準確且良好的即時交通資訊，能提供用路人旅程規劃、路線與運具選擇，藉此減少旅行時間的不確定性與運輸成本的耗費。以用路人觀點來說，準確的旅行時間預測是最為貼近用路人直接感受，旅行時間也是最能代表經過處理分析後的交通資訊，用路人掌握良好的旅行時間，可以對路徑選擇、出發時間、旅行規劃進行有效率的評估決策，因此旅行時間的預測為智慧型運輸系統中的重要課題。
本研究使用參考先前旅行時間預測文獻方法 ，提出四種文獻預測模式，並構思新概念方法且建構七種新預測模式，本研究之方法概念如下：考量導致旅行時間增加的交流道擾動延遲因子，以及時間軸反應機制融合歷史與即時資料，再採用e-Tag感應門架資料進行先前的模式校估，並也建構e-Tag預測模型，最後組合多種維度建構新的預測模式，藉由各種新概念模式來預測旅行時間，與真實旅次之旅行時間比較，進行模式預測評估。
本研究實驗結果在長程或與短程旅次路段下，模式皆能有理想的預測表現。採用交流道擾動、時間軸反應機制、校估、多維度組合模式總體來說比現有的預測方式準確率佳，在校估、e-Tag旅行時間預測與二合一多維度組合模式中其準確率達95%，二合一多維度模式準確率達95.65%為最準確的預測模式，研究成果提供準確的旅行時間預測資訊可以幫助用路人做更佳的旅行規劃，讓用路人方便決定出發時間和行車路線，藉以降低旅運成本且提高運輸品質。

Accurate real-time traffic information that provides driver to plan trips, to make better chooses on route and transport equipment, by reducing the travel time and consuming uncertainty transportation cost.Travel time is also the most representative of transportation analysis,driver can control travel time effectively, driver can focus on route, departure time, finally finish travel planning and make efficient decision. This is important issue for predicting travel time in intelligent transport systems.
In this study, refered to the previous literature, proposed four kinds of existing prediction model, and construct seven kinds prediction models of new concepts and methods.The concept of research methods as follows: considering “interchanges disturbances delay factor”of travel time increased, and use “timeline response mechanism” to make a fusion of history and real-time data, and then use e-Tag data to calibrate the previous models and construct e-Tag prediction model, finally construct a new prediction model of combine multiple dimensions.The study via a variety new conceptual models to predict travel time, compare with the real time of travel trip,and finally evaluate prediction models.
The experiment results in long-term or short-term journeys prediction performance is great. All excellent accuracy rate of considering interchange disturbances, timeline response mechanism, model calibration, multi-dimensional combination model is more than existing prediction methods. The accuracy rate of model calibration, e-Tag travel time prediction and two in one models have reach 95%. Considering two in one multi-dimensional prediction model accuracy rate is 95.65% for the most accurate prediction model.The study provide accurate travel time information that can help driver to do better travel planning. To make decision easily in departure time and driving routes, avoid road congestion to reduce transport costs and improve transport trip quality.

一、中文部分
1. 黃惠隆、翁忠川、黃月貞，2004，「以車輛偵測器推估旅行時間之研究—以北二高為例」，中華技術季刊，第63期，財團法人中華顧問工程司
2. 卓訓榮，周幼珍，王晉元，蔡繼光，2009，「高速公路旅行時間預測-以k-NN法及分群方法探討」，中華民國運輸學會98年學術論文研討會
3. 吳文斌，2012，「基於車載網路之都會區路網的即時旅行時間預估系統」，國立成功大學交通管理學系研究所碩士論文
4. 洪偉勛，2013，「高速公路旅行時間推估模式之開發與應用-以國道五號為例」，國立成功大學交通管理學系研究所碩士論文
5. 黃守琮，2004，「運用探針車與偵測器資料融合估計車輛旅行時間之研究」，淡江大學運輸管理學系研究所碩士論文
6. 吳佳峰，2001，「有GPS 資訊提供下之車輛旅行時間預估模式之研究」，國立交通大學運輸工程與管理學系研究所碩士論文。
7. 李穎，2001，「類神經網路應用於國道客運班車旅行時間預測模式之研究」，國立成功大學交通管理學系研究所碩士論文。
8. 吳欣潔，2004，「熵應用於交通資料融合之研究」，國立交通大學運輸科技與管理學系研究所碩士論文。
9. 吳瑞豐，2006，「最佳權重法應用於交通資料融合」，國立交通大學運輸科技與管理學系研究所碩士論文。
10. 李威勳，2009，「都會區交通路網整體效能提升之研究」，國立交通大學資訊工程研究所博士論文。
11. 交通部運輸研究所，2011，「2011年台灣地區公路容量手冊」。
12. 交通部臺灣區國道高速公路局，2013，「高速公路中長程旅行時間預測模式之建立與應用」。
13. 資拓宏宇國際股份有限公司，2013，「交通資訊服務雲基礎建設與應用計畫整體規劃委外服務案-交通面整體規劃報告」。

二、英文部分
1. Basir, O.A. & Shen, H.C. (1992), Sensory Data Integration: A Team Consensus Approach, 1992 IEEE International Conference on Robotics and Automation, pp. 1683-1688.
2. Wu, C.H., Ho, J.M. & Lee, D.T. (2004), Travel-Time Prediction With Support Vector Regression, IEEE Transactions on Intelligent Transportation Systems, vol. 5, no. 4, pp.276-281.
3. Chen, M., Xia, J.& Liu, R. R.(2006), Developing a Strategy for Imputing Missing Traffic Volume Data, Journal of the Transportation Research Forum, Vol. 45, No. 3, pp. 57-75.
4. Lin, H.E., Aptaylor, M. & Zito, Rocco.(2005), A Review of Travel-Time Prediction In Transport And Logistics, Proceedings of the Eastern Asia Society for Transportation Studies, Vol. 5, pp. 1433 – 1448.
5. Rice, J.& Zwet, E.V. (2004), A Simple and Effective Method for Predicting Travel Times on Freeways, IEEE Transactions on Intelligent Transportation Systems, vol. 5, no. 3, pp.200-207.
6. Wang, J.Y., Wong, K.I. & Chen, Y.Y. (2012), Short-term Travel Time Estimation and Prediction for Long Freeway Corridor using NN and regression, 2012 15th International IEEE Conference on Intelligent Transportation Systems Anchorage, Alaska, USA, pp.582-587.
7. KISGYÖRGY, L. & RILETT, L.R. (2002), Travel Time Prediction By Advanced Neural Network, periodica polytechnica ser. civ. eng, vol. 46, no. 1, pp. 15–32.
8. Lee, W.H., Tseng, S.S. & Tsai, S.H. (2009), A Knowledge based Real-time Travel Time Prediction System for Urban Network, Expert System with Applications, Vol. 36, No. 3, Part1, pp. 4239-4247.
9. Huang, L. & Barth, M. (2008), A Novel Loglinear Model for Freeway Travel Time Prediction, Proceedings of the 11th International IEEE Conference on Intelligent Transportation Systems Beijing, China, pp.210-215.
10. D’Angelo, M.P., Al-Deek,H.M. & Wang,M.C. (1999), Travel-time Prediction for Freeway Corridors, Transportation Research Record, No. 1676, pp. 184-191.
11. Yildirimoglu, M., & Geroliminis, N. (2013).Experienced travel time prediction for congested freeways, Transportation Research Part B: Methodological,vol.53, 45–63.
12. Nanthawichit, C., Nakatsuji, T., & Suzuki, H. (2004).Application of Probe-Vehicle Data for Real-Time Traffic-State Estimation and Short-Term Travel-Time Prediction on a Freeway, Transportation Research Record: Journal of the Transportation Research Board, Vol. 1855 / 2003, pp. 49-59.
13. Nelson, P. C.(1996).Application of neural networks to data fusion: a feasibility study,Transportation research board.
14. Hwang, K.P.,Lee, W.H. &Wu, W.B.(2012).Travel time prediction by weighted fusion of probing vehicles and vehicle detectors data sources, ITS Telecommunications (ITST), 2012 12th International Conference on Taipei, Taiwan, pp.478-481.
15. Lee, W.H., Tseng, S.S., Shieh, J.L.& Chen, H.H. (2011).Discovering Traffic Bottlenecks in an Urban Network by Spatiotemporal Data Mining on Location-Based Services, IEEE Transactions on Intelligent Transportation Systems, vol. 12, no. 4, pp.1047-1056.
16. Van Lint, J. W. C.(2004)” Reliable Travel Time Prediction for Freeways” TU Delft, Delft University of Technology