Traffic Forecasting Research Articles

Enhanced Information Graph Recursive Network for Traffic Forecasting

Accurate traffic forecasting is crucial for the advancement of smart cities. Although there have been many studies on traffic forecasting, the accurate forecasting of traffic volume is still a challenge. To effectively capture the spatio-temporal correlations of traffic data, a deep learning-based traffic volume forecasting model called the Enhanced Information Graph Recursive Network (EIGRN) is presented in this paper. The model consists of three main parts: a Graph Embedding Adaptive Graph Convolution Network (GE-AGCN), a Modified Gated Recursive Unit (MGRU), and a local information enhancement module. The local information enhancement module is composed of a convolutional neural network (CNN), a transposed convolutional neural network, and an attention mechanism. In the EIGRN, the GE-AGCN is used to capture the spatial correlation of the traffic network by adaptively learning the hidden information of the complex topology, the MGRU is employed to capture the temporal correlation by learning the time change of the traffic volume, and the local information enhancement module is employed to capture the global and local correlations of the traffic volume. The EIGRN was evaluated using the real datasets PEMS-BAY and PeMSD7(M) to assess its predictive performance The results indicate that the forecasting performance of the EIGRN is better than the comparison models.

Multilevel Federated Learning-Based Intelligent Traffic Flow Forecasting for Transportation Network Management

Accurate traffic flow forecasting is crucial to improving traffic safety and alleviating road congestion for intelligent transportation network management. Recently, spatial-temporal graph-based deep learning methods have achieving significant performance improvements in traffic flow forecasting. However, they only consider spatial-temporal correlation of traffic network but ignore a mass of semantic correlation. In addition, they need to centralize data for training models, leading to privacy leakage concern. To tackle these problems, we introduce a federated learning-based intelligent traffic flow forecasting model that integrates our proposed spatial-temporal graph-based deep learning model into the devised Multilevel Federated Learning framework(MFL), named MFVSTGNN. This MFL is used to allow data collaboration among different data owners to train an efficient model without sharing their private data, while achieving the trade-off between communication overhead and computation performance. The proposed spatial-temporal graph-based deep learning model is composed of two phases. The first phase utilizes Variational Graph Autoencoder (VGAE) to dynamically generate adjacency matrix that contains both the spatial and semantic dependencies, contributing to preserving valuable information for improving prediction accuracy, and the second phase employs general spatial-temporal graph neural network to conduct prediction. We evaluate the performance of MFVSTGNN with two large-scale traffic datasets from California and Los Angeles County. The experimental results demonstrate the superior performance of MFVSTGNN in reducing communication overhead, and improving prediction accuracy, validating the effectiveness of our proposed model.

Spatial-temporal gated graph convolutional network: a new deep learning framework for long-term traffic speed forecasting

The key to solving traffic congestion is the accurate traffic speed forecasting. However, this is difficult owing to the intricate spatial-temporal correlation of traffic networks. Most existing studies either ignore the correlations among distant sensors, or ignore the time-varying spatial features, resulting in the inability to extract accurate and reliable spatial-temporal features. To overcome these shortcomings, this study proposes a new deep learning framework named spatial-temporal gated graph convolutional network for long-term traffic speed forecasting. Firstly, a new spatial graph generation method is proposed, which uses the adjacency matrix to generate a global spatial graph with more comprehensive spatial features. Then, a new spatial-temporal gated recurrent unit is proposed to extract the comprehensive spatial-temporal features from traffic data by embedding a new graph convolution operation into gated recurrent unit. Finally, a new self-attention block is proposed to extract global features from the traffic data. The evaluation on two real-world traffic speed datasets demonstrates the proposed model can accurately forecast the long-term traffic speed, and outperforms the baseline models in most evaluation metrics.

Traffic demand prediction based on spatial-temporal guided multi graph Sandwich-Transformer

The ability of spatial-temporal traffic demand prediction is crucial for urban computing, traffic management and future autonomous driving. In this paper, a novel Spatial-Temporal Guided Multi-graph Sandwich-Transformer (STGMT) is suggested to address the ubiquitous spatial-temporal heterogeneity in traffic demand forecasting. Compared to the original Transformer, we employ Time to Vector (Time2Vec) and Node to Vector (Node2Vec) in the embedding layer to obtain universal representations for temporal nodes and spatial nodes, respectively, which are then combined to form Spatial-Temporal Embedding (STE) blocks. The STE guides the attention mechanism, maintaining a unique parameter space for spatial-temporal nodes and enabling the learning of node-specific patterns. In STGMT, we develop Multi-head Temporal Attention (MTA) and Multi-head Temporal Interactive Attention (MTIA) for extracting temporal features, while Multi-head Spatial Attention (MSA) is employed for extracting spatial features. Furthermore, MSA incorporates both the accessibility graph determined by road topology and the similarity graph determined by specific traffic events to characterize the pairwise relationships among spatial nodes. Various attentions and feed-forward layers are rearranged and combined to form the Sandwich-Transformer. Extensive experiments are conducted on public datasets of node-level tasks of two different types (highway and urban) and indicate that the STGMT outperforms state-of-the-art models. The proposed STGMT effectively addresses the ubiquitous spatial-temporal heterogeneity challenge in traffic demand forecasting, thereby enhancing the accuracy of traffic demand prediction and offering valuable guidance for traffic planning and operations. Our code and data are open source at https://github.com/YanJieWen/STGMT-Tensorflow-implementation.

Semantics-Aware Dynamic Graph Convolutional Network for Traffic Flow Forecasting

Traffic flow forecasting is a challenging task due to its spatio-temporal nature and the stochastic features underlying complex traffic situations. Currently, Graph Convolutional Network (GCN) methods are among the most successful and promising approaches. However, most GCNs methods rely on a static graph structure, which is generally unable to extract the dynamic spatio-temporal relationships of traffic data and to interpret trip patterns or motivation behind traffic flows. In this paper, we propose a novel Semantics-aware Dynamic Graph Convolutional Network (SDGCN) for traffic flow forecasting. A sparse, state-sharing, hidden Markov model is applied to capture the patterns of traffic flows from sparse trajectory data; this way, latent states, as well as transition matrices that govern the observed trajectory, can be learned. Consequently, we can build dynamic Laplacian matrices adaptively by jointly considering the trip pattern and motivation of traffic flows. Moreover, high-order Laplacian matrices can be obtained by a newly designed forward algorithm of low time complexity. GCN is then employed to exploit spatial features, and Gated Recurrent Unit (GRU) is applied to exploit temporal features. We conduct extensive experiments on three real-world traffic datasets. Experimental results demonstrate that the prediction accuracy of SDGCN outperforms existing traffic flow forecasting methods. In addition, it provides better explanations of the generative Laplace matrices, making it suitable for traffic flow forecasting in large cities and providing insight into the causes of various phenomena such as traffic congestion. The code is publicly available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/gorgen2020/SDGCN</uri> .

Deep Collaborative Intelligence-Driven Traffic Forecasting in Green Internet of Vehicles

Accompanied with the development of green wireless communication, the green Internet of Vehicles (GIoV) has been a latent solution for future transportation. Among them, intelligent traffic forecasting for key nodes in GIoV is a significant research topic. Much research had been devoted to this issue, and graph learning-based approaches seemed to be a promising solution. However, existing research works concentrated more on graph-structured features in GIoV yet neglected global reliability. To deal with such issue, this work combines both deep embedding and graph embedding together and proposes a deep collaborative intelligence-driven traffic forecasting model in GIoV. By establishing more reliable feature spaces for traffic flow prediction, forecasting efficiency is expected to be promoted. Specifically, deep embedding is utilized to generate more abstract representation for basic features of road networks, and graph embedding is employed to update feature representation for different timestamps. Their collaboration contributes to considerable reliability. In addition, experiments are also conducted on a real-world dataset, and the results indicate that forecasting deviation receives about 15%-25% reduction.

Long-term traffic pattern forecasting using dynamic classifier selection

Dynamic Classifier Selection (DCS) techniques aim to select the most competent classifiers from an ensemble per test sample. For each test sample, only a subset of the most competent classifiers is used to estimate its target value. The performance of the DCS highly depends on how we define the local region of competence, which is a local region in the feature space around the test sample. In this paper, we propose a new definition of region of competence based on a new proximity measure. We exploit the observed similarities between traffic profiles at different links, days and hours to obtain similarities between different values. Furthermore, long-term traffic pattern prediction is a complex problem and most of the traffic prediction literature are based on time-series and regression approaches and their prediction time is limited to next few hours or days. We tackle the long-term traffic pattern prediction as a classification of discretized traffic indicators to improve the accuracy of urban traffic pattern forecasting of next weeks by using DCS. We also employ two different link clustering methods, for grouping traffic links. For each cluster, we train a dynamic classifier system for predicting the traffic variables (flow, speed and journey time). Our results on strategic road network data shows that the proposed method outperforms the existing ensemble and baseline models in long-term traffic prediction.

Pattern Discovery and Multi-Slot-Ahead Forecast of Network Traffic: A Revisiting to Gaussian Process

The forecast of network traffic with arbitrary predicting horizon is a key enabler of smart management in next-generation networks, as sufficient amount of time can be provided for the proactive manipulation of network resources to maintain high quality transmission. Nevertheless, the evolving characteristic of network traffic challenges the current learning-based and data-driven algorithms on both prediction accuracy and computational complexity. In this work, we explore special properties of network traffic, which are further encoded into the Gaussian Process (GP)-based online learning framework, so as to better comprehend and predict future network traffic from a Bayesian perspective. Specifically, we proceed by three steps, 1). Observing network traffic is evolving, to explore and exploit the dynamic traffic patterns at different times and time-scales, we try to approximate the optimal kernel function of GP by utilizing a mixture of Gaussian to encode the dominant and several nondominant patterns. 2). As network traffic at different time-scales share several common patterns, we adopt Process Convolution (PConv) to fully exploit correlations among multiple subsequent time-slots, so as to facilitate network traffic forecast with large predicting horizon. 3). To promote the tracking capability of the proposed GP-PConv framework without significantly increasing the number of hyper-parameters to train, we slightly modify the GP-based prediction through Lyapunov optimization, which brings performance improvements both in terms of accuracy and computational complexity. Finally, we demonstrate the superiority of the proposed algorithm through simulation.

An empirical analysis of airport capacity evaluation: insights regarding air traffic design hours

An important and challenging question for air transportation regulators and airport operators is the definition and specification of airport capacity. Airport capacity is rather difficult to describe due to its multi-faceted and dynamic nature, and it depends both on the available infrastructure, on external factors and on operating procedures. Moreover, annual capacity is used for long term planning purposes as a degree of available service volume, but it poses several inefficiencies when measuring the true throughput of the system because of seasonal and daily variations of traffic. Instead, airport throughput is calculated or estimated for a short period of time, usually one hour. This brings about a mismatch: air traffic forecasts typically yield annual volumes, whereas capacity is measured on hourly figures. To manage the right balance between airport capacity and demand, annual traffic volumes must be converted into design hour volumes so that they can be compared with the true throughput of the system. This comparison is a cornerstone in planning new airport infrastructures, as design-period parameters are important for airport planners in anticipating where and when congestion occurs. Although the design hour for airport traffic has historically had a number of definitions, it is necessary to improve the way air traffic design hours are selected. By reviewing the relationships between hourly and annual air traffic volumes at 50 European airports during the period 2004-2021, this paper discusses the problem of defining a suitable peak hour for capacity evaluation purposes. Additionally, we appraise different daily traffic distribution patterns and their variation by hour of the day. The clustering of airports with respect to their capacity, operational, and traffic characteristics allows us to discover functional relationships between design hours and annual volumes. These relationships help us to propose empirical methods to derive expected traffic in design hours from annual volumes. This could be used to properly assess airport expansion projects or to optimise resource allocation tasks. Finally, we provide new evidence on the nature of airport capacity and the dynamics of air traffic design hours.

Cloud Model-Based Fuzzy Inference System for Short-Term Traffic Flow Prediction

Since traffic congestion during peak hours has become the norm in daily life, research on short-term traffic flow forecasting has attracted widespread attention that can alleviate urban traffic congestion. However, the existing research ignores the uncertainty of short-term traffic flow forecasting, which will affect the accuracy and robustness of traffic flow forecasting models. Therefore, this paper proposes a short-term traffic flow forecasting algorithm combining the cloud model and the fuzzy inference system in an uncertain environment, which uses the idea of the cloud model to process the traffic flow data and describe its randomness and fuzziness at the same time. First, the fuzzy c-means algorithm is selected to carry out cluster analysis on the original traffic flow data, and the number and parameter values of the initial membership function of the system are obtained. Based on the cloud reasoning algorithm and the cloud rule generator, an improved fuzzy reasoning system is proposed for short-term traffic flow predictions. The reasoning system cannot only capture the uncertainty of traffic flow data, but it also can describe temporal dependencies well. Finally, experimental results indicate that the proposed model has a better prediction accuracy and better stability, which reduces 0.6106 in RMSE, reduces 0.281 in MAE, and reduces 0.0022 in MRE compared with the suboptimal comparative methods.

A hybrid model of neural network with VMD–CNN–GRU for traffic flow prediction

An effective traffic flow prediction can serve as a foundation for control decisions on intelligent transportation. However, in view of the nonstationarity and complexity of traffic flow sequences, it is impossible to fully extract the dynamic change laws of time-series based on traditional forecasting models. Traffic flow data are often disturbed by noise during the collection. The existence of noise data may affect the features of the sequence itself or cover the real change trend of the series, resulting in the decline of prediction reliability. A hybrid prediction model based on variational mode decomposition–convolutional neural network–gated recurrent unit (VMD–CNN–GRU) is presented to increase the predictability of traffic flow, which is combined by VMD, CNN and GRU. First, the original time-series is decomposed into K components by VMD, and the noise part is eliminated to improve the modeling accuracy. Next, the time characteristics of traffic flow are mined by constructing the CNN–GRU network in Keras, a deep learning framework. Each sub-sequence is trained and predicted separately as an input vector. The total expected value of traffic flow is then calculated by superimposing the predicted value of each subsequence. The model performance is verified by the open-source dataset of actual England highways. The results show that compared with other models, the hybrid model established in this paper significantly raises the precision of traffic flow forecasting. The results could offer some useful insights for predicting traffic flow.

Graph dropout self-learning hierarchical graph convolution network for traffic prediction

Traffic prediction is a challenging topic in urban traffic construction and management due to its complex dynamic spatial–temporal correlations. Currently, graph neural network achieves good results in traffic prediction, but the existing methods usually do not take into account the multi-layer information of the graph and the redundant transmission of information. Moreover, they do not consider the over-smoothing of the graph. In this paper, we propose a novel graph dropout self-learning hierarchical graph convolution network (DHGCN). Firstly, we design a self-learning hierarchical graph convolution network, which captures spatial features at different layers through multiple self-learning dynamic graphs and avoids redundant information transmission. Secondly, a novel graph dropout structure is proposed to sparsify the graph and avoid the over-smoothing of the graph. Meanwhile, an encoder–decoder architecture with gated residuals is designed to capture dynamic temporal features. In addition, this paper addresses two important traffic forecasting tasks: traffic flow and traffic speed. Extensive experiments with six real-world datasets verify that our method achieves state-of-the-art performance in both traffic flow and traffic speed and consistently outperforms baselines.

Fridays for Future and Mondays for Memes: How Climate Crisis Memes Mobilize Social Media Users

Modern protest movements rely on digital activism on social media, which serves as a conduit for mobilization. In the social media landscape, internet memes have emerged as a popular practice of expressing political protest. Although it is known that social media facilitates mobilization, researchers have neglected how distinct types of content affect mobilization. Moreover, research regarding users’ perspectives on mobilization through memes is lacking. To close these research gaps, this study investigates memes in the context of climate protest mobilization. Based on the four-step model of mobilization, a survey of users who create and share memes related to the Fridays for Future movement on social media (&lt;em&gt;N&lt;/em&gt; = 325) revealed that the prosumption of climate crisis memes increases users’ issue involvement and strengthens their online networks. These factors serve as crucial mediators in the relationship between users’ prosumption of climate crisis memes and political participation. The results suggest that mobilization through memes is effective at raising awareness of political issues and strengthening online discussion networks, which means that it has strategic potential for protest movements. By looking at memes from the perspective of their creators and examining a specific type of social media content, this study contributes to the literature on digital mobilization.

Empirical Research on Machine Learning Models and Feature Selection for Traffic Congestion Prediction in Smart Cities

The development of smart cities has occurred over the past ten years. One primary goal of “smart city” initiatives is to lessen vehicle congestion. Several innovative technologies, including vehicular communications, navigation, and traffic control, have been created by Vehicle Networking System to address this problem. The traffic data gathered by smart devices aids in the forecasting of traffic in smart cities. This project created an Intelligent Traffic Congestion Management System (ITCMS) that uses machine learning techniques and traffic data from Kaggle to decrease the amount of time spent stuck in traffic. This study aims to assess feature selection methods and machine learning models for traffic forecasting in smart cities. The feature dimension is reduced using feature selection techniques, such information gain, correlation attribute, and principal component analysis. The recommended model successfully predicted traffic flow, assisting in the alleviation of congestion. The principal component analysis with random forest model outperforms the other machine learning models and has a 95% accuracy rate.

Forecasting Traffic Speed during Daytime from Google Street View Images using Deep Learning

Traffic forecasting plays an important role in urban planning. Deep learning methods outperform traditional traffic flow forecasting models because of their ability to capture spatiotemporal characteristics of traffic conditions. However, these methods require high-quality historical traffic data, which can be both difficult to acquire and non-comprehensive, making it hard to predict traffic flows at the city scale. To resolve this problem, we implemented a deep learning method, SceneGCN, to forecast traffic speed at the city scale. The model involves two steps: firstly, scene features are extracted from Google Street View (GSV) images for each road segment using pretrained Resnet18 models. Then, the extracted features are entered into a graph convolutional neural network to predict traffic speed at different hours of the day. Our results show that the accuracy of the model can reach up to 86.5% and the Resnet18 model pretrained by Places365 is the best choice to extract scene features for traffic forecasting tasks. Finally, we conclude that the proposed model can predict traffic speed efficiently at the city scale and GSV images have the potential to capture information about human activities.

Treatment cascade for patients with multidrug- or rifampicin-resistant tuberculosis and associated factors with patient attrition in southeastern China: a retrospective cohort study

ObjectivesTo address gaps in health services for multidrug- or rifampicin-resistant tuberculosis (MDR/RR-TB), a treatment cascade model was used to evaluate patient retention and attrition at each successive step required to achieve a successful treatment outcome. MethodsFrom 2015–2018, a four-step treatment cascade model was established in patients with confirmed MDR/RR-TB in southeast China. Step 1: diagnosis of MDR/RR-TB, step 2: Initiation of treatment, step 3: still under treatment at 6 month and step 4: cure or completion of MDR/RR-TB treatment, with each successive step including a gap that shows attrition of patients between steps. The retention and attrition of each step were graphed. Multi-variate logistic regression was carried out to further identify potential factors associated with the attrition. ResultsIn the treatment cascade consisting of 1752 MDR/RR-TB patients, the overall patient attrition rate was 55.8% (978/1752), with 28.0% (491/1752), 19.9% (251/1261), and 23.4% (236/1010) of patients attrition in the first, second, and third gap. Factors associated with MDR/RR-TB patients not initiating treatment included age ≥60 years (OR:2.875), and time for diagnosis ≥30 days (OR: 2.653). Patients who were diagnosed with MDR/RR-TB through rapid molecular test (OR: 0.517) and non-migrant residents of Zhejiang Province (OR: 0.273) both exhibited a lower likelihood of attrition during the treatment initiation phase. Meanwhile, old age (OR: 2.190) and non-resident migrants to the province were factors associated with not completing ≥ 6 months of treatment. Old age (OR: 3.883), retreatment (OR: 1.440), and time to diagnosis ≥30 days (OR: 1.626) were factors contributing to poor treatment outcomes. ConclusionSeveral programmatic gaps were identified in the MDR/RR-TB treatment cascade. Future policies should provide more comprehensive support for vulnerable populations to improve the care quality at each step.

Graph transformer based dynamic multiple graph convolution networks for traffic flow forecasting

AbstractTraffic prediction is an important part of intelligent transportation system. Recently, graph convolution network (GCN) is introduced for traffic flow forecasting and achieves good performance due to its superiority of representing the graph traffic road structure network. Moreover, the dynamic GCN is put forward to model the temporal property of the traffic flow. Although great progress has been made, most GCN based traffic flow forecasting methods utilize a single graph for convolution, which is considered not enough to reveal the inherent property of traffic graph as it is influenced by many factors, for example weather, season and traffic accidents etc. In this paper, an exotic graph transformer based dynamic multiple graph convolution networks (GTDMGCN) is conceived for traffic flow forecasting. Instead of the single graph, multiple graphs are constructed to modulate the complex traffic network by the proposed graph transformer network. Additionally, a temporal gate convolution is proposed to get the temporal property of traffic flow. The proposed GTDMGCN model is evaluated on four real traffic datasets of PEMS03, PEMS04, PEMS07, PEMS08, and there are average increments of 9.78%, 7.80%, 5.96% under MAE, RMSE, and MAPE metrics compared with the current results.

A Framework for Urban Last-Mile Delivery Traffic Forecasting: An In-Depth Review of Social Media Analytics and Deep Learning Techniques

The proliferation of e-commerce in recent years has been driven in part by the increasing ease of making purchases online and having them delivered directly to the consumer. However, these last-mile delivery logistics have become complex due to external factors (traffic, weather, etc.) affecting the delivery routes’ optimization. Intelligent Transportation Systems (ITS) also have a challenge that contributes to the need of delivery companies for traffic sensors in urban areas. The main purpose of this paper is to propose a framework that closes the gap on accurate traffic prediction tailored for last-mile delivery logistics, leveraging social media analysis along with traditional methods. This work can be divided into two stages: (1) traffic prediction, which utilizes advanced deep learning techniques such as Graph Convolutional and Long-Short Term Memory Neural Networks, as well as data from sources such as social media check-ins and Collaborative Innovation Networks (COINs); and (2) experimentation in both short- and long-term settings, examining the interactions of traffic, social media, weather, and other factors within the model. The proposed framework allows for the integration of additional analytical techniques to further enhance vehicle routing, including the use of simulation tools such as agent-based simulation, discrete-event simulation, and system dynamics.

Spatiotemporal dynamic graph convolutional network for traffic speed forecasting

Accurate traffic speed forecasting is challenging because of complex spatiotemporal correlations of traffic data. Some studies have recognized that correlations among sensors change gradually and have constructed dynamic graphs to reflect this change. However, they ignored the temporal dependencies among dynamic graphs, resulting in an inability to capture the deep dynamic dependencies among sensors. Few studies have explored the hybrid interaction patterns of static and dynamic graphs, hindering the adequate exploration of spatial dependencies. Therefore, a novel deep learning model is proposed in this study to address these problems and produce accurate traffic speed forecasting. First, a new graph generation method is proposed to capture the deep dynamic dependencies among sensors, which exploits historical information of dynamic graphs to develop temporal dependencies among dynamic graphs. Then, a new fusion strategy is proposed to investigate the hybrid interaction patterns of static and dynamic graphs, which effectively mines hidden information in graphs to fully extract spatial dependencies. Finally, a new spatiotemporal network architecture is proposed, which unifies the proposed graph generation method and fusion strategy into a consistent framework and yields the final forecasting results. Experimental results on two real-world traffic datasets indicate that the proposed model outperforms state-of-the-art models.

A secondary decomposition–ensemble approach to interval predicting China’s railway container volume

Precise forecasts of railway container demand is crucial for railway infrastructure construction and daily operations management. Nevertheless, temporal variations in railway container traffic are subject to a diversity of factors, and such dynamics are therefore extremely difficult to capture in forecasts. Decomposing the temporal data into a number of subseries with distinct qualities is a prevalent technique for reducing the complexity of data. Yet, a few of sub-series resulted from such decomposition tend to remain irregular and unstable. In this study, a novel secondary decomposition–ensemble method is proposed for railroad container volume forecasting. Specifically, CEEDMAN and VMD are employed successively to decompose the time series into various components. The sub-series are processed by different models, according to their distinct features, to yield their respective independent predictions, which are then ensembled to give the final railway container traffic forecast. Additionally, we incorporate the DEEPAR model for interval predictions, providing valuable uncertainty information that assists decision-makers in preparing for potential challenges. Our method demonstrates superior accuracy and stability compared to other benchmark models, even in the presence of disruptive events such as the big epidemic. We further validate the applicability and robustness of the proposed method by incorporating an additional dataset with a finer-time data. Our findings contribute to the field of railway container demand forecasting and offer practical insights for decision-makers in the railway industry.