對於一個上班族來說，每日上下班的通勤為生活中的一部份，不管是自己開車或搭乘大眾交通運輸工具，最惱人的不是遇上塞車而是對於現狀及未來交通狀況的不確定感。傳統上高速公路有警察廣播電台幫助高速公路上的駕駛了解前方路段的狀況供駕駛避免塞車路段，然而廣播多半只能以塞車等模糊字彙來形容交通狀況。在現代科技進步下，智慧型運輸系統設置感測器於高速公路上來偵測交通狀況。藉由這些感測器搜集的資料以及機器學習領域相關的研究，我們期望提供準確的交通狀況，例如:車輛平均速度，來提供給駕駛幫助他們做判斷是否要離開高速公路或是加速行駛通過路段以避免未來可能的堵塞。

此篇論文針對美國加洲高速公路資料做研究，其資料蒐集系統為PeMS。另外，論文中利用Gaussian Process為主要的方法來預測未來交通狀況，論文中也探討當前車況與歷史車況中的時間關係以及不同路段交通的關係來改善預測結果。

For a salaryman, commuting between home and office is a part of daily life. No matter what transportation you travel by, traffic jam is not the main factor which we feel depressed, but the unknown of the future traffic state let people restless. Traditionally, there are radio stations which help drivers to understand the forward segment traffic state by helicopters. However, the broadcast only can take some fuzzy glossary to describe the traffoc state. By modern technology, Intelligent Transportation Systemn(ITS) builds many detectors on freeway to detect traffic state. By these detectors, we prefer to provide more accuracy information, such as vehicle average travel speed, to help drivers make decision what should he leave the freeway to avoid the possible traffic jam or not.

This thesis focus on State of California freeway data, and the data is from Caltrans Performance Measurement System(PeMS). The main method which help us to predict traffic state is Gaussian Process and we also discuss the relationship between real-time data and historical data, the relationship between different segment to improve the prediction performance.

[1] N. L. Nihan and K. O. Holmesland, “Use of the box and jenkins time series technique in traffic fore-
casting,” Transportation, vol. 9, no. 2, pp. 125–143, 1980.
[2] M. S. Ahmed and A. R. Cook, “Analysis of freeway traffic time-series data by using box-jenkins
techniques,” Transportation Research Record, no. 722, 1979.
[3] B. M. Williams, P. K. Durvasula, and D. E. Brown, “Urban freeway traffic flow prediction: applica-
tion of seasonal autoregressive integrated moving average and exponential smoothing models,” Trans-
portation Research Record: Journal of the Transportation Research Board, vol. 1644, no. 1, pp. 132–
141, 1998.
[4] G. A. Davis and N. L. Nihan, “Nonparametric regression and short-term freeway traffic forecasting,”
Journal of Transportation Engineering, vol. 117, no. 2, pp. 178–188, 1991.
[5] B. L. Smith and M. J. Demetsky, “Traffic flow forecasting: comparison of modeling approaches,”
Journal of transportation engineering, vol. 123, no. 4, pp. 261–266, 1997.
[6] I. Okutani and Y. J. Stephanedes, “Dynamic prediction of traffic volume through kalman filtering
theory,” Transportation Research Part B: Methodological, vol. 18, no. 1, pp. 1–11, 1984.
[7] Y. Wang and M. Papageorgiou, “Real-time freeway traffic state estimation based on extended kalman
filter: a general approach,” Transportation Research Part B: Methodological, vol. 39, no. 2, pp. 141–
167, 2005.
[8] B. L. Smith and M. J. Demetsky, “Short-term traffic flow prediction: neural network approach,” Trans-
portation Research Record, no. 1453, 1994.
[9] B. Park, C. J. Messer, and T. Urbanik II, “Short-term freeway traffic volume forecasting using ra-
dial basis function neural network,” Transportation Research Record: Journal of the Transportation
Research Board, vol. 1651, no. 1, pp. 39–47, 1998.
[10] W. Zheng, D.-H. Lee, and Q. Shi, “Short-term freeway traffic flow prediction: Bayesian combined
neural network approach,” Journal of transportation engineering, vol. 132, no. 2, pp. 114–121, 2006.
[11] Y. Xie and Y. Zhang, “A wavelet network model for short-term traffic volume forecasting,” Journal
of Intelligent Transportation Systems, vol. 10, no. 3, pp. 141–150, 2006.
[12] M. Castro-Neto, Y.-S. Jeong, M.-K. Jeong, and L. D. Han, “Online-svr for short-term traffic flow
prediction under typical and atypical traffic conditions,” Expert systems with applications, vol. 36,
no. 3, pp. 6164–6173, 2009.
[13] Y. Zhang and Y. Xie, “Forecasting of short-term freeway volume with v-support vector machines,”
Transportation Research Record: Journal of the Transportation Research Board, vol. 2024, no. 1,
pp. 92–99, 2008.
53[14] C.-H. Wu, J.-M. Ho, and D.-T. Lee, “Travel-time prediction with support vector regression,” Intelligent
Transportation Systems, IEEE Transactions on, vol. 5, no. 4, pp. 276–281, 2004.
[15] Y. Xie, K. Zhao, Y. Sun, and D. Chen, “Gaussian processes for short-term traffic volume forecasting,”
Transportation Research Record: Journal of the Transportation Research Board, vol. 2165, no. 1,
pp. 69–78, 2010.
[16] C. Chen, “Freeway performance measurement system (pems),” California Partners for Advanced
Transit and Highways (PATH), 2003.