Search

Driving style identification is of vital importance for intelligent driving system design and urban traffic management. This study aims to identify and analyze driving styles using large-scale ride-hailing GPS data taking different time periods, traffic, and weather conditions into account. The large-scale GPS data are collected and preprocessed, and then, the k-means clustering is implemented to acquire driving behavior. The modified latent Dirichlet allocation topic approach is applied to extract the driving states as the latent variables behind driving behaviors and finally recognize driving styles. The results show that driving styles are composed of five driving states with different probability combinations. Different driving styles in different situations are further analyzed and compared. When considering the impact of peak periods on the driving style, it indicates that styles tend to be conservative in the morning peak, free and dispersed in the evening peak, and diverse in the off-peak hours. While comparing styles regarding the influence of workdays, drivers act more cautiously and conservatively on weekdays but freer on weekends without the pressure of peak hours. The weather factor is also explored and rainy days are verified to be the resistance of driving so that most drivers become cautious and conservative. Finally, two aberrant driving styles are discovered and countermeasures are suggested to improve traffic safety. [ABSTRACT FROM AUTHOR]

The inconvenience of travel, air pollution and consequent economic losses caused by traffic congestion have seriously restricted the healthy and sustainable development of cities in China. In this context, as the main component of current and future urban traffic management measures, intelligent transportation system is an important means to improve the traffic efficiency of road network and alleviate urban traffic congestion. Traffic flow prediction plays an important role in this connection. In this paper, an ensemble short-term traffic flow prediction method based on optimized variational mode decomposition (OVMD) and combined long short-term memory network (LSTM) is proposed. The method consists of three main components: 1. Use the improved bat algorithm to optimize the parameters of VMD to achieve better decomposition effect; 2. Use the optimized variational mode decomposition algorithm (OVMD) to decompose the unstable original traffic flow time series data into relatively stable multiple Intrinsic Mode Functions (IMFs); 3. The optimized L-BILSTM model is established by combining the basic long short-term memory network with the bidirectional long short-term memory network. It can better extract information from traffic flow data and improve the accuracy of prediction results. In the empirical study part, the traffic flow data of Changsha City is used to verify the prediction model proposed in this paper. The influence of the application of the variational mode decomposition algorithm to the training set data and the overall data on the final prediction results is also compared and analysed. [ABSTRACT FROM AUTHOR]

The accurate forecasting of traffic states is an essential application of intelligent transportation system. Due to the periodic signal control at intersections, the traffic flow in an urban road network is often disturbed and expresses intermittent features. This study proposes a forecasting framework named the spatiotemporal gated graph attention network (STGGAT) model to achieve accurate predictions for network‐scale traffic flows on urban roads. Based on license plate recognition (LPR) records, the average travel times and volume transition relationships are estimated to construct weighted directed graphs. The proposed STGGAT model integrates a gated recurrent unit layer, a graph attention network layer with edge features, a gated mechanism based on the bidirectional long short‐term memory and a residual structure to extract the spatiotemporal dependencies of the approach‐ and lane‐level traffic volumes. Validated on the LPR system in Changsha, China, STGGAT demonstrates superior accuracy and stability to those of the baselines and reveals its inductive learning and fault tolerance capabilities. [ABSTRACT FROM AUTHOR]

Exploring urban travel patterns can analyze the mobility regularity of residents to provide guidance for urban traffic planning and emergency decision. Clustering methods have been widely applied to explore the hidden information from large-scale trajectory data on travel patterns exploring. How to implement soft constraints in the clustering method and evaluate the effectiveness quantitatively is still a challenge. In this study, we propose an improved trajectory clustering method based on fuzzy density-based spatial clustering of applications with noise (TC-FDBSCAN) to conduct classification on trajectory data. Firstly, we define the trajectory distance which considers the influence of different attributes and determines the corresponding weight coefficients to measure the similarity among trajectories. Secondly, membership degrees and membership functions are designed in the fuzzy clustering method as the extension of the classical DBSCAN method. Finally, trajectory data collected in Shenzhen city, China, are divided into two types (workdays and weekends) and then implemented in the experiment to explore different travel patterns. Moreover, three indices including Silhouette Coefficient, Davies–Bouldin index, and Calinski–Harabasz index are used to evaluate the effectiveness among the proposed method and other traditional clustering methods. The results also demonstrate the advantage of the proposed method. [ABSTRACT FROM AUTHOR]

Extracting travel patterns from large-scaled vehicle trajectories is the key step to analyze urban travel characteristics, which can also provide effective strategies for urban traffic planning, construction, management and policy decision. In this study, we adopt the DBSCAN (Density-Based Spatial Clustering of Application with Noise) algorithm by fusing spatial, temporal and directional attributes extracting from vehicle trajectories Furthermore, LCS (Longest Common Sequences) is adopted to estimate spatial similarity, and two measurements are also designed to evaluate the temporal and directional similarity between trajectories. Accordingly, a statistical feature-based parameter optimization method is proposed in the clustering process to achieve reasonable clustering results. Finally, trajectory data collected from Harbin city, China are used to validate the effectiveness of clustering method. A comparison of clustering results considering different combination of attributes is conducted to further demonstrate the advantage of the proposed model. • An improved DBSCAN algorithm is proposed by fusing multi-attributes. • Spatial, temporal and directional attributes are extracted from trajectories. • The LCS is adopted to estimate spatial similarity between trajectories. • A statistical feature-based parameter optimization method is proposed. • A comparison is conducted to demonstrate the effectiveness of the model. [ABSTRACT FROM AUTHOR]

The growth of urban traffic in recent decades has led to environmental problems in terms of increased emissions. In some cities located along waterfronts, multimodal transportation that includes ferry trips plays an important role in public transportation. Compared with roadway traffic, ferry service can often provide shorter routes between given origins and destinations as well as reduce emissions. However, in some areas with high ferry demand, travel delay occurs frequently because of traffic congestion caused by drivers waiting to board the ferry, which can significantly increase travel time and decrease its reliability. In addition, changes in other factors, such as fuel prices, also may influence drivers’ decision making processes in terms of route choice. In this paper, a study focusing on travel time and travel time reliability of ferry service during peak travel periods is performed. Furthermore, as a key result an emission loss model under multimodal conditions is developed that also takes travel cost into account. The analysis of route choice is conducted based on a mixed logit model which is able to handle individual preference. Based upon validation with data from the Seattle area, the proposed model is verified as an efficient way to analyse emission factors in a multimodal transportation environment. [ABSTRACT FROM AUTHOR]

Understanding the spatiotemporal characteristics of traffic congestion is the cornerstone of generating traffic management and control strategies. Based on the large-scale taxi trajectory data in Shenzhen, China, this study designs an effective framework to explore the spatiotemporal patterns of traffic congestions. To bridge trajectory data with urban road networks, we develop a two-stage map-matching method from the aspects of distance and angle. Then, the free-flow speed of each road segment is extracted and employed to identify traffic congestion. In this way, a novel complex network method, named chronological network (chronnet), is utilized for traffic congestion modeling, and we employ an overlapping community detection algorithm to identify region-level bottlenecks. According to the network properties, we explore the influence scope of traffic congestions and uncover the role of each road segment in the propagation process. Meanwhile, community detection results indicate that there are typical local clustering structures in traffic congestions, and each community also has its unique traffic characteristics. Overall, these findings reveal that the complex network can effectively mine the consecutive patterns of traffic congestion. [ABSTRACT FROM AUTHOR]

Investigating the correlation relationship among traffic flow parameters (speed, time headway, volume) and accurately estimating their distribution function at urban road intersections are critical to provide theoretical support for traffic simulation in traffic management and control. Previous studies usually investigated distributions of traffic flow parameters separately, and they did not take into account the correlation between these parameters. In this study, a copula-based approach is proposed to analyze the dependence structure and model the multivariate distribution of traffic flow parameters during peak and off-peak hours in three directions at the intersections. First, the correlation between the traffic flow parameters/variables is examined by Kendall's tau and Spearman's rho to measure the correlation relationship. Then, fitting marginal distributions for traffic variables is conducted. The distribution function with the best fitting performance of each traffic variable is selected based on AIC and K–S tests. Moreover, copula-based models that employ Gaussian, FGM, Gumbel, Clayton, Frank and AMH copula functions are used to construct the bivariate joint distribution. The optimal copula model is selected by using the log-likelihood and AIC to evaluate fitting results. Finally, by comparing the observed data with the same size simulated data generated from the best fitting copula model, we find that the copula-based model could accurately construct the bivariate joint distribution and reproduce the dependence structure between the variables. Overall, the findings of this study provide an in-depth perspective on the dependence structure of traffic variables at urban road intersections. • A copula-based approach is proposed to analyze the dependence relationship and model the multivariate distribution of traffic flow variables. • The dependence structure between the traffic flow variables is examined by Kendall's tau and Spearman's rho. • The log-likelihood and AIC is used to determine the optimal copula model. • The copula-based model could accurately construct the bivariate joint distribution and reproduce the dependence structure between the variables. [ABSTRACT FROM AUTHOR]