公車車輛聚集（Bus Bunching）指相同公車路線上，有兩輛以上的公車同時到達公車站牌。這樣的現象常出現在高頻率的市區公車路線，而且會對公車服務造成負面影響。時間序列式樣探勘（Temporal Sequential Pattern Mining）指將資料點按發生時間的先後順序排列、並找出其循序式樣，此方法原應用於分析消費者的時間連續性購物內容，而本論文將此方法應用在連續的公車到站時間紀錄上，用以分析公車班距離群值的分布情況。
作者為研究公車車輛聚集現象，以收集臺北市307公車路線之車輛軌跡資料為例，提出資料收集、車次編碼、補足中斷資料及計算行車間距等方法，並對這些處理過的資料進行分組、找出資料的離群值，接著進行時間序列式樣探勘、再找出與離群值有關聯的時間序列頻繁項目。我們選擇該路線上其中9個站牌作為觀測點，探討其行車班距離群值的分布情形，找出公車車輛聚集的時間序列式樣，並對前後一個觀察站的班距進行分析。
實驗結果顯示我們能利用探勘時間序列離群值，找出公車聚集現象的相關時間序列，且不論對長程或短程公車路線，本文提出之方法皆可用於識別路線上的公車聚集現象，找出特定的離群值序列式樣。未來則希望能接續此研究，找出離群值產生的原因。

“Bus Bunching” phenomenon, which implies more than one bus arrive at a bus stop simultaneously, often occurs on high-frequency bus routes and causes negative effects on bus services. In order to identify and analyze bus bunching, we take a high frequency bus service case – Route 307 in Taipei City for study.
“Temporal Sequential Pattern Mining” means arranging data points into time orders and mining their sequential patterns. The method was used as mining consumer’s continuous shopping record previously, whereas this thesis applied it to analyze headway outliers of buses.
We chose 9 bus stops on the specific bus route for observation. Based on the observations, we discussed the distribution of headway outliers, found the bus bunching patterns, and analyzed the neighbor stops of outliers. After collecting the Automatic Vehicle Location data, we proposed the following methods for data preprocessing. And they are trip encoding, detecting data interruption, filling the interrupt data, and counting headways between two adjacent buses. Then, we divided the data into 5 groups by its headway, and distinguished outliers from the data. Finally, we utilized AprioriAll algorithm to mine sequential patterns, and found the frequent patterns that corresponded to time sequence outliers.
Expermental results showed that the specific patterns “S6→S2,” and “S2→S6” are likely to be the bus bunching patterns. Compared to previous studies, our method distinguishes the headway outliers by boxplot, and implements sequential pattern mining algorithm. We not only find out frequent sequential patterns, but also recognize the place where bus bunching occurred.

謝辭　　i
顯著聲明　　ii
摘要　　iii
Abstract　　iv
第一章　緒論　　1
第二章　文獻回顧　　3
2.1　公車車輛聚集（Bus Bunching）　　3
2.2　序列式樣探勘（Sequential Pattern Mining）　　5
第三章　問題定義　　6
3.1　公車車輛集中問題　　6
3.2　資料前處理問題　　8
3.3　時間序列式樣探勘　　9
3.4　實驗流程說明　　9
第四章　實驗模型與架構　　11
4.1　資料收集模型與資料型態　　11
4.2　車次編碼及排序模型　　13
4.3　偵測並補足中斷資料　　14
4.4　計算車輛到站時間間隔與分組　　18
4.5　探勘頻繁時間序列模型　　20
第五章　實驗結果與討論　　22
5.1　應用系統與資料集　　22
5.2　按行車間距四分位數分組結果　　22
5.3　頻繁之時間序列　　25
5.4　討論　　29
5.5　在短程路線的表現　　30
第六章　結論與未來展望　　34
第七章　參考文獻　　35

[1]M. Andres, and R. Nair, “A predictive-control framework to address bus bunching,” Transportation Research Part B: Methodological, Vol. 104, pp.123-148, 2017.
[2]王穆衡、李霞，〈公共運輸整合資訊流通服務平臺發展現況〉，輔具之友，第44期，頁29-34，臺北市：衛生福利部社會及家庭署，ISSN：1814-4829，2019年6月。
[3]王穆衡、李霞、王國琛、陳信邦、江長穎、吳怡潔、郭姿岑，〈公共運輸整合資訊流通服務平臺發展〉，土木水利，第45卷，第2期，頁4-17，臺北市：中國土木水利工程學會，ISSN：0253-3804，2018年4月。
[4]S. J. Berrebia, S. Óg Crudden, and K. E. Watkinsa, “Translating research to practice: Implementing real-time control on high-frequency transit routes,” Transportation Research Part A: Policy and Practice, Vol. 111, pp.213-226, 2018.
[5]L. Moreira-Matias, O. Cats, J. Gama, J. Mendes-Moreira, and J. F. Sousafg, “An online learning approach to eliminate Bus Bunching in real-time,” Applied Soft Computing, Vol. 47, pp.460-482, 2016.
[6]C. Iliopoulou, C. Milioti, E. Vlahogianni, K. Kepaptsoglou, and J. Sánchez–Medina, “The Bus Bunching Problem: Empirical Findings from Spatial Analytics,” in 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, Hawaii, United States, 2018.
[7]W. Feng, and M. A. Figliozzi, “Using Archived AVL/APC Bus Data to Identify Spatial-Temporal Causes of Bus Bunching,” in Transportation Research Board 90th Annual Meeting, Washington DC, United States, 2011.
[8]J. J. Bartholdi III, and D. D.Eisenstein, “A self-coördinating bus route to resist bus bunching,” Transportation Research Part B: Methodological, Vol. 46, Issue 4, pp.481-491, 2012.
[9]A. Li, M. Feng, Y. Li, and Z. Liu, “Application of outlier mining in insider identification based on Boxplot method,” in Information Technology and Quantitative Management (ITQM), 2016.
[10]J. L. Devore, Probability Statistics for Engineering and the Sciences, 8th ed., Brooks/Cole (Cengage Learning), 2012, pp. 39-41.
[11]K. Gkiotsalitis, and E.C. van Berkum, “An exact method for the bus dispatching problem in rolling horizons,” Transportation Research Part C: Emerging Technologies, Vol. 110, pp.143–165, 2020.
[12]M.-B. Hu, M. D. Simoni, and C. G. Claudel, “Modeling bus bunching: A comprehensive approach accounting for transit demand and traffic flows,” 21st International Conference on Intelligent Transportation Systems (ITSC), 2018.
[13]I. Gokasar, and Y. Cetinel, “A New Strategy For The Diagnosis Of The Bus Headways Using AVL Data,” 6th International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS), 2019.
[14]M V. Koppisetti, V. Kavitha, and U. Ayesta, “Bus schedule for optimal bus bunching and waiting times,” in 10th International Conference on Communication Systems & Networks (COMSNETS), Bengaluru, India, 2018.
[15]W. Leong, Karen Goh, S. Hess, and P. Murphy, “Improving bus service reliability: The Singapore experience,” Research in Transportation Economics, Vol. 59, pp.40-49, 2016.
[16]S. Rashidi, P. Ranjitkar, O. Csaba, and A. Hooper, “Using Automatic Vehicle Location Data to Model and Identify Determinants of Bus Bunching,” in World Conference on Transport Research (WCTR), Shanghai, China, 2016.
[17]C. F. Daganzo, and J. Pilachowski, “Reducing bunching with bus-to-bus cooperation,” Transportation Research Part B: Methodological, Vol. 45, Issue 1, pp.267-277, 2011.
[18]S.-X. He, S.-D. Liang, J. Dong, D. Zhang, J.-J. He, and P.-C. Yuan, “A holding strategy to resist bus bunching with dynamic target headway,” Computers & Industrial Engineering, 2019.
[19]W. Wu, R. Liu, and W. Jin, “Modelling bus bunching and holding control with vehicle overtaking and distributed passenger boarding behaviour,” Transportation Research Part B: Methodological, Vol. 104, pp.175-197, 2017.
[20]W.-Y. Chen, “Fixed-Route High-Frequency Bus Service Reliability Considering Bus Overtaking and No-overtaking,” International Conference on Transportation, Mechanical, and Electrical Engineering (TMEE), 2011.
[21]A. Petit, C. Lei, and Y. Ouyang, “Multiline Bus Bunching Control via Vehicle Substitution,” Transportation Research Part B: Methodological, Vol. 126, pp.68-86, 2019.
[22]N. B. Hounsell, F. N. McLeod, K. Gardner, J. R. Head, and D. Cook, “Headway-based bus priority in London using AVL: first results,” Tenth International Conference on Road Transport Information and Control, 2000.
[23]L. Meegahapola, N. Athaide, K. Jayarajah, S. Xiang, and A. Misra, “Inferring Accurate Bus Trajectories from Noisy Estimated Arrival Time Records,” in IEEE Intelligent Transportation Systems Conference (ITSC), Auckland, New Zealand, 2019.
[24]A. Bessa, F. d. M. Silva, R. F. Nogueira, E. Bertini, and J. Freire, “RioBusData: Outlier Detection in Bus Routes of Rio de Janeiro,” in Symposium on Visualization in Data Science (VDS), Chicago, Illinois, United States, 2015.
[25]R. Agrawal, and R. Srikant, “Mining sequential patterns,” in 11th International Conference on Data Engineering, Taipei, Taiwan, 1995.
[26]J. Han, J. Pei, B. Mortazavi-Asl, Q. Chen, U. Dayal, and M-C.Hsu, “FreeSpan: Frequent Pattern-projected Sequential Pattern Mining,” Proceedings of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Boston, MA, United States, 2000.
[27]J. Pei, J. Han, B. Mortazavi-asl, H. Pinto, Q. Chen, U. Dayal, and M.-C. Hsu, “PrefixSpan: Mining Sequential Patterns Efficiently by Prefix-Projected Pattern Growth,” in 17th International Conference on Data Engineering, Heidelberg, Germany, 2001.
[28]J. Pei et al., “Mining Sequential Patterns by Pattern-Growth: The PrefixSpan Approach,” IEEE Transactions on Knowledge and Data Engineering, Vol. 16, No. 11, pp.1424-1440, 2004.
[29]Taipei City Hall & New Taipei City Hall, “Taipei eBus,” 2014. [Online]. Available: https://ebus.gov.taipei/Route/StopsOfRoute?routeid=0100030700. [Accessed: 01- Jan- 2020].
[30]江長穎、吳怡潔，《交通部公共運輸旅運資料標準》，第二版，臺北市：中華民國交通部，2017年12月。
[31]Ministry of Transportation and Communications (Taiwan), “PTX API Documentation,” 2016. [Online]. Available: https://ptxmotc.gitbooks.io/ptx-api-documentation/. [Accessed: 23- Dec- 2019].