Traffic Simulation of Kobe-City

In preventing large-scale congestion caused by urban road traffic attacks, both random and deliberate attack methods were employed, with the robustness of the traffic system analyzed using a cascading failure model. The details of the proposed methods are, firstly, a road network model is constructed based on a Geographic Information System (GIS), and the traffic flow data of a provincial city during peak traffic hours is obtained by Python. Then, the flow data of Origin-Destination (OD) pairs for the road network under normal operation is obtained using the OD estimation module in TransCAD, the urban transportation network is modeled based on the actual traffic flow distribution. Subsequently, random attacks and deliberate attacks based on traffic volume were conducted on the road network. The traffic flow of the attacked segments was reallocated according to a cascading failure model, with the robustness of the urban road network assessed using topological and traffic flow indicators. The results indicate that, in the robustness analysis considering cascading failures, deliberate attacks have a more significant impact on high-traffic segments compared to random attacks with the same number of attack steps. Therefore, future urban traffic management should focus on ensuring the efficiency of high-traffic road segments, and prevent it from becoming ineffective due to excessive traffic flow.

Missing data is a major problem in data-driven intelligent transportation systems. This study presents an imputation method, called TrafficMosaic, for effective imputation of lost traffic flow data. If we consider traffic data as a image, then the missing data in it can be regarded as a mosaic. The design of TrafficMosaic is inspired by super resolution techniques. First, a deep neural network (DNN) is employed to recover the lost data by a suite of techniques inspired from image super resolution. This DNN method combines the temporal relevance of historical flow with spatial correlation of current fragmented flow data, and uses the imputation result as input for recursive calculation. Second, a data-driven road network matrixing algorithm is proposed to mine location relations from trajectory data and reconstruct a road network flow into matrixes of road network flow pictures. Convolutional local calculation in a convolutional neural network is introduced to extract local spatial features of the road network, thereby reducing the computational complexity and improving the generalization ability. The final step is to extract the local temporal features of the flow data. Traffic flows at adjacent moments have strong temporal characteristics, and we splice several historical road network traffic pictures in chronological order so that our model can capture temporal information from the sequence. The experimental evaluation used a real automatic number plate recognition dataset for experiments, and the results show the effectiveness of TrafficMosaic for lost data imputation.

In urban road traffic system, a variety of travel modes coexist and interact with each other. Micro modeling and analysis methods are difficult to capture the macro evolution characteristics and interaction of traffic flow. Based on the actual road network and vehicle trajectory data of Beijing, this paper calculates the total number of vehicles on the road section through the taxi trajectory data and the safe distance model to obtain the social vehicle data, and uses the bus moving trajectory data to obtain the bus vehicle data. Based on the three-dimensional macroscopic fundamental diagram (MFD) method, a three- dimensional MFD of social vehicle-bus vehicle is established, and the model parameters are solved by the least square method. The traffic flow data obtained by processing is used to verify its existence. According to the results of regional division, the influence of the number of buses in the two regions on the traffic capacity in the region is compared. The three-dimensional MFD model constructed in this paper can reflect the evolution characteristics of actual traffic flow, which is of great significance for traffic control of different trips.

In many cases, the final path selection of travellers' is not the shortest path, due to the limited computing power and high cost of path search. To solve the problem, this paper proposes a day-to-day (DTD) stochastic traffic flow assignment model that regulates the traffic flow based on the travel time (travel cost) and residual congestion of optional paths. The regulation mechanism is called the mixed regulation. Then, the authored proved the existence, uniqueness and stability of the model solution. The proposed model was verified through simulation on a Nguyen-Dupuis road network. The results show that traffic flows and travel times of all paths reached the equilibrium state, thanks to the DTD mixed regulation for 20~30 days. From the traffic flows and congestion degrees of different sections, it can be seen that our model with mixed regulation diverts the traffic flow to the sections with a low congestion degree, and encourages travellers to drive through the sections with a low traffic flow. In addition, the congestion degrees of the four most congested sections decreased by 5.8%, 4%, 7% and 1.2%, respectively, and the entire road network exhibited a slight downward trend in mean congestion degree. These results prove that our model can uniformize the traffic flow, improve the operation efficiency and alleviate the congestion of the road network. These findings shed new light on the control, guidance and planning of traffic flow in road networks.

Forming comprehensive security plans is essential to ensure safety at large events. The Multi Agent Simulator (MAS) is widely used for preparing security plans that will guide responses to accidents at large events. For forming security plans, it is necessary that we simulate crowd behaviors that reflect real world observations. However, crowd behavior simulations require OD information (departure time, place of Origin, and Destination) of each agent. Moreover, from the viewpoint of protecting personal information, it is difficult to observe the complete and detailed trajectories of all pedestrians. Therefore, the OD information should be estimated from the data observed at several points, usually the number of people passing fixed points. In this paper, we propose an accurate method for estimating OD information; it has three features. First, by using Bayesian optimization (BO) which is widely used to find optimal hyper parameters in the machine learning fields, the OD information is efficiently and accurately estimated using fewer parameter searches. Second, by dividing the time window and ignoring the identity of the observed people, the parameter dimension of the OD information is reduced to yield a solvable search space. Third, by considering the time delay created by the physical separation of the observation points, we develop a more accurate objective function. Experiments evaluate the proposed method using the data collected at three events (University festival, projection-mapping event, and music live), and the accuracy with which reproduction MAS can reproduce the people flows is assessed. We also show an example of the MAS-based process used in making guidance plans to reduce crowd congestion.

Traffic speed is a key indicator for the efficiency of an urban transportation system. Accurate modeling of the spatiotemporally varying traffic speed thus plays a crucial role in urban planning and development. This paper addresses the problem of efficient fine-grained traffic speed prediction using big traffic data obtained from static sensors. Gaussian processes (GPs) have been previously used to model various traffic phenomena, including flow and speed. However, GPs do not scale with big traffic data due to their cubic time complexity. In this work, we address their efficiency issues by proposing local GPs to learn from and make predictions for correlated subsets of data. The main idea is to quickly group speed variables in both spatial and temporal dimensions into a finite number of clusters, so that future and unobserved traffic speed queries can be heuristically mapped to one of such clusters. A local GP corresponding to that cluster can then be trained on the fly to make predictions in real-time. We call this method localization. We use non-negative matrix factorization for localization and propose simple heuristics for cluster mapping. We additionally leverage on the expressiveness of GP kernel functions to model road network topology and incorporate side information. Extensive experiments using real-world traffic data collected in the two U.S. cities of Pittsburgh and Washington, D.C., show that our proposed local GPs significantly improve both runtime performances and prediction accuracies compared to the baseline global and local GPs.

Road network traffic flow prediction: A personalized federated learning method based on client reputation

At present, the urban traffic system is faced with the problems of congestion and low efficiency, and the traditional methods have certain limitations when dealing with the complex urban road network. This paper aims to explore a new method of capacity Optimization of Road Networks in a Smart City environment and proposes a method based on a Graph Neural network, named “Smart City Road optimization Graph Neural Network” (SCRO-GNN). SCRO-GNN first collects and preprocesses multi-source data, including road network data, traffic flow, accident records, environmental factors, etc. The key node and edge features, including the number of lanes at the intersection, the traffic flow of the section, and the adjacency matrix of the road network are defined to characterize the structure of the road network. Then, the graph neural network model is constructed and trained to predict the traffic flow of different sections and evaluate the road capacity by using the graph structure of the road network. This paper tests the performance of SCRO-GNN on real road networks in multiple cities. The results show that, compared with the traditional traffic flow prediction model, SCRO-GNN can significantly improve the prediction accuracy, especially when dealing with the highly complex urban road network structure. Based on these predictions, the proposed optimization strategy performed well in reducing traffic congestion and improving the efficiency of road use. The research in this paper not only demonstrates the potential of graph neural networks in smart city road network optimization, but also provides a new direction for future traffic system research. The successful implementation of the SCRO-GNN approach is expected to provide more efficient and intelligent solutions for urban traffic management and planning.

This research paper examines the application of artificial intelligence (AI) in road network inventory and network-wide road safety assessment. An overview of current research related to this field is presented and various aspects of the use of AI in road infrastructure and safety assessment are analysed. In today’s world, where the road network continues to develop and grow, the use of AI can offer significant advantages in the inventory and assessment of road infrastructure and safety. AI can be used to process large volumes of data collected from various sources such as geographic data, photos, documentation and more. One of the main aspects that the article looks at is the use of AI to automatically process data and create a digital inventory of the road network. AI systems can analyse geographic data and photos to identify and classify roads, road signs, markings, and other elements of road infrastructure. This can facilitate engineers and competent authorities in the process of road inventory and maintenance. Another important aspect discussed in the paper is the use of AI for the general assessment of road safety. AI models can analyse road infrastructure inventory data, as well as traffic data, crashes, and other factors, to provide a comprehensive assessment of road network safety. This allows the competent authorities to identify vulnerable places, carry out preventive measures and plan appropriate interventions aimed at improving road safety. In conclusion, the paper highlights the possibilities and advantages of using artificial intelligence in road network inventory and network-wide road safety assessment. Such an approach can contribute to more efficient management of road infrastructure and improvement of road safety.

Traffic incidents continue to cause a significant loss in deaths, injuries, and property damages. Reported traffic accident data contains a considerable amount of human errors, hindering the studies on traffic accidents. Several approaches have been developed to detect accidents using traffic data in real time. However, those approaches do not consider the spatiotemporal patterns inherent in traffic data, resulting in high false alarm rates. In this paper, we study the problem of traffic accident detection by considering multiple traffic speed time series collected from road network sensors. To capture the spatiotemporal impact of traffic accidents to upstream locations, we adopt Impact Interval Grouping (IIG), which compares real-time traffic speed with historical data, and generates impact intervals to determine the presence of accidents. Furthermore, we take a multivariate time series classification approach and extract three novel features to measure the severity of traffic accidents. We use real-world traffic speed and accident datasets in our empirical evaluation, and our solutions outperform state-of-the-art approaches in multivariate time series classification.

In order to optimize the existing control subarea division methods, a new dynamic subarea division method based on node importance evaluating is proposed for regional coordinated control. Firstly, considering the characteristics of road network and traffic flow between adjacent intersections, correlation degree model is established by calculating the correlation coefficients of traffic flow, signal cycle, and traffic state. Then, road traffic network is abstracted into a network topology structure graph. From the global perspective of the road network, intersection position information and the importance contribution between adjacent intersections are taken into account, and the correlation degrees between adjacent intersections are taken as the edge weights to construct intersection importance evaluation matrix. Finally, an actual road network is selected, and an improved Newman algorithm is employed to verify and analyze the method proposed in this paper. Results show that, compared with other methods, the control subarea division result of the new proposed method is more elaborate and more in line with the actual traffic flow characteristics. Moreover, dynamic subarea division can be realized according to the traffic characteristics of different periods, which can provide a good basis for the formulation of the signal control schemes in the next stage.

Traffic measurements and high-performance modelling of motorway emission rates

Deep neural networks have recently demonstrated the traffic prediction capability with the time series data obtained by sensors mounted on road segments. However, capturing spatio-temporal features of the traffic data often requires a significant number of parameters to train, increasing computational burden. In this work we demonstrate that embedding topological information of the road network improves the process of learning traffic features. We use a graph of a vehicular road network with recurrent neural networks (RNNs) to infer the interaction between adjacent road segments as well as the temporal dynamics. The topology of the road network is converted into a spatio-temporal graph to form a structural RNN (SRNN). The proposed approach is validated over traffic speed data from the road network of the city of Santander in Spain. The experiment shows that the graph-based method outperforms the state-of-the-art methods based on spatio-temporal images, requiring much fewer parameters to train.

Dynamic multi-scale spatial-temporal graph convolutional network for traffic flow prediction

Summary form only given. With the rapid urbanization of developing country, the harm effect to environment of urban carbon emission in traffic has attracted wide attention, under the background of global climate change. The widely used methods, such as remote sensing and monitor station, are unable to get carbon emission on urban road network accurately, due to poor spatial resolution and coverage. In this context, the article discusses the method to extract carbon emission of commuting using urban form information. The research uses the TRANUS integrated land use and transport model to simulate commuting traffic flow on road network. Urban form information is used as input parameter, then transformed into residents' travel requirement, and finally into traffic flow covered all road network. The urban form information includes land use, population, income, block size, potential traffic mode, land price, traffic facilities et al. The spatial distribution of carbon emission on road network is derived from traffic flow information, using the standard car emission factors from IPCC. This paper takes Xiamen Island as study area, simulates residents' commuting travel during rush hour of an ordinary workday. By comparison with 11 sample point data of actual traffic monitor stations, accuracy evaluation shows that system error of traffic flow simulation is 6.56%, and relative mean error is 18.43%. The spatial distribution of commuting travel carbon emission shows variability on different road sections. Carbon emission on most road sections is less than 1.0 tCO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> e/km, some sections is higher than 6.0 tCO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> e/km which mainly distribute on central and north part of the island. The urban form information is showed connection to the characteristics of carbon emission. The result shows that higher income people have a higher total carbon emission and emission intensity. Emission intensity of high income people on Xiamen Island is nearly 30 times than that of low income people. Private cars totally emit 94.17 tCO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> e during rush hour, comparing to the emission of public transportation is 22.23 tCO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> e. Within all public transport forms, bus, BRT and TAXI take up about 38.1%, 3.45% and 58.45% separately. However, the emission intensity of TAXI highly exceeds the other two modes. This study is expected to find an effective method to evaluate the carbon emission with spatial details, and we hope that it can help people to construct a low-carbon city.