因為路側單元(Roadside Unit, RSU)的建置價格昂貴，如何在佈置少量RSU的環境下，可以準確地利用蒐集到的車流資訊來判斷是否有路段發生Incident的情況是很重要的。本論文提出一個系統可以在佈置少量RSU的環境下，利用RSU蒐集一段時間內的部分車流資訊後，根據所觀察到的異常交通流量變化以Data Mining的技巧準確地分析出地圖中是否有發生Incident。為了可以計算出每個路段上的交通流量，本系統使用Frequent Path tree的資料結構來儲存每台車輛的行車資訊，用Frequent Path tree當作資料結構來整合這段時間的資訊不僅節省了儲存大量資料所需的空間，更能有效率地將毫無規則的path list有系統地整理起來，再經由Incident Detection演算法，偵測出發生Incident的路段並提供意外事故的相關訊息。論文最後提供了根據各項參數的不同設定值所繪製的系統效能分析圖以提供使用者做為參數設定的參考。

Due to the high cost of Roadside Unit (RSU), it is important to collect traffic flow data under the environment with few RSUs. In this article, we introduce a system which can detect the occurring of incident by examining the exceptional traffic flow. In order to get the traffic volume regarding each road segment, we use the data structure called Frequent Path Tree to store the information which we collect from vehicles on roads. It can regularly save a large number of traffic flow data and arrange scrambled path lists effectively. By executing the algorithm of incident detection, our system can precisely detect the occurring of incident and send a false alarm to user. We provide figures about efficiency analysis using various parameters to user to set parameters suitably.

[1] S. Dornbush and A. Joshi, 「StreetSmart traffic: Discovering and disseminating automobile congestion using VANET's,」 Proc. IEEE Vehicular Technology Conference, (Dublin, Ireland), pages 11-15, April 2007.
[2] F. Dehne, M.T. Omran, J. Sack, 「Shortest paths in time-dependent FIFO networks using edge load forecasts,」 In Proceedings of the Second International Workshop on Computational Transportation Science, 2009.
[3] H. Zhou, S. Mabu, K. Shimada, K. Hirasawa, 「Generalized Time Related Sequential Association rule mining and traffic prediction,」 Proc. of the IEEE Congress on Evolutionary Computation 2009, pp.2654-2661, 2009.
[4] J. Han, J. Pei, and Y. Yin, "Mining Frequent Patterns without Candidate Generation," Proc. 2000 ACM-SIGMOD Int'l Conf. Management of Data (SIGMOD 』00), pp. 1-12, May 2000.
[5] J. Han, J. Pei, Y. Yin, and R. Mao, "Mining Frequent Patterns without Candidate Generation: A Frequent-Pattern Tree Approach," Data Mining and Knowledge Discovery, vol. 8, no.1, pp. 53-87, 2004.
[6] Kawuu W. Lin, Ming-Hua Hsieh and Vincent S. Tseng, "A Novel Prediction-based Strategy for Object Tracking in Sensor Networks by Mining Seamless Temporal Movement Patterns," Expert Systems with Applications, Vol. 37, No. 4, pp. 2799-2807, 2010.
[7] M. Ester, H.P. Kriegel, S. Jörg, X. Xu, 「A density-based algorithm for discovering clusters in large spatial databases with noise,」 Proc. second International Conference on Knowledge Discovery and Data Mining , pp. 226-231, 1996.
[8] M. Abuelela, S. Olariu, 「Enhancing Automatic Incident Detection Techniques Through Vehicle To Infrastructure Communication,」 Proc. 11th International IEEE Conference on Intelligent Transportation Systems, Oct. 12-15, 2008, Beijing, China, October 2008.
[9] M. Abuelela and S. Olariu, "A Probabilistic Technique for Detecting Permanent and Temporary Incidents in VANETs," Proc. 6th International Workshop on Intelligent Transportation , WIT. Hamburg, Germany, March 2009.
[10] H. Moustafa, Y. Zhang, 「Vehicular Networks: Techniques, Standards and Applications.」 CRC Press, 2009.
[11] R. Agrawal, R. Srikant, 「Fast Algorithms for Mining Association Rules in Large Databases,」 Proc. 20th International Conference on Very Large Data Bases, pages 478-499, September 1994.
[12] S. Guha, R. Rastogi, and K. Shim, 「CURE: an efficient clustering algorithm for large databases,」 Proc. 1998 ACM SIGMOD international conference on Management of data, 1998.
[13] SUMO: Simulation of UrBan Mobility, 「http://sumo.sourceforge.net/". 2011.
[14] F. Salim, S.W. Loke, A. Rakotonirainy, B. Srinivasan, and S. Krishnaswamy, "Collision Pattern Modeling and Real-Time Collision Detection at Road Intersections," Proc. of The 10th International IEEE Conference on Intelligent Transportation Systems, Seattle, Washington, USA , IEEE Computer Society Press, 2007.
[15] S.R. Hu and C.M. Wang, 「Vehicle Detector Deployment Strategies for the Estimation of Network Origin–Destination Demands Using Partial Link Traffic Counts,」 Intelligent Transportation Systems, IEEE Transactions on, vol. 9, pp. 288-300, 2008
[16] TIGER: Topologically Integrated Geographic Encoding and Referencing System, 「http://www.icpsr.umich.edu/TIGER/2006se/." 2011.
[17] T. Nakata, J.I. Takeuchi, 「Mining traffic data from probe-car system for travel time prediction,」 Proc. 10th ACM SIGKDD international conference on Knowledge discovery and data mining, pp.817-822, 2004.
[18] X. Xu , M. Ester , H.P. Kriegel, and, J. Sander, 「A Distribution-Based Clustering Algorithm for Mining in Large Spatial Databases.」, Proc. 14th International Conference on Data Engineering, 1998
[19] Y.K. Ki, D.Y. Lee, "A Traffic Accident Recording and Reporting Model at Intersections," Proc. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, vol. 8, no. 2, pp. 188–194, Jun. 2007.
[20] Y. Ji, W. Daamen, X. Zhang, L. Sun, "Traffic incident recovery time prediction model based on cell transmission model," Proc. Intelligent Transportation Systems 2009 ITSC 09 12th International IEEE, pp. 1–4, 2009.
[21] Y. Yang, R. Bagrodia, 「Evaluation of VANET-based advanced intelligent transportation systems,」 Proc. 6th ACM international workshop on VehiculAr InterNETworking, pp. 3–12, 2009.
[22] M. Abuelela and S. Olariu, 「Automatic Incident Detection in VANETs: A Bayesian Approach,」 Proc. IEEE 69th Vehicular Technology Conference, 2009. VTC Spring 2009., April 2009, pp. 1-5.
[23] B. Khorashadi, F. Liu, D. Ghosal, M. Zhang, and C.N. Chuah "Distributed automated incident detection with VGRID,」 IEEE Wireless Communication Magazine, vol. 18, no.1, pp. 64-73, February 2011.
[24] N. Persaud, F. L. Hall, and L. M. Hall, 「Congestion Identification Aspects of the McMaster Incident Detection Algorithm,」 Transportation Research Record, tech. rep. 1287, pp. 167–75, 1990.