準點率對於採行公告班表的鐵路系統，是影響顧客滿意度的重要因子，而在不增加基礎設施與服務人員的條件下，提高系統的可靠度(準點率)是一個有效提升滿意度及低成本的做法，故解決延誤進而提高準點率遂變成目前軌道運輸議題上很重要的主題。以台鐵系統為例，在多車種、雙單線系統運轉及多類型月臺型式的狀況下，其交互作用之影響更為錯綜複雜，營運單位很難掌握延誤的關鍵因素，若能有效的釐清延誤發生的原因及其交互作用，將可以確實掌握其對運轉時隔之衝擊，進而提升列車營運之可靠度與服務品質。
由於台鐵紀錄延誤事件的特性，導致很難透過資料掌握延誤的關鍵因素，故本研究透過機器學習方法中，C4.5監督式決策樹技術來推估完整延誤紀錄，再藉由邏輯分析會讓行為，並將其推估結果利用本研究設計方法尋找誤點關鍵影響延誤因素，最後頻率篩選挑出可藉由班表調整解決之延誤因子，研究成果可作為後續營運單位排班規劃、系統可靠度分析及服務品質改善之參考。

With published timetables in railway system, punctuality is an important factor which effects degree of customer satisfaction. Promoting the system Reliability (punctuality) is an effective and low-cost method without adding any infrastructure and staff. Therefore, it’s important to resolve delay problems for promoting punctuality in railway transportation. In the case of Taiwan railway administration (TRA), it is complicated to release the key factors in traditional railway system with multiple service type, single-double track and multiple types of platform. If the delay reasons and the interactions among the delay factors can be clearly clarified, the impacts of headway can be exactly handled. Furthermore, reliability and service quality of railway operation can be enhanced.
Due to the record characteristics of delay events in TRA, it is difficult to catch the key factors of delay reasons by historical data. The study adopts a supervised decision tree method in machine learning techniques, which is named C4.5, to estimate the key factors of delay. In this study, a delay root cause mining method is designed to discover the root cause delay factor by logic analyzing the trains waiting behavior which is caused by scheduled or un-scheduled meetings and overtaking. The delays can be resolved by the adjustment of timetable, and discovered by frequency filtering which would be an important reference for the next timetable rescheduling. The result of this study can be applied as a reference for the railway system, especially in timetable rescheduling, system reliability analysis and service quality improvements.

英文文獻
1. Association of Train Operating Companies(2005),Passenger Demand Forecasting Handbook, London: Association of Train Operating Companies.
2. Berry, M. J., & Linoff, G.(1997), Data Mining Techniques: For Marketing, Sales, and Customer Support, New York: John Wiley and Sons Inc.
3. Breiman, L., Friedman, J., Stone, C. J., & Olshen, R. A.(1984), Classification and Regression Trees. USA: Chapman and Hall.
4. Bai, Y., Ho, T., & Mao, B.(2011), “Train Control to Reduce Delays upon Service Disturbances at Railway Junctions,” Journal of Transportation Systems Engineering and Information Technology, 11(5) pp.114~122.
5. Carey, M.(1999), “Ex ante Heuristic Measures of Schedule Reliability,” Transportation Research Part B, Vol. 33, pp.473~494.
6. Carey, M. and Carville, S.(2000), “Testing Schedule Performance and Reliability for Train Stations”, Journal of the Operational Research Society, Vol. 51, pp.666~682.
7. Chen, I.-C., Hsu, S.-K., Wu, T.-J., Yen, L.-H., Lee, Y., Lin, D.-Y., Chen, C.-Y., Lee, W.-H. and Su, G.-W. (2013), “RDSP: A Railway Decision Support Platform for Integrating and Bridging Existed Legacy Systems,” Joint Railway Conference 2013, Knoxville, Tennessee, USA.
8. Colak, I., Sagiroglu, S., & Yesilbudak, M.(2012), “Data mining and wind power prediction: A literature review,” Renewable Energy, 46(0) pp.241~247.
9. Fayyad, U., Piatetsky-Shapiro, G., & Smyth, P. (1996), “From Data Mining to Knowledge Discovery in Databases,” AI Magazine, 17(3) pp.37~54.
10. Gorman, M. F.(2009), “Statistical estimation of railroad congestion delay,” Transportation Research Part E: Logistics and Transportation Review, 45(3) pp.446~456.
11. Grupe, F. H., & Mehdi Owrang, M.(1995), “DATA BASE MINING Discovering New Knowledge and Competitive Advantage,” Information Systems Management, 12(4) pp.26~31.
12. Higgins, A., & Kozan, E.(1998), “Modeling train delays in urban networks,” Transportation Science, 32(4) pp.346~357.
13. Lee, Y., & Chen, C.-Y.(2009), “A heuristic for the train pathing and timetabling problem,” Transportation Research Part B: Methodological, 43(8–9) pp.837~851.
14. Lindner, T., & Zimmermann, U. T.(2000), “Train schedule optimization in public rail transport,” Mathematics¡XKey Technology for the Future: Joint Projects Between Universities and Industry, pp.703~716.
15. McCluskey, W., & Anand, S.(1999). “The application of intelligent hybrid techniques for the mass appraisal of residential properties,” Journal of Property Investment and Finance, 17(3) pp.218~238.
16. Olmeda, I., & Sheldon, P. J.(2001), “Data Mining Techniques and Applications for Tourism Internet Marketing,” Journal of Travel & Tourism Marketing, 11(2-3) pp.1~20.
17. Olsson, N.O.E, Haugland, H.(2004), “Influencing factors on train punctuality – results from some Norwegian studies,” Transport Policy, 11(4) pp.387~397.
18. Quinlan, J. R. (1993), C4.5: programs for machine learning, Morgan : Kaufmann Publishers Inc.
19. Pal, M., & Mather, P. M.(2003), “An assessment of the effectiveness of decision tree methods for land cover classification,” Remote Sensing of Environment, 86(4) pp.554~565.
20. Salido, M. A., & Barber, F.(2009), “Mathematical Solutions for Solving Periodic Railway Transportation,” Mathematical Problems in Engineering.
21. Tyrinopoulos, Y., & Antoniou, C.(2008), “Public transit user satisfaction: Variability and policy implications,” Transport Policy, 15(4) pp.260~272.
22. Weigand, W.(1981), “Verspatungsubertragungen in Fernverkehrsnetzen,” Eisenbahntechnische Rundsch, 30 (12) pp.915~920.
23. Yuan, J. and Hansen, I. A.(2007), “Optimizing Capacity Utilization of Stations by Estimating Knock-on Train Delays,” Transportation Research Part B, Vol. 41, pp.202~217.

中文文獻
24. 張正興(民83)，「利用績效函數進行系統可靠度分析之研究─以軌道運輸系統的的誤點事件為例」，國立交通大學工業工程研究所碩士論文。
25. 吳美玲(民100)，「列車班表之穩定化」，國立成功大學交通管理學系碩士論文。
26. 謝興盛(民92)，「捷運列車延誤時班距調整模式之模擬分析-以台北捷運中、高運量系統為例」，國立成功大學交通管理學系博士論文。
27. 劉昭榮(民99)，「鐵路列車連鎖延滯之模擬模式構建與應用」，國立交通大學交通運輸研究所博士論文。
28. 陳心一(民98)，「台鐵對號列車延誤預測之研究」，國立成功大學交通管理學系碩士論文。
29. 張淑珍(民94)，「利用一次性SQL改良決策樹建立信用卡審核之信用評等」，私立東吳大學資訊科學系碩士論文。