本研究利用類神經網路融合多樣交通資料構建一旅行時間預測模式，此模式考慮了預測性的事件延續時間資料並比較不同的資料簡化方法。因此，另優先構建一事件延續時間預測模式，利用事件發生時的即時交通資料及持續性即時資料，每隔固定時間更新事件延續時間預測值到事件結束，此預測性的事件延續時間資訊即作為旅行時間預測模式輸入變數之一。研究中所使用的即時交通資料來自於裝有全球定位系統(Global position systems, GPS)設備之國道客運班車運行資料、迴圈式車輛偵測器之車流資料以及事件資料庫之事件資料。此二類模式皆考慮了資料間的時空關係以表現出交通推移的變化。

為了改善模式績效與節省資料收集時間，本研究討論了資料組合、資料集群與基因演算法資料篩選等三種資料簡化方法之效果。旅行時間預測模式績效方面，除了評估各路段模式的預測績效外，亦評估組合路段預測資訊成為路徑預測資訊時的預測結果，另再分析事件發生時與未有事件發生時的模式預測績效，以瞭解模式未來在服務不同起迄對與有無事件發生時的適用效果。

本研究在事件延續時間預測與旅行時間預測之結果，對於智慧型運輸系統之實務應用推展有具體的參考意義。

This research builds a travel time forecasting model with sequential update of accident duration by fusing a variety of traffic data with Artificial Neural Networks. To consider the influence of accident to the travel time forecasting, the sequential update of accident duration forecasting model is built first. The forecasted duration can be renewed with the updated traffic data throughout the duration of the accident. The output of accident duration model, forecasted accident duration, will become one of the inputs to the travel time forecasting model. The travel time forecasting model constructs a functional relation between real-time traffic data as the input variables and real bus travel time as the output variable. Real-time traffic data are collected from the global position systems (GPS) on board of the intercity buses, vehicle detectors (VD), and accident databases. These two models will consider the time-space relationship between the traffic data and the accident to represent the traffic propagation.

To improve the model performance and save the cost in data collection, the effect of data feature reduction to the model is assessed. The methods considered for data feature reduction include the composition, cluster and selection with Genetic Algorithm. For accident occurrence and no-occurrence uses, the effect of travel time forecasting model will be assessed respectively. To reflect traveler behavior closely, partitioning the freeway into links for model development is considered a proper approach. Once the link travel time forecasting model has been built, the forecasted path travel time will be evaluated by summing the forecasted link travel time to fulfill the user’s trip characteristic.

The features of this research are considering the forecasted accident duration into travel time forecast, discussing the methods of data feature reduction and sequential update of forecasting information. This study shows very promising practical applicability of the proposed models in the Intelligent Transportation Systems (ITS) context.

1.Chang, C. C. (2000) The analysis of user's demand in advanced traveler information system. Thesis, Institute of Traffic & Transportation, National Chiao Tung University.
2.Chen, P. S. T., Srinivasan, K. K., Mahmassani, H.S. (1999) Effect of information quality on compliance behavior of commuters under real-time traffic information. Proceedings of the 77th Transportation Research Board Annual Meeting (CD-ROM), National Academies Press, Washington, DC, USA.
3.Chen, M. and Chien, I. J. (2001) Dynamic freeway travel time prediction using probe vehicle data: link-based vs. path-base. Transportation Research Record 1768, TRB, National Research Council, Washington, D. C., 157-161.
4.Chien, I. J., Ding, Y. and Wei, C. H. (2002) Dynamic bus arrival time prediction with artificial neural networks. Journal of Transportation Engineering, 128(5), 429-438.
5.Coifman, B. (2002) Estimating travel times and vehicle trajectories on freeways using dual loop detectors. Transportation Research, Part A, 36A(4), 351-364.
6.Cortes, C. E. and Lavanya, Rjiu, Oh, J. S. and Jayakrishnan, R. (2002) General-Purpose Methodology for estimating link travel time with multiple-point detection of traffic. Transportation Research Record 1802, TRB, National Research Council, Washington, D. C., 181-189.
7.D’angelo, M. P., Al-Deek, H. M. and Wang, M. C. (1999) Travel time prediction for freeway corridors. Transportation Research Record 1676, TRB, National Research Council, Washington, D. C., 184-191.
8.Dharia, A. and Adeli, H. (2003) Neural network model for rapid forecasting of freeway link travel time. Engineering Application of Artificial Intelligence, 16(7-8), 607-613.
9.Dion, F. and Rakha, H. (2006) Estimating dynamic roadway travel times using automatic vehicle identification data for low sampling rates. Transportation Research, Part B, 40(9), 745-766.
10.Dougherty, M. S. (1997) Applications of neural networks in transportation. Transportation Research, Part C, 5(5), 255-257.
11.Garib, A., Radwan, A. E. and Al-Deek, H. (1997) Estimating magnitude and duration of accident delays, Journal of Transportation Engineering, 123(6), 459-466.
12.Hall, D. L. (1992) Mathematical techniques in Multisensor data fusion. Artech House, Boston.
13.Hiroshi, W., Tomoaki, O. & Atsushi, T. (2001) Evaluation operation for travel time information on the metropolitan expressway, Proceedings of the eighth ITS World Congress (CD-ROM), Sydney, Australia.
14.Huisken, G. and Berkum, E. V. (2002) Short-time travel time prediction using data from detection loops. Proceedings of the ninth ITS World Congress (CD-ROM), Chicago, USA.
15.Krikke, R. (2002) Short-range travel time prediction using an artificial neural network. Proceedings of the ninth ITS World Congress (CD-ROM), Chicago, USA.
16.Lee, J. D. (1997) Object recognition using a neural network with optimal feature extraction. Mathematical and Computer Modelling, 25(12), 105-117.
17.Lee, Y. I. and Choi, C. Y. (1998) Development of a link travel time prediction algorithm for urban expressway. Proceedings of the fifth ITS World Congress (CD-ROM), Seoul, Korea.
18.Lewis, C. D. (1982) Industrial and Business Forecasting Method. Butter worth Scientific, London.
19.Li, R., Rose, G. and Sarvi, M. (2006) Evaluation of speed-based travel time estimation models. Journal of Transportation Engineering, 132(7), 540-547.
20.Li, L., Wei, J., Li, X., Moser, K. L., Guo, Z., Lei, D., Wang, Q., Topol, E. J., Wang, Q. and Rao, S. (2005) A robust hybrid between genetic algorithm and support vector machine for extracting an optimal feature gene subset. Genomics, 85(1), 16-23.
21.Lindveld, C. D. R., Thijs, R., Bovy, P. H. L. and Zijpp, N. J. (2000) Evaluation of online travel time estimators and predictors. Transportation Research Record 1719, TRB, National Research Council, Washington, D. C., 45–53.
22.Lint, J. W. C., Hoogendoorn, S. P. and Zuylen, H. J. (2002) Freeway travel time prediction with state-space neural networks. Transportation Research Record 1811, TRB, National Research Council, Washington, D. C., 30–39.
23.Lint, J. W. C., Hoogendoorn, S. P. and Zuylen, H. J. (2005) Accurate freeway travel time prediction with state-space neural networks under missing data, Transportation Research, Part C, 13(5-6), 347-369.
24.Lint, J. W. C. and Zijpp N. J. (2003) Improving a travel-time estimation algorithm by using dual loop detectors. Transportation Research Record 1855, TRB, National Research Council, Washington, D. C., 41–48.
25.Mahmassani, H. S. and Liu, Y. H. (1999) Dynamics of commuting decision behavior under advanced traveller information systems. Transportation Research, Part C, 7(2-3), 91–107.
26.McCulloch, W. S. and Pitts, W. (1943) A logical calculus of ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 5, 115-133.
27.Ministry of Transportation and Communications. (2006) Monthly Statistics of Transportation and Communications Republic of China. Department of Statistics, Ministry of Transportation and Communications.
28.Ministry of Transportation and Communications. (2003) Highway Travel Time Information and Management System Planning (1/4) – focusing on Freeway and Preliminary Study of Modeling. Institute of Transportation, Ministry of Transportation and Communications.
29.Mutapi, F., Mduluza, T. and Roddam, A. W. (2005) Cluster analysis of schistosome-specific antibody responses partitions the population into distinct epidemiological group. Immunology Letters, 96(2), 231-240.
30.Nakip, M. (1999) Segmenting the global market by usage rate of industrial products. Industrial Marketing Management, 28(2), 177-195.
31.Nam, D. and Mannering, F. (2000) An exploratory hazard-based analysis of highway accident duration. Transportation Research, Part A, 34(2), 85-102.
32.Palacharla, P. V. and Nelson, P. C. (1999) Application of fuzzy logic and neural networks for dynamic travel time estimation. International Transactions in Operational Research, 6(1), 145-160.
33.Park, D. and Rilett, L. (1998) Forecasting multiple-period freeway link travel times using modular neural networks. Transportation Research Record 1617, TRB, National Research Council, Washington, D. C., 163-170.
34.Park, D. and Rilett, L. R. (1999) Forecasting freeway link travel times with a multilayer feedforward neural network. Computer-Aided Civil and Infrastructure Engineering, 14(5), 357-367.
35.Park, D., Rilett, L. R. and Han, G. (1999) Spectral basis neural networks for real-time travel time forecasting. Journal of Transportation Engineering, 125(6), 515-523.
36.Penaloza, M. A. and Welch, R. M. (1996) Feature selection for classification of polar regions using a fuzzy expert system. Remote Sensing of Environment, 58(1), 81-100.
37.Questier, F., Walczak, B., Massart, D. L., Boucon, C. and Jong, S. D. (2002) Feature selection for hierarchical clustering. Analytica Chimica Acta, 466(2), 311-324.
38.Rice, J. and Zwet, E. V. (2004) A simple and effective method for predicting travel time on freeway. IEEE Transaction on Intelligent Transportation Systems, 5(3), 200-207.
39.Saporta, G. (2002) Data fusion and data grafting. Computational Statistics & Data analysis, 38(4), 465-473.
40.Sharma, S. (1996) Applied Multivariate Techniques. Willey, New York.
41.Shie, C. J. (2003) The study of traffic accident duration predicting models in freeway. Thesis, Department of Transportation Technology & Logistics Management Science, Chung hua University.
42.Tao, Y. C. (2004) A study on constructing traveler information service system architecture for expressway/highway network in Taiwan. Thesis, Department of Transportation & Communication Management Science, National Chen Kung University.
43.Wan, R. and Nakamura, H. (2002) Short term prediction works in traffic engineering: the state-of-the-art. Proceedings of the ninth ITS World Congress (CD-ROM), Chicago, USA.
44.Wei, C. H. and Chen, Y. C. (2001) Review of artificial neural network research and applications in transportation. Transportation Planning Journal Quarterly, 30(2), 324-348.
45.Wei, C. H. and Lee, Y. (2003) Development of freeway travel time forecasting models using artificial neural networks. Proceedings of the tenth ITS World Congress (CD-ROM), Madrid, Spain.
46.Wei, C. H. and Lee, Y. (2005) Appling data fusion techniques to traveler information services in highway network, Journal of the Eastern Asia Society for Transportation Studies, 6, 2457-2475.
47.Wu, H. C. (2004) The application of entropy on data fusion of traffic information. Thesis, Department of Transportation Technology & Management Science, National Chiao Tung University.
48.Xu, H. and Barth, M. (2006) Travel time estimation techniques for traffic information systems based on intervehicle communications. Transportation Research Record 1944, TRB, National Research Council, Washington, D. C., 72-81.
49.Zhang, X. and Rice, J. A. (2003) Short-term travel time prediction. Transportation Research, Part C, 11(3-4), 187-210.
50.Zurada, J. M. (1992) Introduction to Artificial Neural Systems. West publishing company, St. Paul.