近年來科技的爆炸性的發展，使用細胞流動資料進行交通資訊評估分析，提供有效的進行交通預估達到即時及高涵蓋率及地成本為重要的議題。本論文透過接收的細胞流動資料及追蹤行動台的智慧型系統，進行交通位置以及交通車速的估計。在交通位置評估方法使用，包含行動台的偏好、經過行動台順序及在路段中經過行動台停留時間進行交通所在位置評估。行動台順序主要是判斷道路的方向，停留時間主要判斷是於快車道或慢車道之下。交通車速估計主要使用細胞流資料評估交通方法透過所在位置的細胞流訊號資訊，包含換手、通話到達、一般性位置更新、週期性位置更新。計算交通的流量及密度，交通流量評估使用換手及一般性位置更新訊號評估，交通密度的評估透過通話到達及週期性位置更新，在依據流量密度進行交通速度的分析。透過交通速度分析結果以倒傳遞類神經進行未來車速的預估。在實驗結果交通位置的評估方法有100%得準確度，比其他的方法(迴歸、倒傳遞類神經等方法)效能更好。在細胞流資料評估交通方法採用台灣地區國家高速公路局的實際交通信息（即交通流量和車輛速度）作為交通模擬程序的輸入特徵，並提到中華電信的行動台通信行為，以模擬交通信息和通信 記錄。 實驗結果表明，車速預測方法的平均精度為95.72％。 因此，基於細胞流動資料的提出的方法適用於智能交通系統。

In recent years, cellular floating vehicle data (CFVD) technology has been a popular traffic information estimation technique to analyze cellular network data and to provide real-time traffic information with the higher coverage and the lower cost. Therefore, this study proposes vehicle positioning and speed estimation methods to capture CFVD and to track mobile stations (MSs) for intelligent transportation system (ITS). Three features of CFVD which include the IDs, sequence, and cell dwell time of connected cells from the signals of MS’s communication are extracted and analyzed. The feature of sequence can be used to judge express road direction, and the feature of cell dwell time can be applied to discriminate proximal express roads. Furthermore, traffic information estimation and forecasting methods based on cellular floating vehicle data (CFVD) are proposed to analyze the signals (e.g., handovers (HOs), call arrivals (CAs), normal location updates (NLUs) and periodic location updates (PLUs)) from cellular networks. For traffic information estimation, analytic models are proposed to estimate the traffic flow in accordance with the amounts of HOs and NLUs and to estimate the traffic density in accordance with the amounts of CAs and PLUs. Then, the vehicle speeds can be estimated in accordance with the estimated traffic flows and estimated traffic densities. For vehicle speed forecasting, a back-propagation neural network algorithm is considered to predict the future vehicle speed in accordance with the current traffic information (i.e., the estimated vehicle speeds from CFVD). In the experimental environment, the experiment results showed the accuracy of the proposed vehicle positioning method which was 100% better than other popular machine learning methods (e.g., logistic regression , and back-propagation neural network). Furthermore, this study adopted the practical traffic information (i.e., traffic flow and vehicle speed) from Taiwan Area National Freeway Bureau as the input characteristics of the traffic simulation program and referred to the MS communication behaviors from Chunghwa Telecom to simulate the traffic information and communication records. The experimental results illustrated that the average accuracy of the vehicle speed forecasting method is 95.72%. Therefore, the proposed methods based on CFVD are suitable for an intelligent transportation system.

中文摘要 1
Abstract 2
Chapter 1 Introduction 6
1.1. Background 6
1.2. Motivation 7
1.3. Organization of Dissertation 8
Chapter 2 Related Work 9
2.1. Intelligent Transportation System 9
2.2. Cellular Networks 11
2.2.1. System Components 12
2.2.2. Mobility Management 14
2.3. Cellular Floating Vehicle Data for Traffic Estimation Methods 15
2.3.1. Location Services 15
2.3.2. Signal Statistics 17
2.3.3. Summary 18
2.4. Cellular Floating Vehicle Data for Traffic Forecasting Methods 19
Chapter 3 Vehicle Speed Estimation and Forecasting Methods 22
3.1. Traffic Information Estimation Methods 23
3.1.1. Vehicle Positioning Estimation 23
3.1.2. Traffic Flow Estimation 36
3.1.3. Traffic Density Estimation 40
3.1.4. Vehicle Speed Estimation 47
3.2. Vehicle Speed Forecasting Method 48
Chapter 4 Evaluations 51
4.1. Evaluation Results of Vehicle Positioning Method 51
4.1.1. Evaluation Environments 51
4.1.2. Evaluation Results 53
4.2. Evaluation Results of Traffic Information Estimation Methods 56
4.2.1. Evaluation Environments 56
4.2.2. Evaluation Results 58
4.3. Evaluation Results of Vehicle Speed Forecasting Methods 65
Chapter 5 Conclusions and Future work 68
References 71
Appendix A. The weights of BPNN 83
Appendix B: Abbreviated table 86

[1] D. Green, J. Gaffney, P. Bennett, Y. Feng, M. Higgins, J. Millner, “Vehicle positioning for C-ITS in Australia,” Project No. AP-R431/13, Australia, 2013. Available online: https://www.onlinepublications.austroads.com.au/items/AP-R431-13
[2] K. Ansari, Y. Feng, “Design of an integration platform for V2X wireless communications and positioning supporting C-ITS safety applications,” Journal of Global Positioning Systems, vol. 12, no. 1, pp. 38-52, 2013.
[3] B. Schoettle, M. Sivak, “A survey of public opinion about connected vehicles in the U.S., the U.K., and Australia,” Report No. UMTRI-2014-10, USA, 2014. Available online: http://hdl.handle.net/2027.42/106590
[4] M. Gao, T. Zhu, X. Wan, Q. Wang, “Analysis of travel time pattern in urban using taxi GPS data,” Proceedings of the 2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical and Social Computing, Beijing, China, 2013.
[5] J. Jang, S. Byun, “Evaluation of traffic data accuracy using Korea detector testbed,” IET Intelligent Transport Systems, vol. 5, no. 4, pp. 286-293, 2011.
[6] A. Ramezani, B. Moshiri, A.R. Kian, B.N. Aarabi, B. Abdulhai, “Distributed maximum likelihood estimation for flow and speed density prediction in distributed traffic detectors with Gaussian mixture model assumption,” IET Intelligent Transport Systems, vol. 6, no. 2, pp. 215-222, 2012.
[7] D. Middleton, R. Parker, “Vehicle detector evaluation,” Report No. FHWA/TX-03 /2119-1; Texas Transportation Institute, Texas Department of Transportation: Austin, TX, USA, 2002.
[8] W.J. Chen, C.H. Chen, B.Y. Lin, C.C. Lo, “A traffic information prediction system based on global position system-equipped probe car reporting,” Advanced Science Letters, vol. 16, no. 1, pp. 117-124,. 2012.
[9] T. Hunter, R. Herring, P. Abbeel, A. Bayen, “Path and travel time inference from GPS probe vehicle data,” Proceedings of the Neural Information Processing Foundation Conference, Vancouver, BC, Canada, 2009.
[10] R.L. Cheu, C. Xie, D.H. Lee, “Probe vehicle population and sample size for arterial speed estimation,” Computer-Aided Civil and Infrastructure Engineering, vol. 17, no. 1, pp. 53-60, 2002.
[11] J.C. Herrera, D.B. Work, R. Herring, X.J. Ban, Q. Jacoboson, A.M. Bayen, “Evaluation of traffic data obtained via GPS-enabled mobile phones: The mobile century field experiment,” Transportation Research Part C: Emerging Technologies, vol. 18, no. 4, pp. 568-583, 2010.
[12] N. Caceres, J.P. Wideberg, F.G. Benitez, “Review of traffic data estimations extracted from cellular networks,” IET Intelligent Transport Systems, vol. 2, no. 3, pp. 179-192, 2008.
[13] United Marketing Research. The Investigation Report on the Digital Opportunity about Phone Users. Research, Development and Evaluation Commission, Executive Yuan, 2011.
Available online: http://www.rdec.gov.tw/public/Attachment/213014313671.pdf
[14] W.K. Lai, T.H. Kuo, C.H. Chen, “Vehicle speed estimation and forecasting methods based on cellular floating vehicle data,” Applied Sciences, vol. 6, article no. 47, 2016.
[15] C.I. Wu, C.H. Chen, B.Y. Lin, C.C. Lo, “Traffic information estimation methods from handover events,” Journal of Testing and Evaluation, vol. 44, no. 1, pp. 656-664, 2016.
[16] M.F. Chang, C.H. Chen, Y.B. Lin, C.Y. Chia, “The frequency of CFVD speed report for highway traffic,” Wireless Communications and Mobile Computing, vol. 15, no. 5, pp. 879-888, 2015.
[17] A. Janecek, D. Valerio, K.A. Hummel, F. Ricciato, H. Hlavacs, “The cellular network as a sensor: From mobile phone data to real-time road traffic monitoring,” IEEE Transactions on Intelligent Transportation Systems, vol. 16, no. 5, pp. 2551-2572, 2015.
[18] C.H. Chen, H.C. Chang, C.Y. Su, C.C. Lo, H.F. Lin, “Traffic speed estimation based on normal location updates and call arrivals from cellular networks,” Simulation Modelling Practice and Theory, vol. 35, no. 1, pp. 26-33, 2013.
[19] H.C. Chang, C.H. Chen, B.Y. Lin, H.Y. Kung, C.C. Lo, “Traffic information estimation using periodic location update events,” International Journal Of Innovative Computing Information and Control, vol. 9, no. 5, pp. 2031-2041, 2013.
[20] S. Maerivoet, S. Logghe, “Validation of travel times based on cellular floating vehicle data,” Proceedings of the 6th European Congress and Exhibition on Intelligent Transport Systems and Services, Aalborg, Denmark, 2007.
[21] N. Caceres, L.M. Romero, F.G. Benitez, J.M. del Castillo, “Traffic flow estimation models using cellular phone data,” IEEE Transactions on Intelligent Transportation Systems, vol. 13, no. 3, pp. 1430-1441, 2012.
[22] D. Valerio, T. Witek, F. Ricciato, R. Pilz, W. Wiedermann, “Road traffic estimation from cellular network monitoring: A hands-on investigation,” Proceedings of the IEEE 20th International Symposium on Personal, Indoor and Mobile Radio Communications, Tokyo, 2009.
[23] D. Valerio, A. D’Alconzo, F. Ricciato, W. Wiedermann, “Exploiting cellular networks for road traffic estimation: A survey and a research roadmap,” Proceedings of the IEEE 69th Vehicular Technology Conference, Barcelona, Spain, 2009.
[24] C.H. Chen, C.C. Lo, H.F. Lin, “The Analysis of Speed-Reporting Rates from a cellular network based on a fingerprint-positioning algorithm,” South African Journal of Industrial Engineering, vol. 24, no. 1, pp. 98-106, 2013.
[25] C.H. Chen, B.Y. Lin, H.C. Chang, C.C. Lo, “The novel positioning algorithm based on cloud computing—A case study of intelligent transportation systems,” Information-An International Interdisciplinary Journal, vol. 15, no. 11(A), pp. 4519-4524, 2012.
[26] D.Y. Cheng, C.H. Chen, C.H. Hsiang, C.C. Lo, H.F. Lin, B.Y. Lin, “The optimal sampling period of a fingerprint positioning algorithm for vehicle speed estimation,” Mathematical Problems in Engineering, vol. 2013, article no. 306783, 2013.
[27] C.H. Chen, B.Y. Lin, C.H. Lin, Y.S. Liu, C.C. Lo, “A green positioning algorithm for campus guidance system,” International Journal of Mobile Communications, vol. 10, no. 2, pp. 119-131, 2012.
[28] D. Gundlegård, J.M. Karlsson, “The smartphone as enabler for road traffic information based on cellular network signaling,” Proceedings of the 16th International IEEE Conference on Intelligent Transportation Systems, Hague, The Netherlands, 2013.
[29] D. Gundlegard, J.M. Karlsson, “Handover location accuracy for travel time estimation in GSM and UMTS,” IET Intelligent Transport Systems, vol. 3, no. 1, pp. 87-94, 2009.
[30] D. Gundlegard, J.M. Karlsson, “Route classification in travel time estimation based on cellular network signaling,” Proceedings of the 12th International IEEE Conference on Intelligent Transportation Systems, St. Louis, MO, USA, 2009.
[31] D. Gundlegard, J.M. Karlsson, “Generating road traffic information from cellular networks—New possibilities in UMTS,” Proceedings of the 6th International Conference on ITS Telecommunications, Chengdu, China, 2006.
[32] C.H. Chen, J.H. Lin, T.S. Kuan, K.. Lo, “A high-efficiency method of mobile positioning based on commercial vehicle operation data,” ISPRS International Journal of Geo-Information, vol. 5, article no. 82, 2016.
[33] J.Y. Yang, L.D. Chou, C.F. Tung, S.M. Huang, Wang, T.W. “Average-speed forecast and adjustment via VANETs,” IEEE Transactions on Vehicular Technology, vol. 62, no. 9, pp. 4318-4327, 2013.
[34] S. Maerivoet, S. Logghe, “Validation of travel times based on cellular floating vehicle data,” Proceedings of the 6th European Congress and Exhibition on Intelligent Transport Systems and Services, Aalborg, Denmark, 2007.
[35] Y.B. Lin, A.C. Pang, Wireless and Mobile All-IP Networks, John Wiley & Sons: Hoboken, NJ, USA, 2005.
[36] H. Holma, A. Toskala, LTE for UMTS: Evolution to LTE-Advanced, 2nd Edition, John Wiley & Sons: Hoboken, NJ, USA, 2011.
[37] ETSI. Digital Cellular Telecommunications System (Phase 2+); Mobile radio interface layer 3 specification, GSM 04.08; European Telecommunications Standards Institute: Sophia Antipolis, France, 1995.
[38] ETSI. Digital Cellular Telecommunications System (Phase 2+); Handover procedures, GSM 03.09 version 5.1.0; European Telecommunications Standards Institute: Sophia Antipolis, France, 1997.
[39] 3GPP Technical Specification Group (TSG) Services and System Aspects, TS 22.071, Location Services (LCS); Service description; Stage 1 (Release 9), version 9.1.0; 2010. Available online: http://www.3gpp.org/specifications-groups
[40] C.H. Chen, “Traffic information estimation methods based on cellular network data,” Ph.D. Thesis, Department of Information Management and Finance, National Chiao Tung University, Hsinchu, Taiwan, 2013.
[41] I. Ernst, S. Sujew, K.U. Thiessenhusen, M. Hetscher, S. Rassmann, M. Ruhe, “LUMOS-airborne traffic monitoring system,” Proceedings of the 6th International IEEE Conference on Intelligent Transportation Systems, Shanghai, China, 2003.
[42] C. Birle, M. Wermuth, “The traffic online project,” Proceedings of the 13th ITS World Congress, London, UK, 2006.
[43] T.H. Kuo, W.K. Lai, C.H. Chen, “A traffic speed estimation model base on using location update events,” Proceedings of the 9th International Conference on Wireless Communications, Network and Mobile Computing, Beijing, China, 2013.
[44] W.K. Lai, T.H. Kuo, C.H. Chen, D.R. Lee, “A vehicle speed estimation mechanism using handovers and call arrivals of cellular networks,” Proceedings of the 12th International Conference on Advances in Mobile Computing and Multimedia, Kaohsiung, Taiwan, 2014.
[45] Z. Shan, D. Zhao, Y. Xia, “Urban road traffic speed estimation for missing probe vehicle data based on multiple linear regression model,” Proceedings of the 16th International IEEE Conference on Intelligent Transportation Systems, Hague, Netherlands, 2013.
[46] C. Antoniou, H.N. Koutsopoulos, G. Yannis, “Dynamic data-driven local traffic state estimation and prediction,” Transportation Research Part C: Emerging Technologies, vol. 34, no. 1, pp. 89-107, 2013.
[47] C.C. Lu, X. Zhou, “Short-term highway traffic state prediction using structural state space models,” Journal of Intelligent Transportation Systems: Technology, Planning, and Operations, vol. 18, no. 3, pp. 309-322, 2014.
[48] X .Fei, C.C. Lu, K. Liu, “A Bayesian dynamic linear model approach for real-time short-term freeway travel time prediction,” Transportation Research Part C: Emerging Technologies, vol. 19, no. 6, pp. 1306-1318, 2011.
[49] T. Liu, J. Ma, W. Guan, Y. Song, H. Niu, “Bus arrival time prediction based on the k-nearest neighbor method,” Proceedings of the Fifth IEEE International Joint Conference on Computational Sciences and Optimization, Harbin, China, 2012.
[50] A.T. Baptista, E.P. Bouillet, P. Pompey, “Towards an uncertainty aware short-term travel time prediction using GPS bus data: Case study in Dublin,” Proceedings of the 15th International IEEE Conference on Intelligent Transportation Systems, Anchorage, AK, USA, 2012.
[51] S. Kim, H. Rim, C. Oh, E. Jeong, Y. Kim, “Multiple-step traffic speed forecasting strategy for winter freeway operations,” Transportation Research Record: Journal of the Transportation Research Board, vol. 2482, pp. 133-140, 2015.
[52] S.I.J. Chien, Y.Q. Ding, C.H. Wei, “Dynamic bus arrival time prediction with artificial neural networks,” Journal of Transportation Engineering, vol. 128, no. 5, pp. 429-438, 2012.
[53] V.J. Hodge, R. Krishnan, J. Austin, J. Polak, T. Jackson, “Short-term prediction of traffic flow using a binary neural network,” Neural Computing and Applications, vol. 25, no. 7, pp. 1639-1655, 2014.
[54] J.W. van Lint, “Reliable real-time framework for short-term freeway travel time prediction,” Journal of Transportation Engineering, vol. 132, no. 12, pp. 921-932, 2006.
[55] X. Ma, Z. Tao, Y. Wang, H. Yu, Y. Wang, “Long short-term memory neural network for traffic speed prediction using remote microwave sensor data,” Transportation Research Part C: Emerging Technologies, vol. 54, no. 1, pp. 187-197, 2015.
[56] J. Han, M. Kamber, J. Pei, Data Mining: Concepts and Techniques, 3rd ed.; Morgan Kaufmann Publishers: San Francisco, CA, USA, 2011.
[57] W.K. Lai, T.H. Kuo, “An urban road segment determination method based on cellular floating vehicle data for tracking mobile stations,” Proceedings of the 7th International IEEE Conference on Ubi-Media Computing and Workshops, Ulaanbaatar, Mongolia, 2014.
[58] R. Ihaka, R. Gentleman, “R: A language for data analysis and graphics,” Journal of Computational and Graphical Statistics, vol. 5, no. 3, pp. 299-314, 1996.
[59] B.D. Ripley, “The R project in statistical computing,” MSOR Connections, vol. 1, no. 1, pp. 23-25. 2001.
[60] Racine, J.S. “RStudio: A platform-independent IDE for R and sweave,” Journal of Applied Econometrics, vol. 27, no. 1, pp. 167-172, 2012.
[61] B. Ripley, W. Venables, “Class: functions for classification,” The Comprehensive R Archive Network 2015.
Available online: https://cran.r-project.org/web/packages/class/index.html
[62] D. Meyer, E. Dimitriadou, K. Hornik, A. Weingessel, F. Leisch, C.C. Chang, C.C. Lin, “e1071: Nisc Functions of the Department of Statistics, Probability Theory Group,” The Comprehensive R Archive Network 2015.
Available online: https://cran.r-project.org/web/packages/e1071/index.html
[63] T. Hothorn, K. Hornik, C. Strobl, A. Zeileis, “Party: a laboratory for recursive partytioning,” The Comprehensive R Archive Network 2015.
Available online: https://cran.r-project.org/web/packages/party/index.html
[64] S. Fritsch, F. Guenther, “Neuralnet: training of neural networks,” The Comprehensive R Archive Network 2012.
Available online: https://cran.r-project.org/web/packages/neuralnet/index.html
[65] J.B. Kruskal, “Multidimensional scaling by optimizing goodness of fit to a non-metric hypothesis,” Psychometrika, vol. 29, no. 1, pp. 1-27,1964
[66] P.C. Mahalanobis, “On the generalised distance in statistics,” Proceedings of the National Institute of Sciences of India, vol. 2, no. 1, pp. 49-55, 1936.
[67] C.H. Chen, J.H. Lin , T.S. Kuan, K.R. Lo, “High-efficiency method of mobile positioning based on commercial vehicle operation data,” ISPRS International journal of Geo-Information, vol. 5, article no. 82, 2016.