Publications-Theses
Article View/Open
Publication Export
Google ScholarTM
NCCU Library
Citation Infomation
Related Publications in TAIR
| Title | FedTS：基於時間序列聯邦學習的羽球揮拍評分 FedTS: Federated Learning Based on Time Series For Scoring Badminton Strokes |
| Creator | 思沛淇 Si, Pei-Qi |
| Contributor | 蔡子傑 Tsai, Tzu-Chieh 思沛淇 Si, Pei-Qi |
| Key Words | 聯邦學習 非獨立同分佈 時間序列資料 穿戴式裝置 知識蒸餾 Federated Learning Non-iid Time-series Data Wearable Devices Knowledge Distillation |
| Date | 2025 |
| Date Issued | 4-Feb-2025 15:44:28 (UTC+8) |
| Summary | 近年來，隨著疫情逐漸趨緩，人們開始積極地投入各項戶外運動。其中，羽球運動因戴資穎在國際賽的亮眼表現，以及李洋、王齊麟勇奪奧運金牌，一時間成為臺灣運動愛好者的矚目焦點，帶動羽球運動人口持續攀升。根據教育部體育署相關調查，網路族群之中每三人便有一人使用穿戴式裝置紀錄運動數據；穿戴式裝置在運動科技領域已成為一種時尚趨勢。
本研究針對時間序列資料的特性，運用穿戴式裝置（Fitbit 智慧手環）收集羽球揮拍資訊，包括三軸加速度與三軸角速度，透過程式串接 Fitbit 提供的 API 即可輕鬆取得。與多數應用影像技術或在球拍嵌入晶片的既有研究相比，穿戴式裝置更具有隨手可得、操作便利的優勢。然而，目前尚缺乏以時間序列為基礎的聯邦學習（Federated Learning, FL）應用於羽球運動評分之研究，故本研究特別關注在「非獨立同分佈（non-iid）資料下的聯邦學習訓練」，以提升模型對實際使用者情境的適應性。
本研究旨在：（1）實際收集揮拍時間序列數據並標註五個面向的教練評分；（2）探討在此資料集中可能面臨的 non-iid 問題，並比較傳統聯邦學習（FedAvg）以及其他改良演算法（FedProx、FedBN、FedTS）在不同實驗情境下之表現；（3）提供各種增量式資料訓練分析，檢驗在初期資料有限、或客戶端分佈差異極大的真實情境中，如何利用蒸餾技術（Knowledge Distillation）與動態正則項（Proximal Term）等方式改善模型效能。最終，研究成果將去識別化後公開於網路上，期能成為未來進行運動數據科學研究之基礎。 In recent years, as the COVID-19 pandemic has gradually subsided, people have increasingly engaged in various outdoor activities. Among these, badminton has gained significant popularity in Taiwan, driven by Tai Tzu-ying's impressive performances in international competitions and the Olympic gold medal won by Lee Yang and Wang Chi-lin. The growing interest in badminton has led to a rising number of enthusiasts. According to surveys conducted by the Sports Administration of the Ministry of Education, one in three internet users employs wearable devices to track their fitness data, making wearable technology a prominent trend in sports science. This study leverages the characteristics of time-series data by collecting badminton stroke information using wearable devices (Fitbit smart bands), including tri-axial acceleration and tri-axial angular velocity. Through API integration provided by Fitbit, data can be effortlessly obtained. Compared to existing studies that primarily utilize imaging technology or embed sensors into rackets, wearable devices offer a more accessible and convenient solution. However, there is a lack of research applying Federated Learning (FL) based on time-series data for badminton performance scoring. This study focuses specifically on Federated Learning training under non-independent and identically distributed (non-iid) data to enhance model adaptability to real-world user scenarios. The objectives of this research are: (1) to collect real-time stroke time-series data and annotate them with coach evaluations across five dimensions; (2) to investigate the challenges of non-iid data in this dataset and compare the performance of traditional Federated Learning (FedAvg) with other advanced algorithms (FedProx, FedBN, FedTS) under different experimental scenarios; and (3) to analyze incremental data training, examining how techniques such as knowledge distillation and dynamic regularization (Proximal Term) can improve model performance in real-world scenarios with limited initial data or significant client distribution disparities. The research results, anonymized and de-identified, will be made publicly available online, aiming to serve as a foundation for future studies in sports data science. |
| 參考文獻 | 1] Fabrizio de Fabritiis and Konstantinos Gryllias. A federated learning approach for rolling bearing fault diagnosis on data sources with imbalanced class distribution. In Surveillance, Vibrations, Shock and Noise, 2023. [2] 王威堯 (Wei-Yao Wang), 張凱翔 (Kai-Shiang Chang), 陳霆峰 (Teng-Fong Chen), 王志全 (Chih-Chuan Wang), 彭文志 (Wen-Chih Peng), and 易志偉 (Chih-Wei Yi). Badminton coach ai：基於深度學習之羽球賽事資訊分析平台. 體育學報, 53(2):201–213, Jun 2020. [3] Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Agueray Arcas. Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics, pages 1273–1282. PMLR, 2017. [4] Peter Kairouz, H Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, et al. Advances and open problems in federated learning. Foundations and trends® in machine learning, 14(1–2):1–210, 2021. [5] Qinbin Li, Yiqun Diao, Quan Chen, and Bingsheng He. Federated learning on non-iid data silos: An experimental study. In 2022 IEEE 38th international conference on data engineering (ICDE), pages 965–978. IEEE, 2022. [6] Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. Federated optimization in heterogeneous networks. Proceedings of Machine learning and systems, 2:429–450, 2020. [7] Xiaoxiao Li, Meirui Jiang, Xiaofei Zhang, Michael Kamp, and Qi Dou. Fedbn: Federated learning on non-iid features via local batch normalization. arXiv preprint arXiv:2102.07623, 2021. [8] Geoffrey Hinton. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2015. [9] Tao Lin, Lingjing Kong, Sebastian U Stich, and Martin Jaggi. Ensemble distillation for robust model fusion in federated learning. Advances in neural information pro- cessing systems, 33:2351–2363, 2020. |
| Description | 碩士 國立政治大學 資訊科學系 111753214 |
| 資料來源 | http://thesis.lib.nccu.edu.tw/record/#G0111753214 |
| Type | thesis |
| dc.contributor.advisor | 蔡子傑 | zh_TW |
| dc.contributor.advisor | Tsai, Tzu-Chieh | en_US |
| dc.contributor.author (Authors) | 思沛淇 | zh_TW |
| dc.contributor.author (Authors) | Si, Pei-Qi | en_US |
| dc.creator (作者) | 思沛淇 | zh_TW |
| dc.creator (作者) | Si, Pei-Qi | en_US |
| dc.date (日期) | 2025 | en_US |
| dc.date.accessioned | 4-Feb-2025 15:44:28 (UTC+8) | - |
| dc.date.available | 4-Feb-2025 15:44:28 (UTC+8) | - |
| dc.date.issued (上傳時間) | 4-Feb-2025 15:44:28 (UTC+8) | - |
| dc.identifier (Other Identifiers) | G0111753214 | en_US |
| dc.identifier.uri (URI) | https://nccur.lib.nccu.edu.tw/handle/140.119/155455 | - |
| dc.description (描述) | 碩士 | zh_TW |
| dc.description (描述) | 國立政治大學 | zh_TW |
| dc.description (描述) | 資訊科學系 | zh_TW |
| dc.description (描述) | 111753214 | zh_TW |
| dc.description.abstract (摘要) | 近年來，隨著疫情逐漸趨緩，人們開始積極地投入各項戶外運動。其中，羽球運動因戴資穎在國際賽的亮眼表現，以及李洋、王齊麟勇奪奧運金牌，一時間成為臺灣運動愛好者的矚目焦點，帶動羽球運動人口持續攀升。根據教育部體育署相關調查，網路族群之中每三人便有一人使用穿戴式裝置紀錄運動數據；穿戴式裝置在運動科技領域已成為一種時尚趨勢。 本研究針對時間序列資料的特性，運用穿戴式裝置（Fitbit 智慧手環）收集羽球揮拍資訊，包括三軸加速度與三軸角速度，透過程式串接 Fitbit 提供的 API 即可輕鬆取得。與多數應用影像技術或在球拍嵌入晶片的既有研究相比，穿戴式裝置更具有隨手可得、操作便利的優勢。然而，目前尚缺乏以時間序列為基礎的聯邦學習（Federated Learning, FL）應用於羽球運動評分之研究，故本研究特別關注在「非獨立同分佈（non-iid）資料下的聯邦學習訓練」，以提升模型對實際使用者情境的適應性。 本研究旨在：（1）實際收集揮拍時間序列數據並標註五個面向的教練評分；（2）探討在此資料集中可能面臨的 non-iid 問題，並比較傳統聯邦學習（FedAvg）以及其他改良演算法（FedProx、FedBN、FedTS）在不同實驗情境下之表現；（3）提供各種增量式資料訓練分析，檢驗在初期資料有限、或客戶端分佈差異極大的真實情境中，如何利用蒸餾技術（Knowledge Distillation）與動態正則項（Proximal Term）等方式改善模型效能。最終，研究成果將去識別化後公開於網路上，期能成為未來進行運動數據科學研究之基礎。 | zh_TW |
| dc.description.abstract (摘要) | In recent years, as the COVID-19 pandemic has gradually subsided, people have increasingly engaged in various outdoor activities. Among these, badminton has gained significant popularity in Taiwan, driven by Tai Tzu-ying's impressive performances in international competitions and the Olympic gold medal won by Lee Yang and Wang Chi-lin. The growing interest in badminton has led to a rising number of enthusiasts. According to surveys conducted by the Sports Administration of the Ministry of Education, one in three internet users employs wearable devices to track their fitness data, making wearable technology a prominent trend in sports science. This study leverages the characteristics of time-series data by collecting badminton stroke information using wearable devices (Fitbit smart bands), including tri-axial acceleration and tri-axial angular velocity. Through API integration provided by Fitbit, data can be effortlessly obtained. Compared to existing studies that primarily utilize imaging technology or embed sensors into rackets, wearable devices offer a more accessible and convenient solution. However, there is a lack of research applying Federated Learning (FL) based on time-series data for badminton performance scoring. This study focuses specifically on Federated Learning training under non-independent and identically distributed (non-iid) data to enhance model adaptability to real-world user scenarios. The objectives of this research are: (1) to collect real-time stroke time-series data and annotate them with coach evaluations across five dimensions; (2) to investigate the challenges of non-iid data in this dataset and compare the performance of traditional Federated Learning (FedAvg) with other advanced algorithms (FedProx, FedBN, FedTS) under different experimental scenarios; and (3) to analyze incremental data training, examining how techniques such as knowledge distillation and dynamic regularization (Proximal Term) can improve model performance in real-world scenarios with limited initial data or significant client distribution disparities. The research results, anonymized and de-identified, will be made publicly available online, aiming to serve as a foundation for future studies in sports data science. | en_US |
| dc.description.tableofcontents | 第一章 Introduction 1 第一節 研究動機 1 第二節 研究目的 2 第三節 預期貢獻 3 第二章 Related work 5 第一節 聯邦學習 5 第二節 非獨立同分布數據對聯邦學習算法的影響 6 第三節 時間序列資料在非獨立同分布下的挑戰 9 第四節 聯邦學習中解決 non-iid 的方法：FedProx 9 第五節 聯邦學習中解決 non-iid 的方法：FedBN 10 第六節 知識蒸餾（Knowledge Distillation） 12 第三章 Methods 15 第一節 收集羽毛球六軸時間序列資料集並標註資料集 15 第二節 時間序列資料特徵提取──羽球擊球區間選擇 16 第二之一小節 判斷揮拍有效性 18 第三節 聯邦學習流程設計 19 第三之一小節 資料分割與前處理 19 第三之二小節 LSTM模型架構與訓練目標 20 第三之三小節 結合知識蒸餾(KnowledgeDistillation) 21 第三之四小節 FedTS之動態正則化機制 22 第三之五小節 本地訓練與動態學習率 23 第三之六小節 資料增強(DataAugmentation) 23 第三之七小節 逐量增加資料(IncrementalTraining)之聯邦蒸餾與評估標準 23 第三之八小節 小結 24 第四章 Experiments 26 第一節 實驗環境與參數設置 26 第二節 實驗數據集 27 第三節 教師模型的選擇 28 第四節 實驗結果 30 第四之一小節 實驗結果（iid分布，2Clients） 30 第四之二小節 Case2（4Clients，數量不平衡，比例為50%、25%、12.5%、12.5%） 32 第四之三小節 Case3（2Clients，non-iid，高分群vs.低分群） 34 第四之四小節 Case4（3Clients，其中1客戶端標籤隨機） 36 第五章 Conclusions and Future Work 38 第一節 結論 38 第二節 未來展望 39 Reference 42 | zh_TW |
| dc.format.extent | 2612759 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.source.uri (資料來源) | http://thesis.lib.nccu.edu.tw/record/#G0111753214 | en_US |
| dc.subject (關鍵詞) | 聯邦學習 | zh_TW |
| dc.subject (關鍵詞) | 非獨立同分佈 | zh_TW |
| dc.subject (關鍵詞) | 時間序列資料 | zh_TW |
| dc.subject (關鍵詞) | 穿戴式裝置 | zh_TW |
| dc.subject (關鍵詞) | 知識蒸餾 | zh_TW |
| dc.subject (關鍵詞) | Federated Learning | en_US |
| dc.subject (關鍵詞) | Non-iid | en_US |
| dc.subject (關鍵詞) | Time-series Data | en_US |
| dc.subject (關鍵詞) | Wearable Devices | en_US |
| dc.subject (關鍵詞) | Knowledge Distillation | en_US |
| dc.title (題名) | FedTS：基於時間序列聯邦學習的羽球揮拍評分 | zh_TW |
| dc.title (題名) | FedTS: Federated Learning Based on Time Series For Scoring Badminton Strokes | en_US |
| dc.type (資料類型) | thesis | en_US |
| dc.relation.reference (參考文獻) | 1] Fabrizio de Fabritiis and Konstantinos Gryllias. A federated learning approach for rolling bearing fault diagnosis on data sources with imbalanced class distribution. In Surveillance, Vibrations, Shock and Noise, 2023. [2] 王威堯 (Wei-Yao Wang), 張凱翔 (Kai-Shiang Chang), 陳霆峰 (Teng-Fong Chen), 王志全 (Chih-Chuan Wang), 彭文志 (Wen-Chih Peng), and 易志偉 (Chih-Wei Yi). Badminton coach ai：基於深度學習之羽球賽事資訊分析平台. 體育學報, 53(2):201–213, Jun 2020. [3] Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Agueray Arcas. Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics, pages 1273–1282. PMLR, 2017. [4] Peter Kairouz, H Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, et al. Advances and open problems in federated learning. Foundations and trends® in machine learning, 14(1–2):1–210, 2021. [5] Qinbin Li, Yiqun Diao, Quan Chen, and Bingsheng He. Federated learning on non-iid data silos: An experimental study. In 2022 IEEE 38th international conference on data engineering (ICDE), pages 965–978. IEEE, 2022. [6] Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. Federated optimization in heterogeneous networks. Proceedings of Machine learning and systems, 2:429–450, 2020. [7] Xiaoxiao Li, Meirui Jiang, Xiaofei Zhang, Michael Kamp, and Qi Dou. Fedbn: Federated learning on non-iid features via local batch normalization. arXiv preprint arXiv:2102.07623, 2021. [8] Geoffrey Hinton. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2015. [9] Tao Lin, Lingjing Kong, Sebastian U Stich, and Martin Jaggi. Ensemble distillation for robust model fusion in federated learning. Advances in neural information pro- cessing systems, 33:2351–2363, 2020. | zh_TW |