Urban Traffic Data Research Articles

New ways of collecting urban freight traffic data and applications for urban freight policies and research

The current quality of data on urban logistics traffic patterns is poor. Data are scarce, heterogeneous, often old and expensive to collect. This research looks at new ways to collect urban freight data and make that data available to both policy-makers and academia. Three case studies are examined: Rotterdam, the Netherlands; Brussels, Belgium; and Barcelona, Spain. They help identify new sources of data from traffic and parking policies: automated number plate recognition cameras, an on-street delivery smartphone app, and a truck pricing scheme. Both the context in which new data sources of interest to urban logistics are produced, and the level of appropriation of these data by local stakeholders and the research community are examined. We then construct an analysis grid to evaluate the diversity of systems (technical and socio-technical) producing data relevant to urban logistics. This analysis framework can be used to facilitate comparisons between data sources and thus help future case studies. In the three cases, we found that local governments use the data more than researchers do. The issue of data dissemination raises questions about costs (who is to bear the cost of storing, maintaining and extracting data sets?) as well as regulatory questions. We conclude that local administrations should be encouraged to work towards harmonizing data collection methods and data sharing conditions in order to improve the quality and comparability of the data. Cities in countries with little access to new sources of data, such as France for regulatory reasons, should try to find ways to create data source opportunities. In all countries, urban freight research communities should be encouraged to use the now increasingly available data.

Transfer Learning for Cross-City Traffic Prediction to Solve Data Scarcity

Deep learning models have demonstrated significant achievements in traffic prediction. However, their predictive performance substantially declines when faced with the scarcity of urban traffic data. Addressing the challenges of data scarcity and heterogeneity between cities, cross-city transfer learning has emerged as a promising solution. This paper proposes a domain adaptation cross-city model, which integrates traffic data with auxiliary urban data for domain adaptation in cross-city transfer learning. Specifically, we designed a domain fusion module to measure the differences between cities. Firstly, the knowledge extractor within the domain fusion module learns the knowledge from urban auxiliary data, such as road networks and points of interest, and calculates transferable knowledge. Then, dynamic time warping is used to measure the similarity of traffic time series. By combining these two aspects, we derive the domain differences between cities. Finally, the spatiotemporal network undergoes pre-learning using abundant data from the source city. According to the differences between cities, the model is fine-tuned to improve the adaptability of the model to the target domain. Experimental results on real-world data validate the effectiveness of the proposed model.

Exploring the Relationship between Data Sample Size and Traffic Flow Prediction Accuracy

Efficiently extracting and analyzing large urban traffic data, accurately predicting traffic conditions, and improving urban traffic management require careful selection of an appropriate data sample size. The suitable size of data sample assumes paramount importance in fostering sustainable transportation development. This paper investigates the relationship between traffic flow prediction performance and data sample size, considering data sample missing rates, duration, and road segment coverage. Real traffic flow data from 13 road sections in Changsha, China, are analyzed using the Decision Tree, Support Vector Machine, Gaussian Process Regression and Artificial Neural Network models. Some key findings include: Lower data sample loss rates improve prediction accuracy by capturing traffic flow patterns effectively, while higher loss rates decrease accuracy; an optimal data sample duration of around 7 days balances prediction accuracy and data stability, with longer durations providing more historical data but risking complexity; Broader road segment coverage gives a more comprehensive traffic flow information, but excessive coverage introduces noise and impacts the improvement of prediction accuracy. The results highlight the significant impact of data sample size on prediction performance. Enhancing reliability can be achieved by reducing data loss, selecting suitable durations, and considering appropriate road segment coverage, supporting improved traffic management and route planning.

Analyzing urban traffic crash patterns through spatio-temporal data: A city-level study using a sparse non-negative matrix factorization model with spatial constraints approach

Urban traffic crashes represent a significant challenge affecting public safety and urban mobility worldwide. This study introduces a novel application of Sparse Non-negative Matrix Factorization with spatial constraints to analyze spatio-temporal patterns of traffic crashes at a city level. Using comprehensive crash data from Denver and Manhattan during 2020, we developed and validated a model capable of capturing distinct temporal dynamics and spatial distributions of traffic crashes. Unlike traditional methods, our approach integrates sparsity and spatial constraints, enhancing the model's ability to handle the inherent sparsity and geographical dependencies found in urban traffic data. The results demonstrate the model's effectiveness in identifying high-risk areas and times, providing actionable insights that can inform urban planning and targeted safety interventions. The study underscores the potential of advanced data-driven techniques in urban traffic analysis and contributes to the broader efforts of improving traffic safety through informed decision-making and policy development.

STVANet: A spatio-temporal visual attention framework with large kernel attention mechanism for citywide traffic dynamics prediction

Enhancing the efficiency and safety of the Intelligent Transportation System requires effective modeling and prediction of citywide traffic dynamics. Most studies employ convolutional neural networks (CNNs) with a 3D convolutional structure or spatio-temporal models with self-attention mechanisms to capture the spatio-temporal information of traffic distribution. Although 3D CNNs excel at capturing local contextual information, they are computationally complex due to the large number of parameters and cannot capture long-range dependence. By contrast, although self-attention mechanisms originally designed to address challenges in natural language processing can capture long-range dependence, their application to 2D image structures requires breaking down the inherent 2D context into a 1D sequence, increasing the computational complexity and neglecting the adaptability between local contextual information and channels. Accordingly, we propose a spatio-temporal visual attention neural network (STVANet), a novel spatio-temporal visual attention 2D CNN, which integrates a unique visual attention module with a large kernel attention (LKA) mechanism, a squeeze-and-excitation (SE) mechanism and a feedforward component to capture long-range dependence and channel information in urban traffic data while preserving the 2D image structure. LKA-based spatio-temporal attention networks extract spatial and temporal features from weekly, daily, and recent hourly periods, and aggregate them with weighted consideration of external features to make predictions. Evaluation of real-world datasets demonstrates STVANet’s superiority over baseline models, showcasing its potential in citywide traffic prediction.

Score-based Graph Learning for Urban Flow Prediction

Accurate urban flow prediction (UFP) is crucial for a range of smart city applications such as traffic management, urban planning, and risk assessment. To capture the intrinsic characteristics of urban flow, recent efforts have utilized spatial and temporal graph neural networks to deal with the complex dependence between the traffic in adjacent areas. However, existing graph neural network based approaches suffer from several critical drawbacks, including improper graph representation of urban traffic data, lack of semantic correlation modeling among graph nodes, and coarse-grained exploitation of external factors. To address these issues, we propose DiffUFP , a novel probabilistic graph-based framework for UFP. DiffUFP consists of two key designs: (1) a semantic region dynamic extraction method that effectively captures the underlying traffic network topology, and (2) a conditional denoising score-based adjacency matrix generator that takes spatial, temporal, and external factors into account when constructing the adjacency matrix rather than simply concatenation in existing studies. Extensive experiments conducted on real-world datasets demonstrate the superiority of DiffUFP over the state-of-the-art UFP models and the effect of the two specific modules.

Multi-scale persistent spatiotemporal transformer for long-term urban traffic flow prediction

Long-term urban traffic flow prediction is an important task in the field of intelligent transportation, as it can help optimize traffic management and improve travel efficiency. To improve prediction accuracy, a crucial issue is how to model spatiotemporal dependency in urban traffic data. In recent years, many studies have adopted spatiotemporal neural networks to extract key information from traffic data. However, most models ignore the semantic spatial similarity between long-distance areas when mining spatial dependency. They also ignore the impact of predicted time steps on the next unpredicted time step for making long-term predictions. Moreover, these models lack a comprehensive data embedding process to represent complex spatiotemporal dependency. This paper proposes a multi-scale persistent spatiotemporal transformer (MSPSTT) model to perform accurate long-term traffic flow prediction in cities. MSPSTT adopts an encoder-decoder structure and incorporates temporal, periodic, and spatial features to fully embed urban traffic data to address these issues. The model consists of a spatiotemporal encoder and a spatiotemporal decoder, which rely on temporal, geospatial, and semantic space multi-head attention modules to dynamically extract temporal, geospatial, and semantic characteristics. The spatiotemporal decoder combines the context information provided by the encoder, integrates the predicted time step information, and is iteratively updated to learn the correlation between different time steps in the broader time range to improve the model's accuracy for long-term prediction. Experiments on four public transportation datasets demonstrate that MSPSTT outperforms the existing models by up to 9.5% on three common metrics.

Urban Traffic Flow Prediction Based on Bayesian Deep Learning Considering Optimal Aggregation Time Interval

Predicting short-term urban traffic flow is a fundamental and cost-effective strategy in traffic signal control systems. However, due to the interrupted, periodic, and stochastic characteristics of urban traffic flow influenced by signal control, there are still unresolved issues related to the selection of the optimal aggregation time interval and the quantifiable uncertainties in prediction. To tackle these challenges, this research introduces a method for predicting urban interrupted traffic flow, which is based on Bayesian deep learning and considers the optimal aggregation time interval. Specifically, this method utilizes the cross-validation mean square error (CVMSE) method to obtain the optimal aggregation time interval and to establish the relationship between the optimal aggregation time interval and the signal cycle. A Bayesian LSTM-CNN prediction model, which extends the LSTM-CNN model under the Bayesian framework to a probabilistic model to better capture the stochasticity and variation in the data, is proposed. Experimental results derived from real-world data demonstrate gathering traffic flow data based on the optimal aggregation time interval significantly enhances the prediction accuracy of the urban interrupted traffic flow model. The optimal aggregation time interval for urban interrupted traffic flow data corresponds to a multiple of the traffic signal control cycle. Comparative experiments indicate that the Bayesian LSTM-CNN prediction model outperforms the state-of-the-art prediction models.

Contextualizing MLP-Mixers Spatiotemporally for Urban Traffic Data Forecast at Scale

Contextualizing MLP-Mixers Spatiotemporally for Urban Traffic Data Forecast at Scale

Diagnosing urban traffic anomalies by integrating geographic knowledge and tensor theory

ABSTRACT Urban traffic anomaly diagnosis is crucial for urban road management and smart city construction. Most existing methods perform anomaly detection from a data-driven perspective and ignore the unique spatiotemporal characteristics of traffic anomalies, resulting in reduced accuracy or incorrect extraction of anomalies. In this study, we integrate geographic methods with high-dimensional tensor theory and develop a comprehensive framework for traffic anomaly diagnosis. The framework is divided into three parts: road traffic status acquisition, traffic anomaly detection, and urban anomaly analysis. First, we perform filtering and map matching on the trajectory data to obtain the traffic states of urban roads and construct them into a tensor. For traffic anomaly detection, a novel Spatio-Temporal constrained Low-Rank Sparse Tensor (ST-LRST) method is constructed to decompose urban traffic data into normal and anomalous components. Specifically, ST-LRST introduces a truncated nuclear norm, as a tighter nonconvex alternative to the tensor low-rank function, to more accurately estimate daily traffic patterns, thus improving the extraction accuracy of the sparse anomaly tensor. The spatiotemporal features of traffic anomalies are embedded into the sparse tensor to reduce the fragmentation and error rate of urban anomaly identification. To analyze anomalies, we study the characteristics of the anomalies detected by ST-LRST, such as duration, impact scope, and impact intensity. Subsequently, combined with crowdsourced geographic information, we comprehensively analyze the anomalous spatiotemporal variations in the road network and explain the factors that induce these urban anomalies. Experiments are performed using traffic data from Xi’an, China, and the results indicate that ST-LRST achieves the most accurate and comprehensive diagnosis of urban anomalies.

City Scale Traffic Monitoring Using WorldView Satellite Imagery and Deep Learning: A Case Study of Barcelona

Accurate traffic data is crucial for a range of different applications such as quantifying vehicle emissions, and transportation planning and management. However, the availability of traffic data is geographically fragmented and is rarely held in an accessible form. Therefore, there is an urgent need for a common approach to developing large urban traffic data sets. Utilising satellite data to estimate traffic data offers a cost-effective and standardized alternative to ground-based traffic monitoring. This study used high-resolution satellite imagery (WorldView-2 and 3) and Deep Learning (DL) to identify vehicles, road by road, in Barcelona (2017–2019). The You Only Look Once (YOLOv3) object detection model was trained and model accuracy was investigated via parameters such as training data set specific anchor boxes, network resolution, image colour band composition and input image size. The best performing vehicle detection model configuration had a precision (proportion of positive detections that were correct) of 0.69 and a recall (proportion of objects in the image correctly identified) of 0.79. We demonstrated that high-resolution satellite imagery and object detection models can be utilised to identify vehicles at a city scale. However, the approach highlights challenges relating to identifying vehicles on narrow roads, in shadow, under vegetation, and obstructed by buildings. This is the first time that DL has been used to identify vehicles at a city scale and demonstrates the possibility of applying these methods to cities globally where data are often unavailable.

Mean-field reinforcement learning for decentralized task offloading in vehicular edge computing

Vehicular Edge Computing (VEC) is a promising paradigm for providing low-latency and high-reliability services in the Internet of Vehicles (IoV). The increasing number of mobile devices and the diverse resource requirements of the growing IoV have resulted in a shift from centralized resource management to a decentralized approach. This shift offers improved fault tolerance, scalability, and privacy preservation. However, constructing collaborative awareness and coordination mechanisms between multiple vehicles and edge nodes in a decentralized manner is a challenge. To address this issue, we propose a decentralized many-to-many task offloading method that aims to minimize the average task completion latency of vehicles. In this study, we propose a data-sharing mechanism between vehicles and edge servers using the digital twin service, which provides global environmental perceptions to the vehicles by a low-cost approach. Additionally, we develop a mean-field multi-agent reinforcement learning algorithm to generate coordinated task offloading schemes. Instead of interacting with multiple agents, the vehicle only needs to respond to the mean action of the environment. Based on this transition, the agent generates coordinated task offloading decisions in complex scenarios. We evaluate the performance of our method using real urban traffic data. Experiment results verify the efficiency of our proposed method.

A STUDY ON THE MORPHOLOGY OF LARGE-SIZED HANDICRAFT STREETS: THE CASES FROM CHINA

China's rich tradition in crafts has given rise to city blocks known for the production, display, and trade of handicrafts. This study focuses on large-sized handicraft streets, particularly those showcasing stone and wood carvings, which stand out in the urban landscape. The research utilizes multiple case studies, combining satellite maps, urban traffic data, and architectural analysis, to explore common and distinctive patterns in the morphology of these craft streets. The findings reveal that these streets are primarily located on the outskirts of cities but have good accessibility for cars, offering large-scale spaces. Additionally, they exhibit variations in streetscape, urban block pattern, and architectural spatial form, allowing for categorization. Understanding the morphology of large-sized craft streets can contribute to preserving and promoting cultural heritage and creative industries.

RL-GCN: Traffic flow prediction based on graph convolution and reinforcement learning for smart cities

The traffic flow problem has become essential in urban planning and management in today’s increasingly urbanized world. Traditional traffic flow prediction models cannot fully consider urban traffic networks’ complex and dynamic characteristics. To this end, this paper proposes a traffic flow prediction method for smart cities (RL-GCN) based on graph convolution, LSTM network and reinforcement learning, aiming to solve the problem of urban traffic flow prediction. Firstly, we use the graph convolutional neural network to process the urban traffic network data features, then use the LSTM network model to learn the temporal information, and then combine the reinforcement learning algorithm to develop the optimal traffic control strategy based on which the future traffic flow is predicted. Our experiments on several datasets show that the model developed in this paper has outstanding performance for urban traffic flow prediction. Compared with the traditional traffic flow prediction methods, the method in this paper has significantly improved prediction accuracy. Our research can provide valuable references and inspiration in urban planning and traffic management.

Exploring the Application of Big Data Visualization Platform in Urban Traffic Data Analysis

With the rapid development of information technology and the popularity of the Internet, the era of big data has come. The urban traffic system continuously generates a large amount of traffic data, which are so large and diverse that the traditional data processing methods have been unable to effectively process and analyze them. Therefore, it is necessary to process and analyze urban traffic data with the help of emerging big data technologies and methods. Starting from introducing the characteristics of big data visualization platforms and common big data visualization tools and technologies, the article analyzes the scale and characteristics of urban traffic data and the limitations of traditional data analysis methods, discusses the advantages and application prospects of visualization platforms, and focuses on the four perspectives of data cleaning and pre-processing, traffic flow and congestion analysis, traffic behavior and trend analysis, traffic simulation, and planning support. The application of big data visualization platforms in urban traffic data analysis is discussed.

MVCV-Traffic: multiview road traffic state estimation via cross-view learning

Fine-grained urban traffic data are often incomplete owing to limitations in sensor technology and economic cost. However, data-driven traffic analysis methods in intelligent transportation systems (ITSs) heavily rely on the quality of input data. Thus, accurately estimating missing traffic observations is an essential data engineering task in ITSs. The complexity of underlying node-wise correlation structures and various missing scenarios presents a significant challenge in achieving high-precision estimation. This study proposes a novel multiview neural network termed MVCV-Traffic, equipped with a cross-view learning mechanism, to improve traffic estimation. The contributions of this model can be summarized into two parts: multiview learning and cross-view fusing. For multiview learning, several specialized neural networks are adopted to fit diverse correlation structures from different views. For cross-view fusing, a new information fusion strategy merges multiview messages at both feature and output levels to enhance the learning of joint correlations. Experiments on two real-world datasets demonstrate that the proposed model significantly outperforms existing traffic speed estimation methods for different types and rates of missing data.

Effects of Mobility Restrictions on Air Pollution in the Madrid Region during the COVID-19 Pandemic and Post-Pandemic Periods

Air quality is one of the problems cities face today. The COVID-19 pandemic provided a unique opportunity to study the influence of traffic reduction on air quality during 2020, 2021, and 2022. The aim of this paper is to analyze the impacts and relationship between mobility restrictions in six COVID-19 wave periods and air pollution and evolution in the post-pandemic period differentiating Madrid city from its metropolitan area. We tested whether the changes produced for NO2, NOx, PM2.5, PM10, and O3 in the urban traffic and suburban traffic air quality stations data in comparison to the 2019 reference period were significant. The findings of this study show that the periods with the greatest reduction in pollutant concentrations were the first and third COVID-19 waves, when mobility restrictions were most stringent: there was strict confinement for the first wave (i.e., 47% reduction in daily average NO2 concentration), while severe weather forced a reduction in traffic in the region in the third wave period (i.e., 41% reduction in daily average NOx concentration). With the return to normal activity in the last period, pollutant concentrations began to exceed pre-pandemic levels. At the urban level, the reductions were more noticeable in relation to NO2 and NOx, while at the suburban level, changes were less prominent, except for the O3. The results are particularly inspiring for designing future mobility strategies for improving air quality in urban and metropolitan areas.

Analysis and Forecast of Traffic Flow between Urban Functional Areas Based on Ride-Hailing Trajectories

Urban planning and function layout have important implications for the journeys of a large percentage of commuters, which often make up the majority of daily traffic in many cities. Therefore, the analysis and forecast of traffic flow among urban functional areas are of great significance for detecting urban traffic flow directions and traffic congestion causes, as well as helping commuters plan routes in advance. Existing methods based on ride-hailing trajectories are relatively effective solution schemes, but they often lack in-depth analyses on time and space. In the paper, to explore the rules and trends of traffic flow among functional areas, a new spatiotemporal characteristics analysis and forecast method of traffic flow among functional areas based on urban ride-hailing trajectories is proposed. Firstly, a city is divided into areas based on the actual urban road topology, and all functional areas are generated by using areas of interest (AOI); then, according to the proximity and periodicity of inter-area traffic flow data, the periodic sequence and the adjacent sequence are established, and the topological structure is learned through graph convolutional neural (GCN) networks to extract the spatial correlation of traffic flow among functional areas. Furthermore, we propose an attention-based gated graph convolutional network (AG-GCN) forecast method, which is used to extract the temporal features of traffic flow among functional areas and make predictions. In the experiment, the proposed method is verified by using real urban traffic flow data. The results show that the method can not only mine the traffic flow characteristics among functional areas under different time periods, directions, and distances, but also forecast the spatiotemporal change trend of traffic flow among functional areas in a multi-step manner, and the accuracy of the forecasting results is higher than that of common benchmark methods, reaching 96.82%.

Toward a Novel RESTFUL Big Data-Based Urban Traffic Incident Data Web Service for Connected Vehicles

Abstract Connected vehicles (CVs) are an emerging technology in intelligent transportation systems. Currently, many data-driven intelligent transportation systems (D2ITS) use CV data. Unfortunately, these D2ITS still need serious improvement before they meet higher-level visualization needs. Thus, we aim to develop a new, intelligent data-driven transportation system framework. We focus on visualizing real-time CV data using a big data analytic system in urban areas. In response, we first propose an effective real-time data distribution approach within the Vehicular Ad-hoc NETwork. Second, we develop novel strategies for aggregating, extracting and ingesting data. We provide scalable and fault-tolerant delivery methods without interruption or delay. Finally, we proposed a novel visualization REpresentational State Transfer (REST) web service. We used Simulation of Urban MObility, OMNET++ and Veins to simulate a traffic incident dataset. Then, we tested the Basic Safety Messages in an experimental big data cluster. We used NIFI, Kafka and Cassandra for ingestion, distribution, delivery and storage. The results show accurate performance for packet loss, packet delivery and communication delay. Also, it indicates high throughput and low latency for distributed data delivery systems. Additionally, we obtained the smallest response time for the RESTFUL visualization web service.

ARDE-N-BEATS: An Evolutionary Deep Learning Framework for Urban Traffic Flow Prediction

Accurate and reliable traffic flow prediction is difficult due to the highly nonlinear, complex, and stochastic natures of urban traffic flow data, but its solutions are critically important for intelligent transportation systems (ITSs) and Internet of Things (IoT). In this study, a novel deep learning framework, named adaptive reinitialized differential evolution (ARDE)-neural basis expansion analysis for time-series forecasting (N-BEATS), is proposed to address this challenge. With the framework of ARDE-N-BEATS, first, an N-BEATS-based deep learning architecture is formulated for modeling traffic flow data. Second, a novel enhanced evolutionary algorithm, termed ARDE, is presented for optimizing the hyperparameter and structure of N-BEATS. Compared to the vanilla differential evolution (DE) algorithm, ARDE exhibits faster convergence and stronger searching capabilities. Experiments on three real-world traffic flow data sets from Dublin and San Francisco demonstrate that ARDE-N-BEATS can achieve high accuracy of at least 94% for most of the predictions, and outperforms the existing counterpart methods. A comparison between different hyperparameter optimization approaches further reveals that ARDE provides better or very competitive predictions and saves as high as 78.90% of computational expense.