Abstract
The change of urban road traffic flow has strong randomness and strong timeliness. The traditional short-term traffic flow prediction model has high complexity and strong closeness, and it is difficult to make full use of the previous learning results. In this paper, we analyze the support vector sparsity loss and parameter optimization time-consuming of Least Squares Support Vector Machine (LS-SVM) and propose a Dynamic Parameter Optimization LS-SVM named DPO-LSSVM for predicting short-term traffic flow. The experiments conducted on the real-world data set demonstrate the effectiveness of DPO-LSSVM on the training speed. Comparing with the Particle Swarm Optimization LS-SVM (PSO-LSSVM) and the RBF neural network online prediction model, the average training time of our model is only 30–60% of the other two.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
B. Hong, X. Jiang, Y. Qi, Q. Cheng, Research on LSSVM online prediction algorithm based on inverse of Hermite matrix. J. Syst. Simul. 29(1), 1–6 (2017)
Z. Li, Y. Li, F. Wang, A survey of online learning algorithms for big data analysis. J. Comput. Res. Dev. 52(8), 1707–1721 (2015)
J.A.K. Suykens, J. Vandewalle, B.D. Moor, Optimal control by least squares support vector machines. Neural Netw. 14, 23–35 (2001)
J.A.K. Suykens, J.D. Brabanter, L. Lukas, et al., Weighted least squares support vector machines: robustness and sparse approximation. Neurocompting 48(1), 85–105 (2002)
Z. Pan, S. Tang, J. Qiu, H. Guyu, Overview of online learning algorithms. J. Data Acquis. Process. 31(6), 1067–1082 (2016)
C. Xiang, Z. Zhou, L. Zhang, Improved algorithm of least squares support vector machine based on uniform design. Comput. Simul. 28(3), 194–197 (2011)
Y. Wang, D. Li, C. Gao, H. Zhang, Short-term load forecasting based on improved PSO-SVM. Elect. Meas. Instrum. 52(3), 22–25 (2015)
Y. Liu, Y. Sheng, C. Jiang, L. Chen, Short-term load forecasting based on LS-SVM and SMO sparse algorithm. Power Syst. Protect. Contr. 36(4), 63–66 (2008)
G. Si, H. Cao, Y. Zhang, L. Jia, A least squares support vector machine sparse algorithm based on density weighting. J. Xi’an Jiaotong Univ. 43(10), 11–15 (2009)
N. Xiong, B. Liu, On-line prediction of network traffic based on adaptive particle swarm optimization LSSVM. Comput. Appl. Softw. 9, 21–24 (2013)
W. Wang, C. Men, W. Lu, Online prediction model based on support vector machine. Neurocomputing 71(4-6), 550–558 (2008)
X. Zhou, Research on Online Modeling and Control Method Based on Least Squares Support Vector Machine (Hunan University, Changsha, 2012)
Q. Wang, Q. Liu, On-line prediction of sinter quality based on Elman neural network. Instrum. Tech. Sens. 2017, 10 (2017)
C. Ma, Y. Zhang, Z. Li, G. Yi, On-line prediction of characteristic parameters of hydraulic pump based on nuclear extreme learning machine. Comput. Simul. 5, 351–354 (2014)
Y. Ye, Z. Zuo, X. Yuan, S. Zhang, X. Zeng, Y. An, B. Chen, Geographically weighted regression model for urban traffic black-spot analysis, in 2017 IEEE International Geoscience and Remote Sensing Symposium
Z. Luo, H. Lv, F. Fang, Y. Zhao, Y. Liu, X. Xiang, X. Yuan, Dynamic taxi service planning by minimizing cruising distance without passengers. IEEE Access. 6, 70005–70016 (2018)
B Giritharan, S Panchakarla, X Yuan, Segmentation of CE videos by finding convex skin. in 2010 IEEE International Conference on Bioinformatics and Biomedicine Workshops (BIBMW), 2010. pp. 158–163
Acknowledgments
This work is supported by the National Key Research Development Program of China (2016YFC0801804), National Natural Science Foundation of China (61701162) and Fundamental Research Funds for the Central Universities of China (PA2019GDPK0079).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Ma, Z., Feng, L., Wei, Z., Lyu, Z., Huang, Z., Liu, F. (2020). Online Prediction Model of Short-Term Traffic Flow Based on Improved LS-SVM. In: Yuan, X., Elhoseny, M. (eds) Urban Intelligence and Applications. Studies in Distributed Intelligence . Springer, Cham. https://doi.org/10.1007/978-3-030-45099-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-45099-1_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-45098-4
Online ISBN: 978-3-030-45099-1
eBook Packages: Computer ScienceComputer Science (R0)