To effectively solve the traffic data problems such as data invalidation in the process of the acquisition of road traffic states,a road traffic states estimation algorithm based on matching of the regional traffic at...To effectively solve the traffic data problems such as data invalidation in the process of the acquisition of road traffic states,a road traffic states estimation algorithm based on matching of the regional traffic attracters was proposed in this work.First of all,the road traffic running states were divided into several different modes.The concept of the regional traffic attracters of the target link was put forward for effective matching.Then,the reference sequences of characteristics of traffic running states with the contents of the target link's traffic running states and regional traffic attracters under different modes were established.In addition,the current and historical regional traffic attracters of the target link were matched through certain matching rules,and the historical traffic running states of the target link corresponding to the optimal matching were selected as the initial recovery data,which were processed with Kalman filter to obtain the final recovery data.Finally,some typical expressways in Beijing were adopted for the verification of this road traffic states estimation algorithm.The results prove that this traffic states estimation approach based on matching of the regional traffic attracters is feasible and can achieve a high accuracy.展开更多
With continuous urbanization,cities are undergoing a sharp expansion within the regional space.Due to the high cost,the prediction of regional traffic flow is more difficult to extend to entire urban areas.To address ...With continuous urbanization,cities are undergoing a sharp expansion within the regional space.Due to the high cost,the prediction of regional traffic flow is more difficult to extend to entire urban areas.To address this challenging problem,we present a new deep learning architecture for regional epitaxial traffic flow prediction called GACNet,which predicts traffic flow of surrounding areas based on inflow and outflow information in central area.The method is data-driven,and the spatial relationship of traffic flow is characterized by dynamically transforming traffic information into images through a two-dimensional matrix.We introduce adversarial training to improve performance of prediction and enhance the robustness.The generator mainly consists of two parts:abstract traffic feature extraction in the central region and traffic prediction in the extended region.In particular,the feature extraction part captures nonlinear spatial dependence using gated convolution,and replaces the maximum pooling operation with dynamic routing,finally aggregates multidimensional information in capsule form.The effectiveness of the method is evaluated using traffic flow datasets for two real traffic networks:Beijing and New York.Experiments on highly challenging datasets show that our method performs well for this task.展开更多
In a given district, the accessibility of any point should be the synthetically evaluation of the internal and external accessibilities. Using MapX component and Delphi, the author presents an information system to ca...In a given district, the accessibility of any point should be the synthetically evaluation of the internal and external accessibilities. Using MapX component and Delphi, the author presents an information system to calculate and analyze regional accessibility according to the shortest travel time, generating thus a mark diffusing figure. Based on land traffic network, this paper assesses the present and the future regional accessibilities of sixteen major cities in the Yangtze River Delta. The result shows that the regional accessibility of the Yangtze River Delta presents a fan with Shanghai as its core. The top two most accessible cities are Shanghai and Jiaxing, and the bottom two ones are Taizhou （Zhejiang province） and Nantong With the construction of Sutong Bridge, Hangzhouwan Bridge and Zhoushan Bridge, the regional internal accessibility of all cities will be improved. Especially for Shaoxing, Ningbo and Taizhou （Jiangsu province）, the regional internal accessibility will be decreased by one hour, and other cities will be shortened by about 25 minutes averagely. As the construction of Yangkou Harbor in Nantong, the regional external accessibility of the harbor cities in Jiangsu province will be speeded up by about one hour.展开更多
BACKGROUND: Road traffi c accidents(RTA) are responsible for 1.2 million deaths worldwide each year. RTA will become the 3rd largest contributor to the global burden of diseases after ischemic heart diseases(IHD) and ...BACKGROUND: Road traffi c accidents(RTA) are responsible for 1.2 million deaths worldwide each year. RTA will become the 3rd largest contributor to the global burden of diseases after ischemic heart diseases(IHD) and depression. We conducted a retrospective study on RTA in a tertiary center in the hilly district of Uttarakhand in India.METHODS: The number of RTA, pattern of RTA, the number of patients killed and injured, the pattern of injury causing death and disability, the severity of accidents, and the type of disability were noted from December 2009 to November 2011. The accident severity was calculated as the number of patients killed per 100 accidents. The methods for reducing the incidence of RTA were observed, and the role of policy makers was studied.RESULTS: The majority of deaths and disabilities in Uttarakhand were due to road traffic accidents in the hilly districts of the states. The most common cause of RTA was driving fault followed by defective roads.CONCLUSION: Proper designing of roads and minimizing the fault of drivers are essential to prevent road traffi c accidents in hilly regions.展开更多
针对雾霾天气下交通信号灯定位准确率较低、图像增强时出现图像亮度不均匀的问题,该文提出一种基于改进的带色彩恢复的多尺度视网膜增强(Multi-Scale Retinex with Color Restoration,MSRCR)的雾霾天气下信号灯识别算法。首先利用改进的...针对雾霾天气下交通信号灯定位准确率较低、图像增强时出现图像亮度不均匀的问题,该文提出一种基于改进的带色彩恢复的多尺度视网膜增强(Multi-Scale Retinex with Color Restoration,MSRCR)的雾霾天气下信号灯识别算法。首先利用改进的MSRCR算法对有雾图像进行预处理,校正图像亮度并丰富图像细节;再利用最大稳定极值区域(Maximally Stable Extremal Regions,MSER)算法以及信号灯的背板信息确定信号灯的位置;最后将定位区域转换至HSV空间进行信号灯识别。结果表明,该方法能够在雾霾条件下有效地定位及识别交通信号灯。展开更多
为了优化区域交通信号配时方案,提升区域通行效率,文章提出一种基于改进多智能体Nash Q Learning的区域交通信号协调控制方法。首先,采用离散化编码方法,通过划分单元格将连续状态信息转化为离散形式。其次,在算法中融入长短时记忆网络(...为了优化区域交通信号配时方案,提升区域通行效率,文章提出一种基于改进多智能体Nash Q Learning的区域交通信号协调控制方法。首先,采用离散化编码方法,通过划分单元格将连续状态信息转化为离散形式。其次,在算法中融入长短时记忆网络(Long Short Term Memory,LSTM)模块,用于从状态数据中挖掘更多的隐藏信息,丰富Q值表中的状态数据。最后,基于微观交通仿真软件SUMO(Simulation of Urban Mobility)的仿真测试结果表明,相较于原始Nash Q Learning交通信号控制方法,所提方法在低、中、高流量下车辆的平均等待时间分别减少了11.5%、16.2%和10.0%,平均排队长度分别减少了9.1%、8.2%和7.6%,平均停车次数分别减少了18.3%、16.1%和10.0%。结果证明了该算法具有更好的控制效果。展开更多
基金Projects(D07020601400707,D101106049710005)supported by the Beijing Science Foundation Plan Project,ChinaProjects(2006AA11Z231,2012AA112401)supported by the National High Technology Research and Development Program of China(863 Program)Project(61104164)supported by the National Natural Science Foundation of China
文摘To effectively solve the traffic data problems such as data invalidation in the process of the acquisition of road traffic states,a road traffic states estimation algorithm based on matching of the regional traffic attracters was proposed in this work.First of all,the road traffic running states were divided into several different modes.The concept of the regional traffic attracters of the target link was put forward for effective matching.Then,the reference sequences of characteristics of traffic running states with the contents of the target link's traffic running states and regional traffic attracters under different modes were established.In addition,the current and historical regional traffic attracters of the target link were matched through certain matching rules,and the historical traffic running states of the target link corresponding to the optimal matching were selected as the initial recovery data,which were processed with Kalman filter to obtain the final recovery data.Finally,some typical expressways in Beijing were adopted for the verification of this road traffic states estimation algorithm.The results prove that this traffic states estimation approach based on matching of the regional traffic attracters is feasible and can achieve a high accuracy.
基金This work was funded by the National Natural Science Foundation of China under Grant(Nos.61762092 and 61762089).
文摘With continuous urbanization,cities are undergoing a sharp expansion within the regional space.Due to the high cost,the prediction of regional traffic flow is more difficult to extend to entire urban areas.To address this challenging problem,we present a new deep learning architecture for regional epitaxial traffic flow prediction called GACNet,which predicts traffic flow of surrounding areas based on inflow and outflow information in central area.The method is data-driven,and the spatial relationship of traffic flow is characterized by dynamically transforming traffic information into images through a two-dimensional matrix.We introduce adversarial training to improve performance of prediction and enhance the robustness.The generator mainly consists of two parts:abstract traffic feature extraction in the central region and traffic prediction in the extended region.In particular,the feature extraction part captures nonlinear spatial dependence using gated convolution,and replaces the maximum pooling operation with dynamic routing,finally aggregates multidimensional information in capsule form.The effectiveness of the method is evaluated using traffic flow datasets for two real traffic networks:Beijing and New York.Experiments on highly challenging datasets show that our method performs well for this task.
基金National Natural Science Foundation of China, No.40371044 No.70573053
文摘In a given district, the accessibility of any point should be the synthetically evaluation of the internal and external accessibilities. Using MapX component and Delphi, the author presents an information system to calculate and analyze regional accessibility according to the shortest travel time, generating thus a mark diffusing figure. Based on land traffic network, this paper assesses the present and the future regional accessibilities of sixteen major cities in the Yangtze River Delta. The result shows that the regional accessibility of the Yangtze River Delta presents a fan with Shanghai as its core. The top two most accessible cities are Shanghai and Jiaxing, and the bottom two ones are Taizhou （Zhejiang province） and Nantong With the construction of Sutong Bridge, Hangzhouwan Bridge and Zhoushan Bridge, the regional internal accessibility of all cities will be improved. Especially for Shaoxing, Ningbo and Taizhou （Jiangsu province）, the regional internal accessibility will be decreased by one hour, and other cities will be shortened by about 25 minutes averagely. As the construction of Yangkou Harbor in Nantong, the regional external accessibility of the harbor cities in Jiangsu province will be speeded up by about one hour.
文摘BACKGROUND: Road traffi c accidents(RTA) are responsible for 1.2 million deaths worldwide each year. RTA will become the 3rd largest contributor to the global burden of diseases after ischemic heart diseases(IHD) and depression. We conducted a retrospective study on RTA in a tertiary center in the hilly district of Uttarakhand in India.METHODS: The number of RTA, pattern of RTA, the number of patients killed and injured, the pattern of injury causing death and disability, the severity of accidents, and the type of disability were noted from December 2009 to November 2011. The accident severity was calculated as the number of patients killed per 100 accidents. The methods for reducing the incidence of RTA were observed, and the role of policy makers was studied.RESULTS: The majority of deaths and disabilities in Uttarakhand were due to road traffic accidents in the hilly districts of the states. The most common cause of RTA was driving fault followed by defective roads.CONCLUSION: Proper designing of roads and minimizing the fault of drivers are essential to prevent road traffi c accidents in hilly regions.
文摘针对雾霾天气下交通信号灯定位准确率较低、图像增强时出现图像亮度不均匀的问题,该文提出一种基于改进的带色彩恢复的多尺度视网膜增强(Multi-Scale Retinex with Color Restoration,MSRCR)的雾霾天气下信号灯识别算法。首先利用改进的MSRCR算法对有雾图像进行预处理,校正图像亮度并丰富图像细节;再利用最大稳定极值区域(Maximally Stable Extremal Regions,MSER)算法以及信号灯的背板信息确定信号灯的位置;最后将定位区域转换至HSV空间进行信号灯识别。结果表明,该方法能够在雾霾条件下有效地定位及识别交通信号灯。
文摘为了优化区域交通信号配时方案,提升区域通行效率,文章提出一种基于改进多智能体Nash Q Learning的区域交通信号协调控制方法。首先,采用离散化编码方法,通过划分单元格将连续状态信息转化为离散形式。其次,在算法中融入长短时记忆网络(Long Short Term Memory,LSTM)模块,用于从状态数据中挖掘更多的隐藏信息,丰富Q值表中的状态数据。最后,基于微观交通仿真软件SUMO(Simulation of Urban Mobility)的仿真测试结果表明,相较于原始Nash Q Learning交通信号控制方法,所提方法在低、中、高流量下车辆的平均等待时间分别减少了11.5%、16.2%和10.0%,平均排队长度分别减少了9.1%、8.2%和7.6%,平均停车次数分别减少了18.3%、16.1%和10.0%。结果证明了该算法具有更好的控制效果。
