×

Bus arrival time prediction using support vector machines. (English) Zbl 1130.90320

Summary: Effective prediction of bus arrival time is central to many advanced traveler information systems. This article presents support vector machines (SVM), a new neural network algorithm, to predict bus arrival time. The objective of this paper is to examine the feasibility and applicability of SVM in vehicle travel time forecasting area. Segment, the travel time of current segment, and the latest travel time of next segment are taken as three input features. Bus arrival time predicted by the SVM is assessed with the data of transit route number 4 in Dalian economic and technological development zone in China and conclusions are drawn.

MSC:

90B20 Traffic problems in operations research
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Cao, L. and Francis, E. and Tay. (2003) Support vector machine with adaptive parameters in financial time series forecasting <i>IEEE Transactions on Neural Networks</i>, 14(6), pp. 1506 - 1518. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=1045-9227&vol=14&iss=6&firstpage=1506” target=”new”>[CSA]</a>
[2] Cao, L. and Tay, F. (2001) Financial forecasting using support vector machines <i>Neural Comput. Appl.</i>, 10, pp. 184 - 192. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=0941-0643&vol=10&iss=&firstpage=184” target=”new”>[CSA]</a><a href=”http://dx.doi.org/10.1007 · Zbl 1002.68689
[3] Chen, M. and Liu, X. and Xia, J. and Chien, S. (2004) A dynamic bus-arrival time prediction model based on APC data <i>Computer-Aided Civil and Infrastructure Engineering</i>, 19, pp. 364 - 376. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=1093-9687&vol=19&iss=&firstpage=364” target=”new”>[CSA]</a><a href=”http://dx.doi.org/10.1111
[4] Chien, I-Jy. and Ding, Y. and Wei, C. (2002) Dynamic bus arrival time prediction with artificial neural networks <i>Journal of Transportation Engineering, ASCE</i>, 128(5), pp. 429 - 38. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=&vol=128&iss=&firstpage=429” target=”new”>[CSA]</a>
[5] Cristianini, N. and Taylor, J.(2000) <i> An introduction to support vector machines and other kernel-based learning methods</i>. New York : Cambridge University Press. · Zbl 0994.68074
[6] Dailey, D. and Maclean, S. and Cathey, F. and Wall, Z. (2001) Transit vehicle arrival prediction: Algorithm and large-scale implementation <i>Journal of the Transportation Research Board</i>, 1771, pp. 46 - 51. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=&vol=1771&iss=&firstpage=46” target=”new”>[CSA]</a>
[7] DeLurgio, S.(1998) <i> Forecasting Principles and Applications</i>. New York : McGraw-Hill.
[8] Ding, Y. and Chien, S.(2000). The prediction of bus arrival times with link-based artificial neural networks. <i> <i>Proceedings of the International Conference on Computational Intelligence & Neurosciences (CI&N)–Intelligent Transportation Systems</i> . </i> In [ pp. 730 - 733] . .
[9] Dong, B. and Cao, C. and Lee, S. (2005) Applying support vector machines to predict building energy consumption in tropical region <i>Energy and Buildings</i>, 37, pp. 545 - 553. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=0378-7788&vol=37&iss=&firstpage=545” target=”new”>[CSA]</a><a href=”http://dx.doi.org/10.1016
[10] Federal Transit Administration.(1998) <i> Advanced Public Transportation Systems: The State of the Art</i>. Washington DC: U.S. Department of Transportation. Update 1998. Rep.
[11] Hagan, M. and Demuth, H. and Beale, M.(1996) <i> Neural Network Design</i>. Boston : PWS.
[12] Hastie, T. and Tibshirani, R. and Friedman, J.(2001) <i> The Elements of Statistical Learning: Data Mining, Inference and Prediction</i>. New York : Springer-Verlag. · Zbl 0973.62007
[13] Hsu, C. and Chang, C. and Lin, C.(2003) A practical guide to support vector classification, technical report. In <i>Department of Computer Science and Information Engineering</i>. . Taipei : National Taiwan University. Available at <a href=”http://www.csie.ntu.edu.tw/cjlin/papers/guide/guide.pdf” target=”new”>http://www.csie.ntu.edu.tw/cjlin/papers/guide/guide.pdf</a>
[14] Keerthi, S. and Lin, C. (2001) Asymptotic behaviors of support vector machines with gaussian kernel <i>Neural Computation</i>, 15(7), pp. 1667 - 1689. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=0899-7667&vol=15&iss=7&firstpage=1667” target=”new”>[CSA]</a><a href=”http://dx.doi.org/10.1162
[15] Lawrence, S. and Giles, C. and Tsoi, A.(1997). Lessons in neural network training: Overfitting may be harder than expected. <i> <i>Proceedings of the Fourteenth National Conference on Artificial Intelligence</i> . </i> In [ pp. 540 - 545] . . AAAl-97
[16] Lin, H. and Lin, C.(2003) A Study on Sigmoid Kernels for SVM and the Training of Non-PSD Kernels by SMO-type Methods, Technical report. In <i>Department of Computer Science and Information Engineering</i>. . National Taiwan University. Available at <a href=”http://www.csie.ntu.edu.tw/cjlin/papers/tanh.pdf” target=”new”>http://www.csie.ntu.edu.tw/cjlin/papers/tanh.pdf</a>
[17] Moller, M. (1993) A scaled conjugate gradient algorithm for fast supervised learning <i>Neural Networks</i>, 6, pp. 523 - 533. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=0893-6080&vol=6&iss=&firstpage=523” target=”new”>[CSA]</a><a href=”http://dx.doi.org/10.1016
[18] Moody, J. (1992) The effective number of parameters: An analysis of generalization and regularization in nonlinear learning systems <i>NIPS</i>, 4, pp. 847 - 854. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=&vol=4&iss=&firstpage=847” target=”new”>[CSA]</a>
[19] Mukherjee, S. and Osuna, E. and Girosi, F.(1997). Nonlinear Prediction of Chaotic Time Series Using Support Vector Machines. <i> <i>NNSP1997: Neural Networks for Signal Processing VII: Proceedings of the IEEE Signal Processing Society Workshop</i> Amelia IslandFL. </i> In [ pp. ] . .
[20] Muller, K. and Smola, J. and Ratsch, G. and Scholkopf, B. and Kohlmorgen, J.(1999) Using support vector machines for time series prediction. In <i>Advances in Kernel Methods–Support Vector Learning</i>. ( pp. 243 - 254 ). Cambridge MA: MIT Press.
[21] Muller, K. and Smola, J. and Ratsch, G. and Scholkopf, B. and Kohlmorgen, J. and Vapnik, V.(1997). Predicting time series with support vector machines. <i> <i>ICANN1997: Proceedings of the Seventh International Conference on Artificial Neural Networks</i> LausanneSwitzerland. </i> In [ pp. 999 - 1004] . .
[22] Okutani, I. and Stephanedes, Y. (1984) Dynamic prediction of traffic volume through kalman filtering theory <i>Transp. Res.</i>, 18B(1), pp. 1 - 11. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=1366-5545&vol=18B&iss=1&firstpage=1” target=”new”>[CSA]</a><a href=”http://dx.doi.org/10.1016
[23] Park, D. and Rilett, L. (1999) Forecasting freeway link travel times with a multilayer feedforward neural network <i>Computer-Aided Civil and Infrastructure Engineering</i>, 14(5), pp. 357 - 367. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=1093-9687&vol=14&iss=5&firstpage=357” target=”new”>[CSA]</a><a href=”http://dx.doi.org/10.1111
[24] Ren, J. and Ou, X. and Zhang, Y. and Hu, D.(2002). Research on networklevel traffic pattern recognition. <i> <i>Proc. IEEE 5th Int. Conf. Intelligent Transportation Systems</i> . </i> In [ pp. 500 - 504] . .
[25] Reyna, R. and Giralt, A. and Esteve, D.(2001). Head detection inside vehicles with a modified SVM for safer airbags. <i> <i>Proc. IEEE 4th Int. Conf. Intelligent Transportation Systems</i> . </i> In [ pp. 500 - 504] . .
[26] Sansom, D. and Downs, T. and Saha, T. (2002) Evaluation of support vector machine based forecasting tool in electricity price forecasting for Australian National Electricity Market participants <i>J. Elect. Electron. Eng. Austr.</i>, 22, pp. 227 - 234. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=0725-2986&vol=22&iss=&firstpage=227” target=”new”>[CSA]</a>
[27] Sarle, W.(1995). Stopped training and other remedies for overfitting. <i> <i>Proceedings of the twenty-seventh symposium on the interface of computing science and statistics</i> . </i> In [ pp. 352 - 360] . .
[28] Shalaby, A. and Farhan, A.(2003). Bus travel time prediction model for dynamic operations control and passenger information systems. <i> <i>The 82nd Annual Meeting of the Transportation Research Board</i> WashingtonDC. </i> In [ pp. ] . . CD-ROM
[29] Smith, B. and Demetsky, M. (1995) Short-term traffic flow prediction: Neural network approach <i>Transportation Research Record</i>, 1453, pp. 98 - 104. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=0361-1981&vol=1453&iss=&firstpage=98” target=”new”>[CSA]</a>
[30] Stephanedes, Y. and Kwon, E. and Michalopoulos, P. (1990) On-line diversion prediction for dynamic control and vehicle guidance in freeway corridors <i>Transportation Research Record</i>, 1287, pp. 11 - 19. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=0361-1981&vol=1287&iss=&firstpage=11” target=”new”>[CSA]</a>
[31] Sun, Z. and Bebis, G. and Miller, R.(2002). Improving the performance of on-road vehicle detection by combining Gabor and wavelet features. <i> <i>Proc. IEEE 5th Int. Conf. Intelligent Transportation Systems</i> . </i> In [ pp. 130 - 135] . .
[32] Tay, F. and Cao, L. (2001) Improved 3nancial time series forecasting by combining support vector machines with self-organizing feature map <i>Intelligent Data Analysis</i>, 5, pp. 1 - 16. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=1088-467X&vol=5&iss=&firstpage=1” target=”new”>[CSA]</a>
[33] University of Southampton.(2005) <i> Electronics and computer science: Support vector machines</i>. <a href=”http://www.isis.ecs.soton.ac.uk/resources/svminfo/” target=”new”>http://www.isis.ecs.soton.ac.uk/resources/svminfo/</a>
[34] Vapnik, V. (1999) An overview of statistical learning theory <i>IEEE Transactions on Neural Networks</i>, 10(5), pp. 988 - 999. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=1045-9227&vol=10&iss=5&firstpage=988” target=”new”>[CSA]</a><a href=”http://dx.doi.org/10.1109
[35] Vapnik, V.(2000) <i> The nature of statistical learning theory</i>. New York : Springer. · Zbl 0934.62009
[36] Wei, C. and Wu, K. (1997) Developing intelligent freeway ramp metering control systems <i>Conf. Proc., National Science Council in Taiwan</i>, 7C(3), pp. 371 - 389. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=&vol=7C&iss=5&firstpage=371” target=”new”>[CSA]</a>
[37] Weigend, A.(1994). On overfitting and the effective number of hidden units. <i> <i>Proceedings of the 1993 Connectionist Models Summer School</i> . </i> In [ pp. 335 - 342] . .
[38] Wu, C. and Ho, J. and Lee, D. (2004) Travel-time prediction with support vector regression <i>IEEE Transactions On Intelligent Transportation Systems</i>, 5(4), pp. 276 - 281. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=1524-9050&vol=5&iss=4&firstpage=276” target=”new”>[CSA]</a><a href=”http://dx.doi.org/10.1109
[39] Yang, H. and Chan, L. and King, I.(2002). Support vector machine regression for volatile stock market prediction. <i> <i>Proc. Intelligent Data Engineering and Automated Learning</i> . </i> In [ pp. 391 - 396] . . 2412 · Zbl 1020.68956
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.