大眾捷運系統(MRT) 在運量穩定成長的情況之下，同時隨著捷運路網的擴建，路網逐漸複雜化，乘客搭乘的區段選擇越來越多樣，對於列車營運計畫的準確度只會隨著路網的複雜程度，導致站間量的準確度逐漸下降。因此本研究利用行動定位服務中的手機信令資料，建立乘客在臺北捷運移動區段模型，將乘客手機信令資料判讀為乘客的移動區段，透過信令資料建立尖峰時段的捷運站間量了解旅客乘車需求。
本研究透過手機信令資料蒐集計畫獲得真實的信令資料，將實際的信令資料經過處理，速度基礎法、型態基礎法與基於HMM隱馬可夫模型的地圖匹配，以及匹配路網後，透過路網資訊的合理路徑集合判斷，建立移動區段模型，利用移動區段模型產出乘客移動區段資料，將乘客移動區段資料轉換成乘客移動區段比例與捷運電子票證OD資料結合，獲得信令資料的捷運尖峰站間量。
信令資料建立的尖峰站間量與目前臺北捷運站間量相比，人流變化更多乘客選擇在忠孝復興進行轉乘，而非南京復興站，因南京復興站需要花費大量的轉乘時間，松山新店線與臺北車站周圍的搭乘選擇則可以觀察到松山新店線的中正紀念堂站至中山站之間真實人流更傾向主要幹道，而非以臺北車站四周的綠線。乘客在搭乘捷運進入三重與蘆洲區域更多選擇往台北車站方向搭乘，導致松江南京至大橋頭方向在站間量被低估，同時信令資料建立的尖峰小時站間量在臺北大眾捷運股份有限公司系統服務指標中的舒適度計算中，臺北捷運都保有足夠的乘載量，預留充裕的舒適度。

The Mass Rapid Transit (MRT) system is steadily expanding its network, leading to increased complexity in the road network and diversification in passenger routes. As the network grows more intricate, the accuracy of train operation planning gradually diminishes.
In this study, sighting data underwent preprocessing using a collection plan that included velocity-based, type-based methods, Hidden Markov Models (HMM), and alignment with the road network. This process converted movement segment data into passenger movement segment ratios. These ratios, combined with MRT E-ticket Origin-Destination (OD) data, facilitated the determination of peak inter-station volumes for the MRT.
Compared to the current station-to-station volumes on the Taipei Metro, peak hour data derived from signaling information reveals a shift in passenger flow, with more passengers opting to transfer at Zhongxiao Fuxing Station rather than at Nanjing Fuxing Station. This shift occurs because transferring at Nanjing Fuxing Station takes significantly more time.
On the Songshan-Xindian Line and in the vicinity of Taipei Main Station, it is observed that real passenger flow between Zhongzheng Memorial Hall Station and Zhongshan Station leans more toward the main routes rather than the green line around Taipei Main Station. Passengers traveling towards the Sanchong and Luzhou areas often board trains heading in the direction of Taipei Main Station, leading to an underestimation of passenger volume in the direction from Songjiang Nanjing to Daqiaotou.
Despite these observations, peak hour station-to-station volumes derived from signaling data indicate that the Taipei Metro system maintains adequate capacity and offers ample comfort, ensuring a pleasant riding experience.

參考文獻
[1] 陳惠國，2021，運輸規劃-基礎與進階，國立中央大學土木工程學系，桃園市。
[2] 交通部運輸研究所著，2017.12，台北區域整體運輸規劃－旅次特性調查與供需分析。
[3] Aguiléra, V., Allio, S., Benezech, V., Combes, F., & Milion, C., 2014. Using cell phone data to measure quality of service and passenger flows of Paris transit system. Transportation Research Part C: Emerging Technologies, 43, 198-211.
[4] Alexander, L., Jiang, S., Murga, M., & González, M. C., 2015. Origin–destination trips by purpose and time of day inferred from mobile phone data. Transportation Research Part C: Emerging Technologies, 58, 240-250.
[5] Bonnetain, L., Furno, A., El Faouzi, N. E., Fiore, M., Stanica, R., Smoreda, Z., & Ziemlicki, C., 2021. TRANSIT: Fine-grained human mobility trajectory inference at scale with mobile network sighting data. Transportation Research Part C: Emerging Technologies, 130, 103-257.
[6] Calabrese, F., Diao, M., Di Lorenzo, G., Ferreira Jr, J., & Ratti, C., 2013. Understanding individual mobility patterns from urban sensing data: A mobile phone trace example. Transportation research part C: emerging technologies, 26, 301-313.
[7] Chen, C., Bian, L., & Ma, J., 2014, From traces to trajectories: How well can we guess activity locations from mobile phone traces. Transportation Research Part C: Emerging Technologies, 46, 326-337.
[8] Chen, H. K., Ho, H. C., Wu, L. Y., Lee, I., & Chou, H. W., 2024. Two-stage procedure for transportation mode detection based on sighting data. Transportmetrica A: transport science, 20(1), 2118558.
[9] De Montjoye, Y. A., Hidalgo, C. A., Verleysen, M., & Blondel, V. D., 2013. Unique in the crowd: The privacy bounds of human mobility. Scientific reports, 3(1), 1-5.
[10] Holleczek, T., Yu, L., Lee, J. K., Senn, O., Ratti, C., & Jaillet, P., 2014. Detecting weak public transport connections from cellphone and public transport data. In Proceedings of the 2014 International Conference on Big Data Science and Computing , 1-8.
[11] Hsueh, Y. L., Chen, H. C., & Huang, W. J., 2017. A Hidden Markov Model-Based Map-Matching Approach for Low-Sampling-Rate GPS Trajectories. In2017 IEEE 7th International Symposium on Cloud and Service Computing (SC2), 271-274.
[12] Huang, Z., Ling, X., Wang, P., Zhang, F., Mao, Y., Lin, T., & Wang, F. Y., 2018. Modeling real-time human mobility based on mobile phone and transportation data fusion. Transportation research part C: emerging technologies, 96, 251-269.
[13] Iqbal, M. S., Choudhury, C. F., Wang, P., & González, M. C., 2014. Development of origin–destination matrices using mobile phone call data. Transportation Research Part C: Emerging Technologies, 40, 63-74.
[14] Iovan, C., Olteanu-Raimond, A. M., Couronné, T., & Smoreda, Z., 2013. Moving and calling: Mobile phone data quality measurements and spatiotemporal uncertainty in human mobility studies. In Geographic information science at the heart of Europe, 247-265.
[15] Hsueh, Y. L., Chen, H. C., & Huang, W. J., 2017. A hidden Markov model-based map-matching approach for low-sampling-rate GPS trajectories. In 2017 IEEE 7th International Symposium on Cloud and Service Computing (SC2), 271-274.
[16] Jagadeesh, G. R., & Srikanthan, T., 2017. Online map-matching of noisy and sparse location data with hidden Markov and route choice models. IEEE Transactions on Intelligent Transportation Systems, 18(9), 2423-2434.
[17] Jagadeesh, G. R., & Srikanthan, T., 2015. Probabilistic Map matching of sparse and noisy smartphone location data. In 2015 IEEE 18th International Conference on Intelligent Transportation Systems, 812-817.
[18] Lee, J. K., & Hou, J. C., 2006. Modeling steady-state and transient behaviors of user mobility: formulation, analysis, and application. In Proceedings of the 7th ACM international symposium on Mobile ad hoc networking and computing, 85-96.
[19] Li, G., Chen, C. J., Peng, W. C., & Yi, C. W., 2017. Estimating crowd flow and crowd density from cellular data for mass rapid transit. In Proceedings of the 6th International Workshop on Urban Computing, Halifax,18-30.
[20] Lu, Z., Long, Z., Xia, J., & An, C., 2019. A Random Forest Model for Travel Mode Identification Based on Mobile Phone Sighting Data. Sustainability, 11(21), 5950.
[21] Newson, P., & Krumm, J., 2009. Hidden Markov Map matching through noise and sparseness. In Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, 336-343.
[22] Nitsche, P., Widhalm, P., Breuss, S., Brändle, N., & Maurer, P., 2014. Supporting large-scale travel surveys with smartphones–A practical approach. Transportation Research Part C: Emerging Technologies, 43, 212-221.
[23] Quddus, M. A., Ochieng, W. Y., Zhao, L., & Noland, R. B., 2003. A general Map matching algorithm for transport telematics applications. GPS Solutions, 7(3), 157-167.
[24] Quddus, M. A., Noland, R. B., & Ochieng, W. Y., 2006. A high accuracy fuzzy logic based Map matching algorithm for road transport. Journal of Intelligent Transportation Systems,10(3), 103-115.
[25] Qi, L., Qiao, Y., Abdesslem, F. B., Ma, Z., & Yang, J., 2016. Oscillation resolution for massive cell phone traffic data. In Proceedings of the First Workshop on Mobile Data, 25-30.
[26] Quddus, M. A., Ochieng, W. Y., & Noland, R. B., 2007. Current map-matching algorithms for transport applications: State-of-the art and future research directions. Transportation research part C: Emerging technologies, 15(5), 312-328.
[27] Reddy, A., Lu, A., Kumar, S., Bashmakov, V., & Rudenko, S., 2009. Entry-only automated fare-collection system data used to infer ridership, rider destinations, unlinked trips, and passenger miles. Transportation research record, 2110(1), 128-136.
[28] Tettamanti, T., Demeter, H., & Varga, I., 2012. Route choice estimation based on cellular sighting data. Acta Polytechnica Hungarica, 9(4), 207-220.
[29] Vlahogianni, E. I., Park, B. B., & Van Lint, J. W. C., 2015. Big data in transportation and traffic engineering. Transportation Research Part C, 161.
[30] Wang, F., & Chen, C., 2018. On data processing required to derive mobility patterns from passively-generated mobile phonedata. Transportation Research Part C: Emerging Technologies, 87, 58-74.