A Hybrid Model Based on Support Vector Machine for Bus Travel-Time Prediction

Shiquan Zhong; Juanjuan Hu; Shuiping Ke; Xuelian Wang; Jingxian Zhao; Baozhen Yao

doi:10.7307/ptt.v27i4.1577

Shiquan Zhong
Juanjuan Hu College of Architecture and Civil Engineering, Beijing University of Technology Beijing, 100022, China Transport Management Institute, Ministry of Transport of the People's Republic of China Beijing, 101601, China
Shuiping Ke College of Management and Economics, Tianjin University Tianjin, 300072, China
Xuelian Wang School of Management, Hebei University of Technology Tianjin 300130, China
Jingxian Zhao School of Economics and Management, Tianjin University of Science & Technology Tianjin, 300222, China
Baozhen Yao School of Automotive Engineering, Dalian University of Technology Dalian 116024, China

DOI: https://doi.org/10.7307/ptt.v27i4.1577

Keywords: bus travel time prediction, support vector machine regression, Grubbs’ test method, adaptive algorithm,

Abstract

Effective bus travel time prediction is essential in transit operation system. An improved support vector machine (SVM) is applied in this paper to predict bus travel time and then the efficiency of the improved SVM is checked. The improved SVM is the combination of traditional SVM, Grubbs’ test method and an adaptive algorithm for bus travel-time prediction. Since error data exists in the collected data, Grubbs’ test method is used for removing outliers from input data before applying the traditional SVM model. Besides, to decrease the influence of the historical data in different stages on the forecast result of the traditional SVM, an adaptive algorithm is adopted to dynamically decrease the forecast error. Finally, the proposed approach is tested with the data of No. 232 bus route in Shenyang. The results show that the improved SVM has good prediction accuracy and practicality.

References

Smith BL, Demetsky MJ. Short-Term Traffic Flow Prediction: Neural Network Approach. Transportation Research Record. 1995;1453:98-104.

Chien SIJ, Ding Y, Wei C. Dynamic Bus Arrival Time Prediction with Artificial Neural Networks. Journal of Transportation Engineering. 2002;128(5):429-438.

Chen M, Liu XB, Xia JX, Chien SI. A Dynamic Bus-Arrival Time Prediction Model Based on APC Data. Computer-Aided Civil and Infrastructure Engineering. 2004;19:364-376.

Acevedo-Rodríguez J, Maldonado-Bascón S, Lafuente-Arroyo S, Siegmann P, López-Ferreras F. Computational load reduction in decision functions using sup-port vector machines. Signal Processing. 2009;89(10):2066-2071.

Dong B, Cao C, Lee SE. Applying support vector machines to predict building energy consumption in tropical region. Energy and Buildings. 2005;37:545-553.

Elish KO, Elish MO. Predicting defect-prone software modules using support vector machines. Journal of Systems and Soft-ware. 2008;81(5):649-660.

Yu B, Yang ZZ, Yao BZ. Bus Arrival Time Prediction Using Support Vector Machines. Journal of Intelligent Transportation Systems. 2006;10(4):151-158.

Wu CH, Ho JM, Lee DT. Travel-time prediction with support vector regression. IEEE Transactions on Intelligent Transportation Systems. 2004;5(4):276-281.

Hellinga BR, Fu LP. Reducing bias in probe-based arterial link travel times estimates. Transportation Research Part C. 2002;10:257-273.

Cathey FW, Dailey DJ. A prescription for transit arrival/departure prediction using automatic vehicle location data. Transportation Research Part C. 2003;11:241-264.

Abbas K, Ehsan M, Saeid N, Doug C, Van LJWC. A genetic algorithm-based method for improving quality of travel time prediction intervals. Transportation Research Part C. 2011;19(6):1364-1376.

Ehsan M, Geoff R, Graham C, Sara M. Prediction intervals to account for uncertainties in neural network predictions: Methodology and application in bus travel time prediction. Engineering Applications of Artificial Intelligence. 2011;24(3):534-542.

Ngoduy D. Applicable filtering framework for online multiclass freeway network estimation. Physica A: Statistical Mechanics and its Applications. 2008;387(2-3):599-616.

Vapnik VN. An Overview of Statistical Learning Theory. IEEE Transactions on Neural Networks. 1999;10(5):988-999.

Vapnik VN. The Nature of Statistical Learning Theory. New York: Springer; 2000.

Yuan F, Cheu RL. Incident detection using support vector machines. Transportation Research Part C. 2003;11:309-328.

Ren JT, Ou XL, Zhang Y, Hu DC. Research on network level traffic pattern recognition. Proceedings of the 5th IEEE Conference on Intelligent Transportation Systems; 2002 Sep 3.6; Singapore. IEEE; 2002. doi: 10.1109/ITSC.2002.1041268

Reyna R, Giralt A, Esteve D. Head detection inside vehicles with a modified SVM for safer air bags. Proceedings of the IEEE Conference on Intelligent Transportation Systems; 2001 Aug 25-29; Oakland, CA. IEEE; 2001. doi: 10.1109/ITSC.2001.948667

Yu B, Yang ZZ, Chen K, Yu B. Hybrid model for prediction of bus arrival times at next station. Journal of Advanced Transportation. 2010;44(3):193-204.

Yu B, Lam WHK, Tam M L. Bus Arrival Time Prediction at Bus Stop with Multiple Routes. Transportation Research Part C. 2011;19(6):1157-1170.

Yu B, Yang ZZ, Li S. Real-Time Partway Deadheading Strategy Based on Transit Service Reliability Assessment. Transportation Research Part A. 2012;46(8):1265-1279.

Grubbs FE. Sample Criteria for Testing Outlying Observations. Annals of Mathematical Statistics. 1950;21(1): 27-58.

Grubbs FE. Procedures for Detecting Outlying Observation in Samples. Technometrics. 1969;11(1):1-21.

NIST/SEMATECH e-Handbook of Statistical Methods; 2010. Available from: http://www.itl.nist.gov/div898/handbook

Yang ZZ, Jin LJ, Wang MH. Forecasting Baltic Panamax Index with Support Vector Machine. Journal of Transportation Systems Engineering and Information Technology. 2011;11(3):50-57.

Moller MF. A Scaled conjugate gradient algorithm for fast supervised learning. Neural Networks. 1993;298(6):523-533.

Yao BZ, Yang CY, Yao JB, Sun J. Tunnel Surrounding Rock Displacement Prediction Using Support Vector Machine. International Journal of Computational Intelligence Systems. 2010;3(6): 843-852.

Yao BZ, Hu P, Zhang MH, Jin MQ. A Support Vector Machine with the Tabu Search Algorithm for Freeway Incident Detection. International Journal of Applied Mathematics and Computer Science. 2014;24(2):397-404.

Cao LJ, Tay FEH. Support Vector Machine with Adaptive Parameters in Financial Time Series Forecasting. IEEE Transactions on Neural Networks. 2003;14 (6):1506-1518.

Yao P, Lu Yh. Neighborhood rough set and SVM based hybrid credit scoring classifier. Expert Systems with Applications. 2011;38 (9):11300-11304.

Suykens JAK, Vandewalle J. Least Squares Support Vector Machine Classifiers. Neural Processing Letters. 1999;9(3):293-300.

Chua KS. Efficient computations for large least square support vector machine classifiers. Pattern Recognition Letters 2003; 24(1-3):75-80.

Ram BJ. A recursive version of Grubbs' test for detecting multiple outliers in environmental and chemical data. Clinical Biochemistry. 2010;43(12):1030-1033.

Azadeh A, Rouzbahman M, Saberi M, Valianpour F, Keramati A. Improved prediction of mental workload versus HSE and ergonomics factors by an adaptive intelligent algorithm. Signal Processing. 2013;94:350-358.

Aytug H, Koehler GJ, He L. Risk minimization and minimum description for linear discriminant functions. Informs Journal on Computing. 2008;20(2):317-331.