun X, Wang Y, Khan J. Hybrid LSTM and GAN model for action recognition and prediction of lawn tennis sport activities[J]. Soft Computing, 2023.
[6] 陈岷. 因子分析和神经网络相融合的体育成绩预测模型[J]. 现代电子技术, 2017, 40(5): 130-133. doi:10.16652/j.issn.1004-373x.2017.05.033.
[7] 修霆喆, 于红妍, 黄雯妍. 基于BP神经网络的乒乓球优秀女子单打比赛结果预测模型构建及仿真应用[J]. 哈尔滨体育学院学报, 2024, 42(2): 89-96. doi:10.16099/j.sus.2023.10.27.0002.
[8] GAO Z, KOWALCZYK A. Random forest model identifies serve strength as a key predictor of tennis match outcome[J]. Journal of Sports Analytics, 2021, 7: 255-262. doi:10.3233/JSA-200515.
[9] MARQUéS-JIMéNEZ D, RAYA-GONZáLEZ J, SáNCHEZ-DíAZ S, et al. A random forest clustering to explore the influence of physical fitness level of youth basketball players on match-related physical performance[J]. International Journal of Sports Science & Coaching, 2022, 17(3): 567-578. doi:10.1177/17479541211041725.
[10] BRIAND J, DEGUIRE S, GAUDET S, et al. Monitoring variables influence on random forest models to forecast injuries in short-track speed skating[J]. Frontiers in Sports and Active Living, 2022, 4: 789012. doi:10.3389/fspor.2022.789012.
[11] LIU J, CARR P. Detecting and tracking sports players with random forests and context-conditioned motion models[EB/OL]. (2024-01-16)[2024-06-20]. https://doi.org/10.21203/rs.3.rs-3859351/v1.
[12] CHEN Z. Application of random forest algorithm based on fiber optic sensors in fatigue detection in sports competitions[EB/OL]. (2024-01-16)[2024-06-20]. https://doi.org/10.21203/rs.3.rs-3859351/v1.
[13] LI Y, MU Y. Research and performance analysis of random forest-based feature selection algorithm in sports effectiveness evaluation[C]//Proceedings of the 2023 International Conference on Artificial Intelligence in Sports. Beijing: IEEE, 2023: 1-6. doi:10.1109/ICAIS58442.2023.00010.
[14] 沈杰.基于灰色理论的可靠性寿命预测研究[D].西华师范大学,2024.
[15] 蔡素丽.灰色系统理论GM(1,1)预测模型应用实证分析[J].廊坊师范学院学报(自然科学版),2015,15(6):5-8,12.
[16] 魏春玲,孙晋海.奥运会田径项目成绩发展趋势及灰色预测研究[J].中国体育科技,2005,41(2):18-20.
[17] 胡文强,李思民.世锦赛视角下标枪竞争格局和成绩演进研究[J].辽宁体育科技,2020,42(4):97-101.
[18] 龙家勇, 蔚卓虹. 基于GM(1,1)灰色模型对奥运会男子100m金牌成绩的预测研究[J].西南师范大学学报(自然科学版), 2023, 48(7): 123-128. doi:10.13718/j.cnki.xsxb.2023.07.018.
[19] Wang T Y, Cui J, Fan Y. A wearable-based sports health monitoring system using CNN and LSTM with self-attentions[J]. PLOS ONE, 2023. doi:10.1371/journal.pone.0283212.
|
|
|
论文收录证明 / 文献检索报告
Document Retrieval Certificate / Proof of Publication Indexing
作者贡献声明 / 贡献确认书
Author Contribution Statement / Certificate of Authorship Contribution
同行评审报告 / 评审意见
Peer Review Report / Peer Review Comments
利益冲突
Conflict of Interest
作者声明不存在任何利益冲突。
The author declares no conflict of interest.
|
|
