States of traffic situations can be classified into peak and nonpeak periods. The complexity of peak traffic brings more difficulty to forecasting models. Travel time index （TTI） is a fundamental measure in transpor...States of traffic situations can be classified into peak and nonpeak periods. The complexity of peak traffic brings more difficulty to forecasting models. Travel time index （TTI） is a fundamental measure in transportation. How to master the characteristics and provide accurate real-time forecasts is essential to intelligent transportation systems （ITS）. Cooperating with state space approach, least squares support vector machines （LS- SVMs） are investigated to solve such a practical problem in this paper. To the best of our knowledge, it is the first time to apply the technique and analyze the forecast performance in the domain. For comparison purpose, other two nonparametric predictors are selected because of their effectiveness proved in past research. Having good generalization ability and guaranteeing global minima, LS-SVMs perform better than the others. Providing sufficient improvement in stability and robustness reveals that the approach is practically promising.展开更多
The expressway traffc incidents have the characteristics of high harmful, strong destructive and refractory.Incident detection can guarantee smooth operation of the expressway, reduce traffc congestion and avoid secon...The expressway traffc incidents have the characteristics of high harmful, strong destructive and refractory.Incident detection can guarantee smooth operation of the expressway, reduce traffc congestion and avoid secondary accident by informing the accident, detection and treatment timely. In this paper, an incident detection method is proposed using the toll station data that takes into account the traffc ratio at the entrances and crossway in the network. The expressway traffc simulation model is improved and a simulation algorithm is established to describe the movement of the vehicles. A numerical example is experimented on the expressway network of Shandong province. The proposed method can effectively detect the expressway incidents, and dynamically estimate the traffc network states so as to provide advice for the highway management department.展开更多
文摘States of traffic situations can be classified into peak and nonpeak periods. The complexity of peak traffic brings more difficulty to forecasting models. Travel time index （TTI） is a fundamental measure in transportation. How to master the characteristics and provide accurate real-time forecasts is essential to intelligent transportation systems （ITS）. Cooperating with state space approach, least squares support vector machines （LS- SVMs） are investigated to solve such a practical problem in this paper. To the best of our knowledge, it is the first time to apply the technique and analyze the forecast performance in the domain. For comparison purpose, other two nonparametric predictors are selected because of their effectiveness proved in past research. Having good generalization ability and guaranteeing global minima, LS-SVMs perform better than the others. Providing sufficient improvement in stability and robustness reveals that the approach is practically promising.
基金Supported by the National Natural Science Foundation of China under Grant Nos.71871130,71471104,71771019,71571109the University Science and Technology Program Funding Projects of Shandong Province under Grant No.J17KA211the Project of Public Security Department of Shandong Province under Grant No.GATHT2015-236
文摘The expressway traffc incidents have the characteristics of high harmful, strong destructive and refractory.Incident detection can guarantee smooth operation of the expressway, reduce traffc congestion and avoid secondary accident by informing the accident, detection and treatment timely. In this paper, an incident detection method is proposed using the toll station data that takes into account the traffc ratio at the entrances and crossway in the network. The expressway traffc simulation model is improved and a simulation algorithm is established to describe the movement of the vehicles. A numerical example is experimented on the expressway network of Shandong province. The proposed method can effectively detect the expressway incidents, and dynamically estimate the traffc network states so as to provide advice for the highway management department.
