论文信息 - Traffic Prediction Based on SVM Training Sample Divided by Time

Traffic Prediction Based on SVM Training Sample Divided by Time

In recent years, the volume of traffic is rapidly increasing. When vehicles running through the tunnel are more intensive or move slowly, the tunnel environment occurs deteriorated sharply, which affects the normal operation of the vehicle in the tunnel. This paper uses the result of previous mining association rules to select feature items and to establish four training samples divided by time. Then the training samples are utilized to create the SVM classification model. Finally the trained SVM model is used to prediction the tunnel traffic situation. Through traffic situation prediction, effective decisions can be made before traffic jams, and ensure that the tunnel traffic is normal. DOI: http://dx.doi.org/10.11591/telkomnika.v11i12.3656 Full Text: PDF

Qingbo Wang | Hongxia Xia | Lin Li | Lingli Li

[1] Xiangyang Wang,et al. A new integrated SVM classifiers for relevance feedback content-based image retrieval using EM parameter estimation , 2011, Appl. Soft Comput..

[2] Yu Bin,et al. Short-Term Traffic Flow Forecasting Based on Multi-Dimensional Parameters , 2011 .

[3] Yang Wang,et al. Traffic Density Estimation with On-line SVM Classifier , 2009, 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance.

[5] Rajeev Kumaraswamy,et al. SVM Based Classification of Traffic Signs for Realtime Embedded Platform , 2011, ACC.

[6] Song Ying,et al. Face recognition based on multi-class SVM , 2009, 2009 Chinese Control and Decision Conference.

[7] Hui Yu,et al. Research on Real-time and Dynamic Urban Traffic Information Service System , 2012 .

[8] Guo Min. Traffic State Forecasting Towards Urban Freeway Based on the Maximum Entropy Model , 2010 .

[9] Yuhong Guo,et al. Learning SVM Classifiers with Indefinite Kernels , 2012, AAAI.