Öz

In this study we predict traffic speed on Istanbul roads using RTMS (Remote Traffic Microwave Sensor) speed measurements obtained from the Istanbul Municipality web site from 327 different sensor locations. We do speed predictions 5 minutes to an hour ahead and use SVM (Support Vector Machine) and kNN (k Nearest Neighbor) methods for speed prediction. We find out which other sensors could be used to predict the speed at a certain sensor location and show that especially for nearby/correlated sensors, it is possible to get better results using related sensor measurements in addition to the sensor being predicted.

Örüntü Tanıma ve Öznitelik Seçme Yöntemleri Kullanarak Kısa Zaman Sonraki Yol Trafik Hız Öngörüsü

Öz

Bu çalışmada İstanbul Büyükşehir Belediyesi’nin web sitesininden alınan RTMS (Remote Traffic Microwave Sensor) cihazlarının hız ölçüm değerleri kullanılarak ileriye yönelik trafik hızı tahmin edilmiştir. Örüntü tanıma yöntemi olarak k-En Yakın Komşu (kNN) ve Karar Destek Makinesi (SVM) kullanılmıştır. Bir sensöre ait hız verilerinin değişik zamanlarda alınarak yapılan trafik hızı öngörüsüne ek olarak bu sensöre yakın sensörlerin hız bilgileri alınarak ve yüksek bağıntıya sahip sensörlerin hız bilgileri alınarak hız öngörüsü yapılmıştır. Yapılan testler sonucunda genel olarak SVR metodunun KNN metodundan daha başarılı olduğu görülmüştür. Yakın konumlardaki veya yüksek bağıntılı sensör verisi kullanılarak yapılan tahminlerin ise bir sensör verisi kullanılarak yapılan tahminlerden daha iyi sonuç verdiği görülmüştür.

Kaynakça

1. [1] Alpaydin, E., 2004, ``Introduction to Machine Learning'', MIT Press.
2. [2] Bin, Y., Zhongzhen, Y. Baozhen, Y., 2006, "Bus Arrival Time Prediction Using Support Vector Machines", Journal of Intelligent Transportation Systems, Volume 10, Issue 4 October 2006 , pages 151 – 158.
3. [3] Burges, C.J.C., 1998, "A Tutorial on Support Vector Machines for Pattern Recognition", Data Mining and Knowledge Discovery, Vol. 2, Number 2, p. 121-167.
4. [4] Chrobok, R., Kaumann, O., Wahle, J., Schreckenberg, M., 2000, “Three Categories of Traffic Data: Historical, Current, and Predictive”, the 9th IFAC Syposium Control in Transportation Sytems, 250-25.
5. [5] Hobeika, A.G. and Kim, C.K., 1994, "Trafficflow-prediction systems based on upstream traffic", Proceedings of Vehicle Navigation and Information Systems Conference, 31 Aug-2 Sep 1994, 345 – 350.
6. [6] Kwon, J., Coifman, B., Bickel, P., 2000, ``Day-to-day travel time trends and travel time prediction from loop detector data'', Transportation Research Record, (1554).
7. [7] Lingras, P., and Mountford, P., 2001, "Time Delay Neural Networks Designed Using Genetic Algorithms for Short Term Inter-City Traffic Forecasting Engineering of Intelligent Systems", 14th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, IEA/AIE 2001, Budapest, Hungary, June 4-7, Proceedings, page 390, 2001.
8. [8] Mark, C.D., Sadek, A.W., Rizzo, D., 2004,"Predicting experienced travel time with neural networks: a PARAMICS simulation study", Intelligent Transportation Systems. Proceedings. The 7th International IEEE Conference on Volume , Issue , 3-6 Oct. 2004 Page(s): 906 - 911

9. [9] Park, D., and Ritett, L. R., 1998, “Forecasting Multiple-Period Freeway Link Travel Times Using Modular Neural Networks,” 77th Annual Meeting of the Transportation Research Board, Washington, D.C., January 1998.
10. [10] 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.
11. [11] Rice, J., van Zwet, E., 2001, “A simple and effective method for predicting travel times on freeways'', Intelligent Transp. Systems, IEEE Proceedings, 227 -232.
12. [12] Ruping, S., 2004, ”mySVM software”, Available: http://www-ai.cs.unidortmund.de/SOFTWARE/MYSVM
13. [13] Sun, H., Liu, H., and Ran, B., 2003,“Short Term Traffic Forecasting Using the Local Linear Regression Model”, Transportation Research Record.
14. [14] W.C.Van Lint, W.C., Hoogendoorn, S.P., and van Zuylen, H.J., 2000, “Robust and adaptive travel time prediction with neural networks,” Proceedings of the 6th annual TRAIL Congress (part 2), December 2000.
15. [15] Wu, C.H., Ho, J.M., D.T., Lee, 2004, "Traveltime prediction with support vector regression", Intelligent Transportation Systems, 5(4), 276 – 28, Dec. 2004.
16. [16] Zhang, Z., Rice, J., and Bickel, P., 1999, “Empirical Comparison of Travel Time Estimation Methods”, Report for MOU 353, UCB-ITS-PRR-99- 43, ISSN1055-1425, December 1999