Travel time prediction with immune genetic algorithm and support vector regression

Travel time prediction, one of the most fundamental problems in almost all subsystems of Intelligent Transportation Systems (ITS), has attracted great attention in recent years. Lots of methods have been researched for this problem, including historical averages method, multiple linear regression and BP neural network. In this paper, an algorithm which combines support vector regression (SVR) and immune genetic algorithm (IGA) is designed for travel time prediction. SVR is used for establishing prediction model and IGA is used for optimizing the parameters of the model. To avoid over fitting problem, a new set which is called the validation set is introduced for the selection of fitness in IGA. Based on the actual traffic data from Langfang City, it is proved that the integration of SVR and IGA is applicable and performs better than historical averages method, multiple linear regression and BP neural network in travel time prediction.

[1]  Wu Meng,et al.  Application of Support Vector Machines in Financial Time Series Forecasting , 2007 .

[2]  M. Khalid,et al.  Machine Learning Using Support Vector Machines , 2002 .

[3]  Chengliang Liu,et al.  A vehicle traveling time prediction method based on grey theory and linear regression analysis , 2009 .

[4]  Hironori Hirata,et al.  An Evolutionary Optimization based on the Immune System and its Application to the VLSI Floorplan Design Problem , 1997 .

[5]  Wei Gao.  An improved fast-convergent genetic algorithm , 2003, IEEE International Conference on Robotics, Intelligent Systems and Signal Processing, 2003. Proceedings. 2003.

[6]  Jianming Hu,et al.  Traffic flow forecasting with particle swarm optimization and support vector regression , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[7]  Zhang Ying.  Genetic algorithms for optimizing of multiple resource scheduling problem , 2002 .

[8]  Guan-zheng Tan,et al.  Elitism-based immune genetic algorithm and its application to optimization of complex multi-modal functions , 2008 .

[9]  Zhang,et al.  An improved BP artificial neural network algorithm for urban traffic flow intelligent prediction , 2009 .

[10]  D. Dasgupta.  Artificial Immune Systems and Their Applications , 1998, Springer Berlin Heidelberg.

[11]  M. Lankhorst,et al.  A genetic algorithm for the induction of pushdown automata , 1995, Proceedings of 1995 IEEE International Conference on Evolutionary Computation.

[12]  Hironori Hirata,et al.  An evolutionary optimization based on the immune system and its application to the VLSI floor‐plan design problem , 1998 .

[13]  Gunnar Rätsch,et al.  Predicting Time Series with Support Vector Machines , 1997, ICANN.