建立準確的預測模型對於軌道系統之營運管理有重要助益，營運單位能藉由提前掌握未來時段之旅運需求以設計短期營運規劃提升服務品質並使資源配置更有效率，也可以做為調整列車計畫或乘務人員排班之考量依據。因此本研究以台灣鐵路管理局之客運市場做為研究對象，收集台鐵之歷史交易紀錄並使用人工智慧方法建構一個售票預測模型，欲建立之預測模型以支持向量回歸(Support Vector Regression)為基礎，使用貝葉斯優化超參數，並增加時間向量作為新的超參數來增加模型預測性能。我們使用十組不同起訖資料進行驗證，並比較三種不同超參數優化模型，結果顯示提出之模型有優於其他模型之表現，且能以有效率的方式達到更好的結果。

Short-term passenger flow forecasting models can offer essential revenue management benefits, and the forecasting results can be used by operators to design short-term operation planning or crew planning programs, which can improve service quality and make resource allocation more efficient. Therefore, this study presents a new railway booking prediction model, which is based on an artificial intelligence method, Support Vector Regression, and Bayesian hyperparameters optimization. Furthermore, we add time vectors as new hyperparameters to increase model prediction performance. To build the model, we use actual historical transaction records from the Taiwan Railways Administration. The results show that our model has better performance than other methods and is more efficient.

[1] Andreoni, A., & Postorino, M. N. (2006). A multivariate ARIMA model to forecast air transport demand. Proceedings of the Association for European Transport and Contributors, 1-14.
[2] Bao, Y., Hu, Z., & Xiong, T. (2013). A PSO and pattern search based memetic algorithm for SVMs parameters optimization. Neurocomputing, 117, 98-106.
[3] Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of Machine Learning Research, 13(Feb), 281-305.
[4] Bergstra, J., Yamins, D., & Cox, D. D. (2013). Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures. Proceeding in the JMLR Workshop and Conference, 115–123.
[5] Bergstra, J. S., Bardenet, R., Bengio, Y., & Kégl, B. (2011). Algorithms for hyper-parameter optimization. Paper presented at the Advances in neural information processing systems.
[6] Billings, D., & Yang, J.-S. (2006). Application of the ARIMA models to urban roadway travel time prediction-a case study. Paper presented at the Systems, Man and Cybernetics, 2006. SMC'06. IEEE International Conference on.
[7] Bin, Y., Zhongzhen, Y., & Baozhen, Y. (2006). Bus arrival time prediction using support vector machines. Journal of Intelligent Transportation Systems, 10(4), 151-158.
[8] Chapelle, O., Vapnik, V., Bousquet, O., & Mukherjee, S. (2002). Choosing multiple parameters for support vector machines. Machine learning, 46(1-3), 131-159.
[9] Chen, C., Wang, Y., Li, L., Hu, J., & Zhang, Z. (2012). The retrieval of intra-day trend and its influence on traffic prediction. Transportation Research Part C: Emerging Technologies, 22, 103-118.
[10] Chien, S. I.-J., & Kuchipudi, C. M. (2003). Dynamic travel time prediction with real-time and historic data. Journal of transportation engineering, 129(6), 608-616.
[11] Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3), 273-297.
[12] Ding, A., Zhao, X., & Jiao, L. (2002). Traffic flow time series prediction based on statistics learning theory. Paper presented at the Intelligent Transportation Systems, 2002. Proceedings. The IEEE 5th International Conference on.
[13] Friedrichs, F., & Igel, C. (2005). Evolutionary tuning of multiple SVM parameters. Neurocomputing, 64, 107-117.
[14] Ghomi, H., Bagheri, M., Fu, L., & Miranda-Moreno, L. F. (2016). Analyzing injury severity factors at highway railway grade crossing accidents involving vulnerable road users: A comparative study. Traffic injury prevention, 17(8), 833-841.
[15] Ghosh, B., Basu, B., & O’Mahony, M. (2005). Time-series modelling for forecasting vehicular traffic flow in Dublin. Paper presented at the 84th Annual Meeting of the Transportation Research Board, Washington, DC.
[16] Goodfellow, I., Bengio, Y., Courville, A., & Bengio, Y. (2016). Deep learning (Vol. 1): MIT press Cambridge.
[17] Guo, Y.-h., Shi, X.-p., & Zhang, X.-d. (2010). A study of short term forecasting of the railway freight volume in China using ARIMA and Holt-Winters models. Paper presented at the Supply Chain Management and Information Systems (SCMIS), 2010 8th International Conference on.
[18] Hamed, M. M., Al-Masaeid, H. R., & Said, Z. M. B. (1995). Short-term prediction of traffic volume in urban arterials. Journal of transportation engineering, 121(3), 249-254.
[19] Hong, W.-C., Dong, Y., Zheng, F., & Lai, C.-Y. (2011). Forecasting urban traffic flow by SVR with continuous ACO. Applied Mathematical Modelling, 35(3), 1282-1291.
[20] Hsu, C.-W., Chang, C.-C., & Lin, C.-J. (2003). A practical guide to support vector classification.
[21] Hu, S.-R., Madanat, S. M., Krogmeier, J. V., & Peeta, S. (2001). Estimation of dynamic assignment matrices and OD demands using adaptive Kalman filtering. Journal of Intelligent Transportation Systems, 6(3), 281-300.
[22] Huang, C.-L. (2009). ACO-based hybrid classification system with feature subset selection and model parameters optimization. Neurocomputing, 73(1-3), 438-448.
[23] Huang, M.-L. (2015). Intersection traffic flow forecasting based on ν-GSVR with a new hybrid evolutionary algorithm. Neurocomputing, 147, 343-349.
[24] Hutter, F., Hoos, H. H., & Leyton-Brown, K. (2011). Sequential model-based optimization for general algorithm configuration. Paper presented at the International Conference on Learning and Intelligent Optimization.
[25] Ishak, S., Kotha, P., & Alecsandru, C. (2003). Optimization of dynamic neural network performance for short-term traffic prediction. Transportation Research Record: Journal of the Transportation Research Board(1836), 45-56.
[26] Karlaftis, M. G., & Vlahogianni, E. I. (2011). Statistical methods versus neural networks in transportation research: Differences, similarities and some insights. Transportation Research Part C: Emerging Technologies, 19(3), 387-399.
[27] Kecman, V. (2001). Learning and soft computing: support vector machines, neural networks, and fuzzy logic models: MIT press.
[28] Lee, A. O. (1990). Airline reservations forecasting: Probabilistic and statistical models of the booking process. Retrieved from
[29] Lee, W.-H., Yen, L.-H., & Chou, C.-M. (2016). A delay root cause discovery and timetable adjustment model for enhancing the punctuality of railway services. Transportation Research Part C: Emerging Technologies, 73, 49-64.
[30] Lewis, C. D. (1982). Industrial and business forecasting methods: A practical guide to exponential smoothing and curve fitting: Butterworth-Heinemann.
[31] Lin, S.-W., Ying, K.-C., Chen, S.-C., & Lee, Z.-J. (2008). Particle swarm optimization for parameter determination and feature selection of support vector machines. Expert Systems with Applications, 35(4), 1817-1824.
[32] Liu, X., Huang, X., Chen, L., Qiu, Z., & Chen, M. (2017). Improving the Forecasting Accuracy of Civil Aviation Passengers Based on Machine Learning Models. Paper presented at the Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC), 2017 International Conference on.
[33] Marković, N., Milinković, S., Tikhonov, K. S., & Schonfeld, P. (2015). Analyzing passenger train arrival delays with support vector regression. Transportation Research Part C: Emerging Technologies, 56, 251-262.
[34] Meng, J., & Yang, Z. (2006). Civil aviation passenger traffic volume forecasting based on fuzzy diagonal regression neural networks. Paper presented at the Computational Engineering in Systems Applications, IMACS Multiconference on.
[35] Nihan, N. L., & Holmesland, K. O. (1980). Use of the Box and Jenkins time series technique in traffic forecasting. Transportation, 9(2), 125-143.
[36] Queen, C. M., & Albers, C. J. (2009). Intervention and causality: forecasting traffic flows using a dynamic Bayesian network. Journal of the American Statistical Association, 104(486), 669-681.
[37] Russell, S. J., & Norvig, P. (2016). Artificial intelligence: a modern approach: Malaysia; Pearson Education Limited.
[38] Smith, B. L., Williams, B. M., & Keith Oswald, R. (2002). Comparison of parametric and nonparametric models for traffic flow forecasting. Transportation Research Part C: Emerging Technologies, 10(4), 303-321.
[39] Smith, B. L., Williams, B. M., & Oswald, R. K. (2002). Comparison of parametric and nonparametric models for traffic flow forecasting. Transportation Research Part C: Emerging Technologies, 10(4), 303-321.
[40] Snoek, J., Larochelle, H., & Adams, R. P. (2012). Practical bayesian optimization of machine learning algorithms. Paper presented at the Advances in neural information processing systems.
[41] Stathopoulos, A., & Karlaftis, M. G. (2003). A multivariate state space approach for urban traffic flow modeling and prediction. Transportation Research Part C: Emerging Technologies, 11(2), 121-135.
[42] Sun, L., Lu, Y., Jin, J. G., Lee, D.-H., & Axhausen, K. W. (2015). An integrated Bayesian approach for passenger flow assignment in metro networks. Transportation Research Part C: Emerging Technologies, 52, 116-131.
[43] Sun, S., Zhang, C., & Yu, G. (2006). A Bayesian network approach to traffic flow forecasting. IEEE Transactions on intelligent transportation systems, 7(1), 124-132.
[44] Tavakkoli, A., Rezaeenour, J., & Hadavandi, E. (2015). A novel forecasting model based on support vector regression and bat meta-heuristic (Bat–SVR): case study in printed circuit board industry. International Journal of Information Technology & Decision Making, 14(01), 195-215.
[45] Vanajakshi, L., & Rilett, L. R. (2007). Support vector machine technique for the short term prediction of travel time. Paper presented at the Intelligent Vehicles Symposium, 2007 IEEE.
[46] Wang, Y., & Papageorgiou, M. (2005). Real-time freeway traffic state estimation based on extended Kalman filter: a general approach. Transportation Research Part B: Methodological, 39(2), 141-167.
[47] Wei, Y., & Chen, M.-C. (2012). Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks. Transportation Research Part C: Emerging Technologies, 21(1), 148-162.
[48] Whittaker, J., Garside, S., & Lindveld, K. (1997). Tracking and predicting a network traffic process. International Journal of Forecasting, 13(1), 51-61.
[49] Williams, B., Durvasula, P., & Brown, D. (1998). Urban freeway traffic flow prediction: application of seasonal autoregressive integrated moving average and exponential smoothing models. Transportation Research Record: Journal of the Transportation Research Board(1644), 132-141.
[50] Williams, B. M., & Hoel, L. A. (2003). Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: Theoretical basis and empirical results. Journal of transportation engineering, 129(6), 664-672.
[51] Yang, C., & Létourneau, S. (2009). Two-stage classifications for improving time-to-failure estimates: a case study in prognostic of train wheels. Applied Intelligence, 31(3), 255.
[52] Ye, Y., & Lu, Z.-L. (2009). Neural network short-term traffic flow forecasting model based on particle swarm optimization. Computer Engineering and Design, 30(18), 4296-4298.
[53] Zhang, G., Patuwo, B. E., & Hu, M. Y. (1998). Forecasting with artificial neural networks:: The state of the art. International Journal of Forecasting, 14(1), 35-62.
[54] Zhang, L., Liu, Q., Yang, W., Wei, N., & Dong, D. (2013). An improved k-nearest neighbor model for short-term traffic flow prediction. Procedia-Social and Behavioral Sciences, 96, 653-662.