準確的旅行時間預測在智慧運輸中非常重要。在文獻中，多種旅行時間預測方法已被
提出，例如差分整合移動平均自迴歸模型和類神經網路模型。然而，現有模型忽略了
紅綠燈模型的設計，導致在預測複雜城市道路中旅行時間的性能較差。本文提出了一
種考慮車輛偵測器訊息與影像資料的旅行時間預測演算法。我們提出的演算法可以分
為兩部分：基於駕駛員行為的車速預測模型與紅綠燈模型。我們觀察實際平均車速與
平均瞬時速度之間的關係，以設計車速預測模型。此外，我們使用長短期記憶網路預
測平均瞬時速度。對於我們的紅綠燈模型，我們從政府收集相關的紅綠燈訊息，進一
步估算路口號誌處車輛的排隊時間。由真實世界的實驗證明，我們演算法能符合實際
道路交通狀況。

Accurate travel time prediction is essential in smart transportation. In the literature, variety of travel time prediction methods, e.g., the ARIMA and Neural Networks model, have been proposed. However, existing models ignore the design of traffic lights model, leading to poor performance for predicting travel times in complex urban road networks. In this thesis, a novel travel time prediction algorithm is proposed, considering measurements from vehicle detector information and detailed traffic data. The proposed prediction algorithm can be divided into two parts: driver behavior-based vehicle speed prediction model and traffic light model. For our speed prediction model, we design a formula to describe the relationship between the actual vehicle speed and average instantaneous speed. Then, we use the Long Short-Term Memory model to predict the average instantaneous speed. On the other hand, in the traffic light model, we collect related traffic light information from the government and further estimate the queuing time of vehicles at an intersection. Real-world experiments showed that the predicted travel times are close to the actual traffic condition.

摘要 ... i
Abstract ... ii
Contents ... iii
List of Figures ... v
List of Tables ... vi
1 Introduction ... 1
2 Related Work ... 5
2.1 Parametric Approaches ... 6
2.2 Nonparametric Approaches ... 6
3 Data Collection and Preparation ... 9
3.1 Vehicle Detector Information ... 9
3.2 Detailed Traffic Data ... 11
4 Travel Time Prediction Algorithm ... 13
5 Driver Behavior-Based Vehicle Speed Prediction Model ... 16
5.1 Data Pre-Processing ... 17
5.1.1 Definition of Actual Average Speed wj ... 17
5.1.2 Data Acquisition ... 17
5.1.3 Normalization ... 17
5.2 Overall Structure ... 18
5.3 Average Instantaneous Speed vr(Tr) Prediction ... 20
6 Traffic Light Model ... 23
6.1 tm(r,τr) Time ... 23
6.2 tw(r,τr) Time ... 25
6.2.1 Nc(r,te(r,τr)) ... 25
6.2.2 tI(l,r) ... 28
7 Model Validation ... 30
7.1 Driver Behavior-Based Vehicle Speed Prediction Model ... 30
7.1.1 Model Verification ... 30
7.1.2 Performance of vr(Tr) Prediction With LSTM Model ... 31
7.2 Traffic Light Model ... 33
7.3 Travel Time Prediction Algorithm ... 37
8 Conclusion ... 41
Bibliography ... 43

[1] L. Vanajakshi and L. R. Rilett, “Support vector machine technique for the short term prediction of travel time,” in 2007 IEEE Intelligent Vehicles Symposium, pp. 600–605, June 2007.
[2] S. Yang, Y. Su, Y. Chang, and H. Hung, “Short-term traffic prediction for edge computing-enhanced autonomous and connected cars,” IEEE Transactions on Vehicular Technology, vol. 68, pp. 3140–3153, April 2019.
[3] C. Guo, D. Li, G. Zhang, and M. Zhai, “Real-time path planning in urban area via vanet-assisted traffic information sharing,” IEEE Transactions on Vehicular Technology, vol. 67, pp. 5635–5649, July 2018.
[4] Q. Gan, G. Gomes, and A. Bayen, “Estimation of performance metrics at signalized intersections using loop detector data and probe travel times,” IEEE Transactions on Intelligent Transportation Systems, vol. 18, pp. 2939–2949, Nov 2017.
[5] T. Babicheva, “The use of queuing theory at research and optimization of traffic on the signal-controlled road intersections,” Procedia Computer Science, vol. 55, pp. 469–478, 2015. 3rd International Conference on Information Technology and Quantitative Management, ITQM 2015.
[6] E. I. Vlahogianni, M. G. Karlaftis, and J. C. Golias, “Short-term traffic forecasting: Where we are and where we’re going,” Transportation Research Part C: Emerging Technologies, vol. 43, pp. 3 – 19, 2014. Special Issue on Short-term Traffic Flow Forecasting.
[7] T.-H. Chang, A. Y. Chen, Y.-T. Hsu, and C.-L. Yang, “Freeway travel time prediction based on seamless spatio-temporal data fusion: Case study of the freeway in taiwan,” Transportation Research Procedia, vol. 17, pp. 452 – 459, 2016. International Conference on Transportation Planning and Implementation Methodologies for Developing Countries (12th TPMDC) Selected Proceedings, IIT Bombay, Mumbai, India, 10-12 December 2014.
[8] S. Oh, Y.-J. Byon, K. Jang, and H. Yeo, “Short-term travel-time prediction on highway: A review on model-based approach,” KSCE Journal of Civil Engineering, vol. 22, pp. 298–310, Jan 2018.
[9] K. Tang, S. Chen, and Z. Liu, “Citywide spatial-temporal travel time estimation using big and sparse trajectories,” IEEE Transactions on Intelligent Transportation Systems, vol. 19, pp. 4023–4034, Dec 2018.
[10] J. Tang, F. Liu, Y. Zou, W. Zhang, and Y. Wang, “An improved fuzzy neural network for traffic speed prediction considering periodic characteristic,” IEEE Transactions on Intelligent Transportation Systems, vol. 18, pp. 2340–2350, Sep. 2017.
[11] H. Kim, Y. Kim, and K. Jang, “Systematic relation of estimated travel speed and actual travel speed,” IEEE Transactions on Intelligent Transportation Systems, vol. 18, pp. 2780–2789, Oct 2017.
[12] F. Ye, P. Hao, X. Qi, G. Wu, K. Boriboonsomsin, and M. J. Barth, “Prediction- based eco-approach and departure at signalized intersections with speed forecasting on preceding vehicles,” IEEE Transactions on Intelligent Transportation Systems, vol. 20, pp. 1378–1389, April 2019.
[13] X. Feng, X. Ling, H. Zheng, Z. Chen, and Y. Xu, “Adaptive multi-kernel svm with spatial–temporal correlation for short-term traffic flow prediction,” IEEE Transactions on Intelligent Transportation Systems, vol. 20, pp. 2001–2013, June 2019.
[14] H. Zhan, G. Gomes, X. S. Li, K. Madduri, A. Sim, and K. Wu, “Consensus ensemble system for traffic flow prediction,” IEEE Transactions on Intelligent Transportation Systems, vol. 19, pp. 3903–3914, Dec 2018.
[15] J. Mackenzie, J. F. Roddick, and R. Zito, “An evaluation of htm and lstm for short- term arterial traffic flow prediction,” IEEE Transactions on Intelligent Transportation Systems, vol. 20, pp. 1847–1857, May 2019.
[16] M. Althoff, D. Heß, and F. Gambert, “Road occupancy prediction of traffic participants,” in 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013), pp. 99–105, Oct 2013.
[17] P. Zechel, R. Streiter, K. Bogenberger, and U. Goehner, “Probabilistic interaction- aware occupancy prediction for vehicles in arbitrary road scenes,” in 2019 Third IEEE International Conference on Robotic Computing (IRC), pp. 423–424, Feb 2019.
[18] M. Koschi and M. Althoff, “Spot: A tool for set-based prediction of traffic participants,” in 2017 IEEE Intelligent Vehicles Symposium (IV), pp. 1686–1693, June 2017.
[19] U. Mori, A. Mendiburu, M. A´lvarez, and J. A. Lozano, “A review of travel time
estimation and forecasting for advanced traveller information systems,” Transport- metrica A: Transport Science, vol. 11, no. 2, pp. 119–157, 2015.
[20] C. Menelaou, S. Timotheou, P. Kolios, C. G. Panayiotou, and M. M. Polycarpou, “Minimizing traffic congestion through continuous-time route reservations with travel time predictions,” IEEE Transactions on Intelligent Vehicles, vol. 4, pp. 141–153, March 2019.
[21] Z. Yu, J. S. Wood, and V. V. Gayah, “Using survival models to estimate bus travel times and associated uncertainties,” Transportation Research Part C: Emerging Technologies, vol. 74, pp. 366 – 382, 2017.
[22] A. Achar, D. Bharathi, B. A. Kumar, and L. Vanajakshi, “Bus arrival time prediction: A spatial kalman filter approach,” IEEE Transactions on Intelligent Transportation Systems, pp. 1–10, 2019.
[23] Chun-Hsin Wu, Jan-Ming Ho, and D. T. Lee, “Travel-time prediction with support vector regression,” IEEE Transactions on Intelligent Transportation Systems, vol. 5, pp. 276–281, Dec 2004.
[24] R. P. D. Nath, H.-J. Lee, N. K. Chowdhury, and J.-W. Chang, “Modified k-means clustering for travel time prediction based on historical traffic data,” in Proceedings of the 14th International Conference on Knowledge-based and Intelligent Information and Engineering Systems: Part I, KES’10, (Berlin, Heidelberg), pp. 511–521, Springer-Verlag, 2010.
[25] E. Jenelius and H. N. Koutsopoulos, “Urban network travel time prediction based on a probabilistic principal component analysis model of probe data,” IEEE Trans- actions on Intelligent Transportation Systems, vol. 19, pp. 436–445, Feb 2018.
[26] K. Chu, A. Y. S. Lam, and V. O. K. Li, “Deep multi-scale convolutional lstm net- work for travel demand and origin-destination predictions,” IEEE Transactions on Intelligent Transportation Systems, pp. 1–14, 2019.
[27] A. S. Mane and S. S. Pulugurtha, “Link-level travel time prediction using artificial neural network models,” in 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp. 1487–1492, Nov 2018.
[28] P. He, G. Jiang, S. Lam, and D. Tang, “Travel-time prediction of bus journey with multiple bus trips,” IEEE Transactions on Intelligent Transportation Systems, pp. 1– 14, 2018.
[29] A. Ladino, A. Kibangou, C. C. de Wit, and H. Fourati, “A real time forecasting tool for dynamic travel time from clustered time series,” Transportation Research Part C: Emerging Technologies, vol. 80, pp. 216 – 238, 2017.
[30] H. Akaike, Information Theory and an Extension of the Maximum Likelihood Principle, pp. 199–213. New York, NY: Springer New York, 1998.
[31] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput., vol. 9, pp. 1735–1780, Nov. 1997.
[32] S. Hochreiter, “The vanishing gradient problem during learning recurrent neural nets and problem solutions,” International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, vol. 06, no. 02, pp. 107–116, 1998.