Traffic flow prediction plays an important role in intelligent transportation systems and is of great significance in the applications of traffic control and urban planning.Due to the complexity of road traffic flow d...Traffic flow prediction plays an important role in intelligent transportation systems and is of great significance in the applications of traffic control and urban planning.Due to the complexity of road traffic flow data,traffic flow prediction has been one of the challenging tasks to fully exploit the spatiotemporal characteristics of roads to improve prediction accuracy.In this study,a combined flow direction level traffic flow prediction graph convolutional network(GCN)and long short-term memory(LSTM)model based on spatiotemporal characteristics is proposed.First,a GCN model is employed to capture the topological structure of the data graph and extract the spatial features of road networks.Additionally,due to the capability to handle long-term dependencies,the longterm memory is used to predict the time series of traffic flow and extract the time features.The proposed model is evaluated using real-world data,which are obtained from the intersection of Liuquan Road and Zhongrun Avenue in the Zibo High-Tech Zone of China.The results show that the developed combined GCNLSTM flow direction level traffic flow prediction model can perform better than the single models of the LSTM model and GCN model,and the combined ARIMA-LSTM model in traffic flow has a strong spatiotemporal correlation.展开更多
A fluid dynamic traffic flow model based on a non-linear velocity-density function is considered. The model provides a quasi-linear first order hyperbolic partial differential equation which is appended with initial a...A fluid dynamic traffic flow model based on a non-linear velocity-density function is considered. The model provides a quasi-linear first order hyperbolic partial differential equation which is appended with initial and boundary data and turns out an initial boundary value problem (IBVP). A first order explicit finite difference scheme of the IBVP known as Lax-Friedrich’s scheme for our model is presented and a well-posedness and stability condition of the scheme is established. The numerical scheme is implemented in order to perform the numerical features of error estimation and rate of convergence. Fundamental diagram, density, velocity and flux profiles are presented.展开更多
The effects of a building＇s density on urban flows are investigated using a CFD model with the RNG k - ε turbulence closure scheme. Twenty-seven cases with different building＇s density parameters （e.g., building a...The effects of a building＇s density on urban flows are investigated using a CFD model with the RNG k - ε turbulence closure scheme. Twenty-seven cases with different building＇s density parameters （e.g., building and street-canyon aspect ratios） are numerically simulated. As the building＇s density parameters vary, different flow regimes appear. When the street canyon is relatively narrow and high, two counterrotating vortices in the vertical direction are generated. The wind speed along streets is mainly affected by the building＇s length. However, it is very difficult to find or generalize the characteristics of the street-canyon flows in terms of a single building＇s density parameter. This is because the complicated flow patterns appear due to the variation of the vortex structure and vortex number. Volume-averaged vorticity magnitude is a very good indicator to reflect the flow characteristics despite the strong dependency of flows on the variation of the building＇s density parameters. Multi-linear regression shows that the volume-averaged vorticity magnitude is a strong function of the building＇s length and the street-canyon width. The increase in the building＇s length decreases the vorticity of the street-canyon flow, while, the increase in the street- canyon width increases the vorticity.展开更多
Road traffic accidents are the outcome of the factors associated with the traffic system namely road users, road environment and vehicles. Despite good road surface, the Kathmandu-Bhaktapur road has high accident reco...Road traffic accidents are the outcome of the factors associated with the traffic system namely road users, road environment and vehicles. Despite good road surface, the Kathmandu-Bhaktapur road has high accident records. The traffic police record shows that 1530 accidents have occurred from July 2009 to June 2012. The area of study of this research is the Kathmandu-Bhaktapur road which starts at Tinkune Kathmandu and ends at Suryabinayak with a length of 9.1 kilometer, a section of Araniko highway heading towards China. The road is the first ever six lane road constructed in Nepal. The objectives of this research work are to identify locations with high accident numbers, to investigate possible causes of accidents, and to propose countermeasures for traffic safety along the Kathmandu-Bhaktapur road.展开更多
Mixed traffic flow composed of autos and non-autos widely exists in developing countries and areas. To investigate the operational characteristics of the mixed traffic flow consisting of vehicles in different types （...Mixed traffic flow composed of autos and non-autos widely exists in developing countries and areas. To investigate the operational characteristics of the mixed traffic flow consisting of vehicles in different types （large vehicles, cars, and bicycles）, we develop a cellular automaton model to repli- cate the travel behaviors on a bi-directional road segment with respect to the physical and mechanic features of different vehicle types. By implementing the essential parameters calibrated through the field data collection, a numerical study is carried out considering the variation in volume, density, and velocity with different compositions of mixed traffic flows. The primary findings include： the average ve- locity of traffic flow and total volume decrease 60% and 30% after incorporating 10% bicycles, respectively; the phenomenon of double-summit in terms bicycle is beyond 60 % ; the maximal total volume higher than 10 %. of the total volume appears when the proportion of starts to recover when the proportion of bicycle is展开更多
基金supported by the National Natural Science Foundation of China (Grant Nos.71901134&51878165)the National Science Foundation for Distinguished Young Scholars (Grant No.51925801).
文摘Traffic flow prediction plays an important role in intelligent transportation systems and is of great significance in the applications of traffic control and urban planning.Due to the complexity of road traffic flow data,traffic flow prediction has been one of the challenging tasks to fully exploit the spatiotemporal characteristics of roads to improve prediction accuracy.In this study,a combined flow direction level traffic flow prediction graph convolutional network(GCN)and long short-term memory(LSTM)model based on spatiotemporal characteristics is proposed.First,a GCN model is employed to capture the topological structure of the data graph and extract the spatial features of road networks.Additionally,due to the capability to handle long-term dependencies,the longterm memory is used to predict the time series of traffic flow and extract the time features.The proposed model is evaluated using real-world data,which are obtained from the intersection of Liuquan Road and Zhongrun Avenue in the Zibo High-Tech Zone of China.The results show that the developed combined GCNLSTM flow direction level traffic flow prediction model can perform better than the single models of the LSTM model and GCN model,and the combined ARIMA-LSTM model in traffic flow has a strong spatiotemporal correlation.
文摘A fluid dynamic traffic flow model based on a non-linear velocity-density function is considered. The model provides a quasi-linear first order hyperbolic partial differential equation which is appended with initial and boundary data and turns out an initial boundary value problem (IBVP). A first order explicit finite difference scheme of the IBVP known as Lax-Friedrich’s scheme for our model is presented and a well-posedness and stability condition of the scheme is established. The numerical scheme is implemented in order to perform the numerical features of error estimation and rate of convergence. Fundamental diagram, density, velocity and flux profiles are presented.
基金funded by the Korea Meteorological Administration Research and Development Program under Grant CATER 2007–3307
文摘The effects of a building＇s density on urban flows are investigated using a CFD model with the RNG k - ε turbulence closure scheme. Twenty-seven cases with different building＇s density parameters （e.g., building and street-canyon aspect ratios） are numerically simulated. As the building＇s density parameters vary, different flow regimes appear. When the street canyon is relatively narrow and high, two counterrotating vortices in the vertical direction are generated. The wind speed along streets is mainly affected by the building＇s length. However, it is very difficult to find or generalize the characteristics of the street-canyon flows in terms of a single building＇s density parameter. This is because the complicated flow patterns appear due to the variation of the vortex structure and vortex number. Volume-averaged vorticity magnitude is a very good indicator to reflect the flow characteristics despite the strong dependency of flows on the variation of the building＇s density parameters. Multi-linear regression shows that the volume-averaged vorticity magnitude is a strong function of the building＇s length and the street-canyon width. The increase in the building＇s length decreases the vorticity of the street-canyon flow, while, the increase in the street- canyon width increases the vorticity.
文摘Road traffic accidents are the outcome of the factors associated with the traffic system namely road users, road environment and vehicles. Despite good road surface, the Kathmandu-Bhaktapur road has high accident records. The traffic police record shows that 1530 accidents have occurred from July 2009 to June 2012. The area of study of this research is the Kathmandu-Bhaktapur road which starts at Tinkune Kathmandu and ends at Suryabinayak with a length of 9.1 kilometer, a section of Araniko highway heading towards China. The road is the first ever six lane road constructed in Nepal. The objectives of this research work are to identify locations with high accident numbers, to investigate possible causes of accidents, and to propose countermeasures for traffic safety along the Kathmandu-Bhaktapur road.
文摘Mixed traffic flow composed of autos and non-autos widely exists in developing countries and areas. To investigate the operational characteristics of the mixed traffic flow consisting of vehicles in different types （large vehicles, cars, and bicycles）, we develop a cellular automaton model to repli- cate the travel behaviors on a bi-directional road segment with respect to the physical and mechanic features of different vehicle types. By implementing the essential parameters calibrated through the field data collection, a numerical study is carried out considering the variation in volume, density, and velocity with different compositions of mixed traffic flows. The primary findings include： the average ve- locity of traffic flow and total volume decrease 60% and 30% after incorporating 10% bicycles, respectively; the phenomenon of double-summit in terms bicycle is beyond 60 % ; the maximal total volume higher than 10 %. of the total volume appears when the proportion of starts to recover when the proportion of bicycle is
