近年來，人們對於休閒運動是更加重視，而自行車運動就是一個非常受歡迎的運動。自行車公路團體計時賽則是國際運動賽事中的一項活動，自行車公路賽的表現取決於比賽的騎行策略，如何最少化整體完成比賽的時間是一個值得探討的問題。隨著科技的進步，行動運算具備提供資訊處理及通訊的能力，對於其嵌入的對象有著深遠的影響。此項技術特可應用於監控車手的疲勞及提高能量效率。
本研究基於網宇實體系統(Cyber Physical System, CPS)的分層式架構所設計，提出一自行車公路賽建議系統，其中包含實體層及虛擬層。在實體層中，心率感測器及肌電感測器配置在嵌入式系統中，負責將感測資料轉為車手疲勞指標；在虛擬層中，主要採用電腦負責監測實體層的車手狀態及發展出最佳的騎行策略。本研究利用代理人的方法將每位車手建構為一個代理人，並對系統及代理人平台進行溝通。基於車手的及時生理狀態產生一個最佳的比賽策略，在比賽期間，建議車手輪替交換騎行位置的時機，藉以縮短完賽時間，達到最小化的目標。
本研究的目的是探討如何建構及規劃基於網宇實體系統的自行車公路賽整體建議系統，藉由模擬分析呈現所設計之系統的可行性。實驗結果顯示，最佳化演算可以優於目前車隊所使用的最新策略。

In recent years, people pay more attention to leisure sports. Cycling is a very popular sport. The road cycling team time trial(TTT) is one of the events in international sports competitions. Road cycling performance is dependent on race tactics and pacing strategy. To minimize the overall time that a team of cyclists needs to complete a race is an interesting real-world problem. With the progress of technology, mobile computing has far-reaching impacts the object in which they are embedded and provide it with information processing and communication capabilities. It promises to monitor the fatigue of the cyclist and to improve power efficiency.
In this research, a road cycling race suggestion system is presented. The proposed hierarchical framework is designed based on the Cyber Physical System, which includes physical level and virtual level. In the physical level, heart rate sensors and electromyogram(EMG) sensors are deployed in an embedded system, which transforms sensor data into fatigue index. In the virtual level, the main computer is employed to monitor the status of the physical layer and generates an optimal pacing strategy. Using an agent-based approach, each rider is represented as an agent and communicates with the system on the agent platform. An optimization race tactics is generated based on rider’s real time physiological status, then cyclists have to change their position within the team during the race in order to minimize the overall time.
The purpose of this study is to explore how to construct and plan the whole system of road cycling race based on the Cyber Physical System. The feasibility of the designed system is presented by the simulation analysis. The experimental results show that the optimal heuristics lead to better strategies than state-of-art strategies that are currently used by teams of cyclists.

摘要..........i
Abstract..........iii
誌謝..........v
目錄..........vi
表目錄..........ix
圖目錄..........x
第一章 緒論..........1
1.1 研究背景..........2
1.2 研究目的..........4
1.3 論文架構..........5
第二章 文獻探討..........7
2.1 自行車公路賽..........7
2.2 網宇實體系統..........11
2.3 多代理人系統..........15
2.4 運動疲勞..........18
2.4.1 肌電圖(Electromyography, EMG)..........18
2.4.2 心率(Heart Rate, HR)..........19
2.5 模糊理論..........20
第三章 自行車公路團體計時賽建議系統..........24
3.1 系統規劃..........24
3.1.1 系統分層架構..........24
3.1.2 系統配置..........25
3.1.3 硬體架構..........26
3.1.4 系統開發工具..........27
3.2 感測系統..........30
3.3 車手疲勞指標分析系統..........32
3.3.1 有氧疲勞..........32
3.3.2 無氧疲勞..........35
3.4 車手疲勞指標預測模型..........38
3.5 決策模型..........41
3.5.1 問題定義..........41
3.5.2 控制變數演算..........42
3.5.3 粒子群演算法..........44
第四章 實驗設計與結果分析..........48
4.1 車手疲勞模型實驗..........48
4.2 建議系統模擬實驗設計..........57
4.2.1 模擬實驗一：車手個人因子固定..........59
4.2.2 模擬實驗二：車手個人因子不等..........61
4.3 代理人平台實作..........65
第五章 結論及未來展望..........67
5.1 結論..........67
5.2 未來展望..........68
參考文獻..........69
Extended Abstract..........72

[1]cycling-update, 5大類公路車手分析。Retrieved from http://www.cycling-update.info
[2]Teodora Sanislav, Liviu Miclea, 2012, “Cyber-Physical System – Concept, Challenges and Research Areas”, CEAI, Vol.14, No.2, pp. 28-33
[3]Baike Baidu, 公路自行車賽。Retrieved from https://baike.baidu.com
[4]Markus Wagner, 2011, “Evolving Pacing Strategies for Team Pursuit Track Cycling”, The IX Metaheuristics International Conference
[5]李育萱，2015，"訓練衝量與臨界功率對自由車運動表現之探討"，國立臺灣體育運動大學競技運動學系研究所碩士論文
[6]Ragunathan Raj Rajkumar, Insup Lee, Lui Sha, John A. Stankovic, 2010, “Cyber-Physical Systems: The Next Computing Revolution”, Proceedings of the 47th Design Automation Conference(DAC)
[7]Liang Hu, Nannan Xie, Zhejun Kuang, Kuo Zhao, 2010, “Review of Cyber-Physical System Architecture”, IEEE 15th International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing Workshops
[8]Dragos Repta, Aurelian Mihai Stanescu, Mihnea Alexandru Moisescu, Monika Benea, 2014, “A cyber-physical systems approach to develop a generic enterprise architecture”, International Conference on Engineering, Technology and Innovation (ICE)
[9]Hyun Jung La, Soo Dong Kim, 2012, “A Service-Based Approach to Designing Cyber Physical Systems”, 9th IEEE/ACIS International Conference on Computer and Information Science
[10]Jietao Dong, Tianyuan Xiao, Linxuan Zhang, 2012, “A Prototype Architecture for Assembly-Oriented Cyber-Physical Systems”, AsiaSim 2012 pp 199-204
[11]Jay Lee, Behrad Bagheri, Hung-AnKao, 2015, “A Cyber-Physical Systems architecture for Industry 4.0-based manufacturing systems”, Manufacturing Letters Volume 3, January 2015, Pages 18-23
[12]PingGuo, Puwadol Dusadeeringsikul, Shimon Y.Nof, 2018, “Agricultural cyber physical system collaboration for greenhouse stress management”, Computers and Electronics in Agriculture, Volume 150, Pages 439-454
[13]黃恩澤，2017，"應用網宇實體系統概念建構智慧型蛋雞場"，建國科技大學電機工程系暨研究所碩士論文
[14]Michael Wooldridge, Nicholas R. Jennings, 1995, “Intelligent Agents: Theory and Practice”, The Knowledge Engineering Review, Vol. 10, No. 02, pp. 115-152
[15]Hyacinth S. Nwana, 1996, “Software agents: An overview”, The Knowledge Engineering Review, Vol. 11, No. 03, pp. 205-244
[16]廖偉倫，2009，"結合RFID技術建構廠區控制代理人系統"，國立虎尾科技大學機械與機電工程研究所碩士論文
[17]E.M. Ratamero, 2011, “An agent-based model for peloton dynamics in competitive cycling”, Erasmus Mundus Masters in Complex Systems Science
[18]L. Chaimowicz, M.F.M. Campos, V. Kumar, 2002, “Dynamic role assignment for cooperative robots”, IEEE International Conference on Robotics and Automation
[19]Yang Wang, C. W. de Silva, 2005, “An object transportation system with multiple robots and machine learning”, American Control Conference, Vol. 2, pp. 1371-1376
[20]R Porter, J Whelan (Eds.), 1981, “Human Muscle Fatigue: Physiological Mechanisms”, Pitman Medical, London, pp. 1-18
[21]P. A. Merton, 1954, “Voluntary strength and fatigue”, The Journal of Physiology, Volume 123, Issue 3, pp. 553-564
[22]Angkoon Phinyomark, Chusak Limsakul, Pornchai Phukpattaranont, 2009, “A Novel Feature Extraction for Robust EMG Pattern Recognition”, Journal of Computing, Volume 1, Issue 1, pp 71-80
[23]Stanley Cobb, Alexander Forbes, 1923, “Electromyographic studies of muscular fatigue in man”, American Journal of Physiology-Legacy Content, Volume 65, Issue 2, pp 234-251
[24]Borg, G.A.,1982, “Psychophysical bases of perceived exertion” Med Sci Sports Exerc, 14(5): pp. 377-381.
[25]L.A.Zadeh, 1965, “Fuzzy sets”, Information and Control
Volume 8, Issue 3, Pages 338-353.
[26]林俊良，2008，智慧型控制: 分析與設計 (修訂版)，全華圖書股份有限公司
[27]L.A.Zadeh, 1975, “The concept of a linguistic variable and its application to approximate reasoning—I”, Information Sciences Volume 8, Issue 3, Pages 199-249
[28]Jade, Tutorials & Guides, Retrieved http://jade.tilab.com
[29]TAIWANIOT, MAX30100, Retrieved from https://www.taiwaniot.com.tw
[30]TAIWANIOT, Grove-EMG Detector, Retrieved from https://www.taiwaniot.com.tw
[31]Alwin Luttmann, Matthias JaKger, Wolfgang Laurig , 2000, “Electromyographical indication of muscular fatigue in occupational field studies”, International Journal of Industrial Ergonomics 25 645-660
[32]J. Kennedy and R. C. Eberhart, 1995, “Particle swarm optimization,” IEEE, pp. 1942-1948