论文部分内容阅读
An analytical model is presented to estimate traffic pollutant concentrations based on an artificial neural network (ANN) approach. The model can analyze the highly nonlinear relationship between the traffic flow attributes, meteorological conditions, road spatial characteristics, and the traffic pollutant concentrations. This study analyzes the multiple factors that affect the pollutant concentration and establishes the model structure using the ANN technique. Collected data for the pollutant concentrations as functions of variant factors was used to train the ANN model. A method was developed to automatically measure the traffic flow attributes, such as traffic flow, vehicle speed, and flow composition from video data. The results indicate that the model can reliably forecast CO2 concentrations along the roads.
An analytical model is presented to estimate traffic pollutant concentrations based on an artificial neural network (ANN) approach. The model can analyze the highly nonlinear relationship between the traffic flow attributes, meteorological conditions, road spatial characteristics, and the traffic pollutant concentrations. analyzes the multiple factors that affect the pollutant concentration and established the model structure using the ANN technique. Collected data for the pollutant concentrations as functions of variant factors was used to train the ANN model. A method was developed to automatically measure the traffic flow attributes, such as traffic flow, vehicle speed, and flow composition from video data. The results indicate that the model can reliably forecast CO2 concentrations along the roads.