keyboard_backspace
返回卷期清單 (第12卷 第1期 / 2025 / 3)
第12卷 第1期
/
2025 / 3
/
pp. 45 - 66
DOI:
臺北市基層競技運動選手訓練站數據治理與人工智慧運用
Data Governance and Artificial Intelligence Applications of Grassroots Athletes Training Stations in Taipei City
66
19
作者
羅國偉 Guo-Wei Luo
(臺北市政府體育局; 國立臺灣師範大學體育與運動科學系 Department of Sports, Taipei City Government, Taipei, Taiwan; Department of Physical Education and Sport Sciences, National Taiwan Normal University, Taipei, Taiwan.)
鄭明華 Mien-Hua Cheng
(臺北市政府體育局 Department of Sports, Taipei City Government, Taipei, Taiwan)
林文斌 Wen-Bin Lin *
(國立臺北藝術大學體育中心 Physical Education Center, Taipei National University of the Arts, Taipei, Taiwan.)
羅國偉 Guo-Wei Luo
臺北市政府體育局; 國立臺灣師範大學體育與運動科學系 Department of Sports, Taipei City Government, Taipei, Taiwan; Department of Physical Education and Sport Sciences, National Taiwan Normal University, Taipei, Taiwan.
鄭明華 Mien-Hua Cheng
臺北市政府體育局 Department of Sports, Taipei City Government, Taipei, Taiwan
林文斌 Wen-Bin Lin *
國立臺北藝術大學體育中心 Physical Education Center, Taipei National University of the Arts, Taipei, Taiwan.
中文摘要

目的：導入精準運動科學研究、探討臺北市基層競技運動選手訓練站數據治理與人工智慧運用。方法：經融合運動數據治理、資料庫知識探索、效率與生產力、類神經網路、IPA管理矩陣分析等，建構臺北市基層競技運動選手訓練站AI預測數據治理模型。結果：從運動數據治理角度切入，基站複評分數強調作對的事情，效率與生產力衡量強調把事情做好，運用類神經網路、倒傳遞類神經網絡資料包絡分析法、結合基站重要性績效分析，求算109-113年「基站複評分數」、109-113年「基站效率值」、109-113年「基站趨勢分析」，運用AI預測114年「基站複評分數」、114年「效率值預測」、114年「基站趨勢分析」等結果。結論：為國內第一篇結合人工智慧、以及效率與生產力的運動數據治理研究，符合國家政策發展趨勢、提供精準運動科學研究方法創新應用、完整考量資料科學增進運動大數據應用參考、完備臺北市基層競技運動選手訓練站AI預測數據治理模型與步驟，用以因應未來包括AI人工智慧、運動數據治理、運動大數據面臨的問題與挑戰。

英文摘要

Purposes: This study integrates precision sports science research with an exploration of grassroots athletes’ training stations (GATS) data governance and the application of artificial intelligence (AI). Methods: The methodology integrated sports data governance principles, knowledge discovery in databases, efficiency and productivity considerations, AI techniques, and important-performance analysis, constructing an AI-based prediction model for the Taipei City GATS data governance system. Results: This study emphasizes a sports data governance perspective, highlights the importance of GATS scores in driving informed decision-making, and addresses the significance of efficiency and productivity in executing tasks effectively. We employed artificial neural networks, back-propagation neural networks, data envelopment analysis, and combined GATS importance-performance analysis to strive for GATS scores, efficiency, and trend analysis for the period 2020-2024. The model then predicted GATS scores, efficiency, and trends for 2025. Conclusions: This study is the first to integrate AI with efficiency and productivity considerations into Taiwan's sports data governance. Aligned with national policy development trends, it offers innovative approaches to precision sports science research and data science applications in sports big data management. The AI prediction model for Taipei City’s GATS data governance serves as a reference for addressing future challenges in AI, sports data governance, and big data management.

中文關鍵字

類神經網路; 運動數據治理; 資料庫知識探索; 精準運動科學研究; 菁英運動員

英文關鍵字

artificial neural networks; sports dada governance; knowledge discovery in database; precision sports science research; elite athletes