對於一個日常工作者來說，每天開車上班是很稀鬆平常的事。但若遇到道路壅塞的狀況時，總是讓人不樂預見的。因此若是有一個即時的道路狀況偵測系統的話，可以幫助工作者提前排除塞車路段並即時的到達目的地。
此篇論文主要是針對大尺度ITS感測器資料的預測，感測器的資料包含了速度、流量、佔有率的資訊，另外我們也根據附近的天氣偵測站獲取天氣資料。我們主要是蒐集各個異質的資料去準確的描述出現在這個車況。
針對大尺度資料的處理我們套用了MapReduce的運算框架去實現，在預測方法上我們考慮當前車況並從歷史資料中擷取相符合之模式。另外，我們更進一步的探討當前車況與歷史車況中的時間跟空間的關係並套用Gaussian process預測未來車流資料。

For routine workers, drive to work is a normal pattern in every day. If there is a congestion happened on his way to work, it is inconvenient to every one. Imagine that, if we have a real-time traffic forecasting system, it can help workers to avoid the road section which may happen traffic jam and the workers can reach destination on time.

This thesis focus on large scale ITS data prediction. The sensor data consist the information of speed, flow, and occupancy. In addition, we also obtain the weather data from the neighboring weather sensors. For precisely decribing the traffic condition, we consider the data from heterogeneous database. For processing massive data, we apply MapReduce framework to implement our method. In the traffic value prediction, we consider the current traffic condition and find the corresponding pattern from historical data. Moreover, we also consider the temporal and spatial relationship between current data and historical data. For building prediction model, Gaussian process is our modeling method.

[1] G. E. P. Box, G. M. Jenkins, and G. C. Reinsel, Time Series Analysis: Forecasting and Control. Wiley,
4 ed., 2008.
[2] 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.
[3] L. Mihaylova, R. Boel, and A. Hegyi, “Freeway traffic estimation within particle filtering framework,”
Automatica, vol. 43, no. 2, pp. 290–300, 2007.
[4] 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.
[5] J. Wang and Q. Shi, “Short-term traffic speed forecasting hybrid model based on chaos - wavelet
analysis-support vector machine theory,” Transportation Research Part C: Emerging Technologies,
vol. 27, pp. 219–232, 2013.
[6] C. Chen, Z. Liu, W.-H. Lin, S. Li, and K. Wang, “Distributed modeling in a mapreduce framework
for data-driven traffic flow forecasting,” Intelligent Transportation Systems, IEEE Transactions on,
vol. 14, no. 1, pp. 22–33, 2013.
[7] X. Min, J. Hu, Q. Chen, T. Zhang, and Y. Zhang, “Short-term traffic flow forecasting of urban network
based on dynamic starima model,” in Intelligent Transportation Systems, 2009. ITSC’09. 12th
International IEEE Conference on, pp. 1–6, IEEE, 2009.
[8] B. Sharma, R. Prabhakar, S. Lim, M. T. Kandemir, and C. R. Das, “Mrorchestrator: A fine-grained
resource orchestration framework for mapreduce clusters,” in Cloud Computing (CLOUD), 2012 IEEE
5th International Conference on, pp. 1–8, IEEE, 2012.
[9] J. Polo, C. Castillo, D. Carrera, Y. Becerra, I. Whalley, M. Steinder, J. Torres, and E. Ayguade,
“Resource-aware adaptive scheduling for mapreduce clusters,” in Middleware 2011, pp. 187–207,
Springer, 2011.
[10] J. Dean and S. Ghemawat, “Mapreduce: simplified data processing on large clusters,” Communications
of the ACM, vol. 51, no. 1, pp. 107–113, 2008.
[11] “Research data exchange.” https://www.its-rde.net/home.
[12] “Caltrans performance measurement system.” http://pems.dot.ca.gov/.
[13] C. E. Rasmussen, “Gaussian processes for machine learning,” MIT Press, 2006.
[14] C.-C. Chang and C.-J. Lin, “Libsvm: a library for support vector machines,” ACM Transactions on
Intelligent Systems and Technology (TIST), vol. 2, no. 3, p. 27, 2011.