Traffic congestion propagation inference using dynamic Bayesian graph convolution network

Spatial distribution complexities of traffic congestion and bottlenecks in different network topologies

Due to the rapid development of vehicular transportation and urbanization, traffic congestion has been increasing and becomes a serious problem in almost all major cities worldwide. Many instances of traffic congestion can be traced to their root causes, the so-called traffic bottlenecks, where relief of traffic congestion at bottlenecks can bring network-wide improvement. Therefore, it is important to identify the locations of bottlenecks and very often the most effective way to improve traffic flow and relieve traffic congestion is to improve traffic situations at bottlenecks. In this article, we first propose a novel definition of traffic bottleneck taking into account both the congestion level cost of a road segment itself and the contagion cost that the congestion may propagate to other road segments. Then, an algorithm is presented to identify congested road segments and construct congestion propagation graphs to model congestion propagation in urban road networks. Using the graphs, maximal spanning trees are constructed that allow an easy identification of the causal relationship between congestion at different road segments. Moreover, using Markov analysis to determine the probabilities of congestion propagation from one road segment to another road segment, we can calculate the aforementioned congestion cost and identify bottlenecks in the road network. Finally, simulation studies using SUMO confirm that traffic relief at the bottlenecks identified using the proposed technique can bring more effective network-wide improvement. Furthermore, when considering the impact of congestion propagation, the most congested road segments are not necessarily bottlenecks in the road network. The proposed approach can better capture the features of urban bottlenecks and lead to a more effective way to identify bottlenecks for traffic improvement. Experiments are further conducted using data collected from inductive loop detectors in Taipei road network and some road segments are identified as bottlenecks using the proposed method.

We propose a dynamic differential Bayesian networks (DDBNs) and nonparametric regression model. This model is an extended model of traditional dynamic Bayesian networks (DBNs), which can incorporate temporal information in a natural way and directly handle real-valued data obtained from microarrays without any transformation. In addition, it can cope with differential information between gene expression levels, without any loss to the traditional advantage, i.e., the capability of estimating non-linear relationships between genes. We apply DDBNs to analyze simulated data and real data, i.e., Saccharomyces cerevisiae cell cycle gene expression data. We have confirmed the effectiveness of our approach in the sense that some edges have been successfully detected only by DDBNs, not by DBNs.

Traffic congestion in urban areas has become a critical issue in the world. As the limits of road topology and the influence of residents' commuting periodic patterns, the same part of the road network usually gets congested, and there are similar propagation paths when congestion occurs in an area. This paper aims to model the congestion propagation phenomenon and further discover the congestion propagation paths that frequently appeared. To this end, we propose an algorithm which analyzes the correlations between congestions on different road segments and constructs a congestion propagation graph to reflect the dynamic process of congestions. The traffic flow entropy is novelty considered to identify the potential essential road segment in traffic congestions. We adopt the Jaccard correlation to estimate the parameters employed. The experiments with the road network in Beijing, China and real-world GPS trajectory data indicate that our approach can reveal congestion propagation patterns and the dynamic process of congestion propagation.

With the advancement of urbanization and the proposal of sustainable development goals, the complexity and vulnerability of urban transportation systems have become increasingly prominent, and their reliability is directly related to the sustainable operation of urban transportation. The reliability of urban road networks, characterized by their dynamic nature, multi-scale characteristics, and anti-interference capabilities, directly restricts the functional guarantee of urban traffic and the efficiency of emergency response. To address the limitations of existing road network connectivity reliability assessment methods in representing time dynamics and modeling failure correlation, this study proposes a road network reliability assessment method based on a Dynamic Bayesian Network (DBN) by constructing a probabilistic reasoning model that integrates cascading failure characteristics. First, the connectivity reliability of the road network under random and targeted attack strategies was evaluated using a Monte Carlo simulation, revealing the impact of different attack strategies on network reliability. Subsequently, the congestion delay index is used as the standard of road section failure, considering the failure distribution and mutual dependence of road sections over time, a cascade failure mechanism is introduced, and a time-varying reliability assessment model based on a DBN is constructed. The effectiveness of the proposed method was verified through a case study of a partial road network in Dalian. The results show that ignoring cascading effects can significantly overestimate the reliability of the road network, especially during peak traffic hours, where such deviations may mask the real paralysis risks of the network. In contrast, the method proposed in this study fully considers time dynamics and failure correlation and can better capture the reliability of the road network under various dynamic conditions, providing a scientific basis for the sustainable planning and emergency management of urban traffic systems.

Urban traffic network congestion propagation prediction model: A case of non-recurrent congestion

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.

In order to find out the problems of students' learning in the online learning process in time and ensure that students can successfully complete the online learning course, the dynamic Bayesian network is used to predict students' online learning scores. First, the online course Bayesian network is established, and then the dynamic Bayesian network is established by combining the Bayesian network and hidden Markov according to the time slice. The maximum expectation algorithm is used for Bayesian parameter learning, and the scores are predicted according to video learning, chapter test and other influencing factors. The results show that the dynamic Bayesian network can effectively predict the online learning results, the prediction results provide teachers with decision-making, and students can carry out targeted reinforcement learning according to the prediction results in the learning process.

With the rapid development of urban transport and the sharp increase in vehicle population, traffic accidents form one of the most important causes of urban traffic congestion other than the imbalance between traffic supply and demand. Traffic congestion causes severe problems, such as environment contamination and energy dissipation. Therefore, it would be useful to analyze the congestion propagation characteristics after traffic accidents. Numerical analysis and computer simulation were two of the typical methods used at present to study the traffic congestion propagation properties. The latter was more widespread as it is more consistent with the actual traffic flow and more visual than the former. In this paper, an improved cellular automata (CA) model was presented to analyze traffic congestion propagation properties and to evaluate control strategies. In order to apply them to urban traffic flow simulation, the CA models have been improved and expanded on. Computer simulations were built for congestion not only extending to the upstream intersection, but also the upstream intersection and the entire road network, respectively. Congestion propagation characteristics after road traffic accidents were obtained, and controls of different severities and durations were analyzed. The results provide the theoretical foundation and practical means for the control of congestion.

Traffic accidents in urban road networks frequently result in significant congestion, further aggravating unsafe conditions. Exploring the congestion propagation from traffic accidents and proposing recovery strategies are crucial for improving urban road network efficiency. We employ the SUMO software to analyze the characteristics of network accidents, including traffic speed, density, occupancy rate, and acceleration. Then, we develop a road network recovery strategy following a traffic accident. The model consists of two parts: (1) A congestion propagation model is constructed, dividing the road network into an “accident core area” and an “accident surrounding area” (2). In the accident core area, traffic signal optimization is applied to improve traffic capacity. Meanwhile, vehicles in the accident surrounding area are guided to avoid the accident core area, thereby reducing traffic pressure. Last, a road network in Zhengzhou city was selected to verify the proposed strategy, with traffic accident points set in the network’s center and edge areas. The results show that the proposed recovery strategy effectively reduces vehicle delay after an accident. When a traffic accident occurs in the edge area of the network, the average vehicle delay is reduced by 6.73%, 16.15%, and 16.84% under low, medium, and high traffic demand, respectively. When a traffic accident occurs in the central area of the network, the average vehicle delay is reduced by 9.91%, 15.56%, and 18.80% under low, medium, and high traffic demand, respectively. Additionally, a sensitivity analysis of the strategy with respect to the traffic accident duration was conducted, demonstrating its good performance.

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

Asymptotic traffic dynamics arising in diverge–merge networks with two intermediate links

Traffic flow forecasting is the basis for the dynamic control and application of Intelligent Transport Systems (ITS), which is of great practical importance in reducing road congestion. Accurately predicting traffic flow remains a significant obstacle due to the intricate spatial and temporal dependencies associated with traffic movement. To capture the simultaneous dynamics of traffic flow’s spatiotemporal features, this paper suggests a novel Spatiotemporal Interactive Dynamic Synchronous Graph Convolution Network (STIDSG) for traffic flow forecasting, which is composed of the Interactive Dynamic Graph Convolution Network (IDGCN) and the Spatiotemporal Synchronous Graph Convolution Layer (STSGCL). IDGCN learns and shares features using an interactive learning strategy that is based on Dynamic Graph Convolution (DGCN). By incorporating DGCN into the interactive learning structure, it is possible to learn dynamic spatial features of traffic flow in an interactive manner while also capturing temporal dependencies. STSGCL effectively captures the intricate local and dynamic correlations of traffic flows by designing numerous Spatiotemporal Synchronization Graph Convolution Modules (STSGCM) for different time periods. The results of the experiment demonstrate that the STIDSG model suggested in this paper can proficiently extract the changing spatiotemporal features of the traffic flow and outperforms the commonly used baseline methods for prediction. The results of the experiment demonstrate that the STIDSG model suggested in this paper can proficiently extract the changing spatiotemporal features of the traffic flow and outperforms the commonly used baseline methods for prediction.

Nowadays, several components and systems are designed and produced based on reliability. Since the reliability criterion has an important role in purchasing and implementation of these systems. In the design of a reliable system, fault and failure analysis must be carried out in order to reduce fault probability of the system. When dependency and the relation between components of a complex system are important and should be mentioned, determination of system reliability is very difficult. In this paper, dynamic fault tree is used to evaluate the systems reliability that their behavior is varied with time. Dynamic fault tree is constructed and then it converted to dynamic bayesian network. In this paper, the principle of dynamic fault tree gates and their mapping into dynamic bayesian are explained and some new relations between events and gates for this mapping are proposed. GeNIe package is used to determine dynamic bayesian network based on stochastic sampling algorithms. Four systems (cardiac assist system, hypothetical cascaded priority-and system, inertial navigation system/ global positioning system integrated, and emergency detection system) are investigated; reliability and fault probability of these systems are calculated. Comparison of the results with those obtained by other researches shows the proposed method effectiveness for systems reliability modeling and assessment via dynamic bayesian network.

Unconventional events exacerbate the imbalance between regional transportation demand and limited road network resources. Scientific and efficient path planning serves as the foundation for rapidly restoring equilibrium to the road network. In real large-scale road networks, especially during emergencies, it is usually difficult to obtain or predict accurate dynamic traffic network flows in real-time, which is used to support equilibrium path planning. Moreover, the traditional iterative methods cannot meet the real-time demand of emergency equilibrium path planning decision generation. To solve the above problems, this paper proposes a hybrid control architecture for path planning based on equilibrium traffic assignment theory. The architecture introduces the travelers’ real-time travel data and constructs a spatio-temporal neural network, which captures the evolution of traffic network loads. Adaptive multi-graph fusion technology is used to mix the background traffic flow data and the traveler’s real-time Origin–Destination (OD) data, to mine the dynamic correlation between the traffic state and the travelers’ travel. Based on the real-time prediction of dynamic network states, equilibrium mapping learning is carried out to pre-allocate potential travel demands and construct equilibrium traffic graphs based on system optimization traffic assignment. Finally, individual evacuation path strategies are generated online in a data-driven manner in real time to achieve improved resilience in the transportation system.