Traffic Forecasting Research Articles

Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution

Traffic prediction is the cornerstone of intelligent transportation system. Accurate traffic forecasting is essential for the applications of smart cities, i.e., intelligent traffic management and urban planning. Although various methods are proposed for spatio-temporal modeling, they ignore the dynamic characteristics of correlations among locations on road network. Meanwhile, most Recurrent Neural Network based works are not efficient enough due to their recurrent operations. Additionally, there is a severe lack of fair comparison among different methods on the same datasets. To address the above challenges, in this article, we propose a novel traffic prediction framework, named Dynamic Graph Convolutional Recurrent Network (DGCRN). In DGCRN, hyper-networks are designed to leverage and extract dynamic characteristics from node attributes, while the parameters of dynamic filters are generated at each time step. We filter the node embeddings and then use them to generate dynamic graph, which is integrated with pre-defined static graph. As far as we know, we are first to employ a generation method to model fine topology of dynamic graph at each time step. Furthermore, to enhance efficiency and performance, we employ a training strategy for DGCRN by restricting the iteration number of decoder during forward and backward propagation. Finally, a reproducible standardized benchmark and a brand new representative traffic dataset are opened for fair comparison and further research. Extensive experiments on three datasets demonstrate that our model outperforms 15 baselines consistently. Source codes are available at https://github.com/tsinghua-fib-lab/Traffic-Benchmark .

Multi-level computational screening of anion-pillared metal-organic frameworks for propane and propene separation

Although the search of proper adsorbents for efficient propane/propene (PA/PE) separation has attracted great interest, the actual process-level performance of adsorbents has been rarely considered as a filtering criterion. In this work, a multi-level computational screening of a database containing 936 anion-pillared metal–organic frameworks (AP MOF) is performed to identify promising adsorbents for practical PA/PE separation in pressure/vacuum swing adsorption (PVSA) processes. At the crystal level, the geometry properties are computed. The adsorption isotherms at the phase level are predicted via molecular simulations with the newly calibrated force field parameters. Based on the results from these two levels, 216 candidates are discarded. Then, referring to a rigorous 4-step PVSA model, a simplified batch adsorber model is proposed and used to efficiently identify qualified AP MOF candidates that can meet the separation requirements on PE purity (≥99.5 %) and a certain recovery. The screening indicates that 15 AP MOFs can be used to separate 15 %/85 % PA/PE feed gas with 80 % PE recovery. Only 2 out of them are feasible for the separation of 50 %/50 % feed with 75 % PE recovery. Finally, one of the best candidates is sent for rigorous PVSA process optimization. It shows that the screened adsorbent consumes less energy in the separation of 15 %/85 % PA/PE mixture compared with the benchmark 4A zeolite process. Clearly, this work is anticipated to provide an effective approach for the rapid screening of adsorbents for PA/PE separation in PVSA processes.

Novel Sparse Feature Regression Method for Traffic Forecasting

Traffic forecasting is an integral part of modern intelligent transportation systems. Although many techniques have been proposed in the literature to address the problem, most of them focus almost exclusively on forecasting accuracy and ignore other important aspects of the problem. In the paper at hand, a new method for both accurate and fast large-scale traffic forecasting, named “sparse feature regression”, is presented. Initially, a set of carefully selected features is extracted from the available traffic data. Then, some of the initial features are sparsified, namely they are transformed into sets of sparse features. Finally, a linear regression model is designed using the sparse feature set, which is trained by solving an optimization problem using a sparse approximate pseudoinverse as a preconditioner. We evaluated the proposed method by conducting experiments on two real-world traffic datasets, and the experimental results showed that the method presents the best balance between accuracy of predictions and time required for achieving them, in comparison with a set of benchmark models.

DSTAGCN: Dynamic Spatial-Temporal Adjacent Graph Convolutional Network for Traffic Forecasting

Capturing complex and dynamic spatial-temporal dependencies of traffic data is of great importance for accurate and real-time traffic forecasting in intelligent transportation systems. The spatial-temporal dependency between traffic locations is often dynamic, which means the correlation between the traffic status of different locations changes jointly over their spatial distance and the time slice they are in. Most of the existing Graph Convolutional Network-based methods usually capture spatial and temporal dependencies separately and then combine them in a parallel or serial mechanism to capture the spatial-temporal features. They always utilize the predefined static graph structure to capture both local correlations and global dependencies in the same time slice. These methods are incapable of directly learning dynamic spatial-temporal dependency across time slices. Meanwhile, it is challenging to learn the spatiotemporal correlation knowledge among traffic locations only by using neural networks. To address these issues, we propose a novel Dynamic Spatial-Temporal Adjacent Graph Convolutional Network (DSTAGCN), which connects the latest time slice with each past time slice to construct the spatial-temporal graph. DSTAGCN can directly learn the global spatial dependency across time and simultaneously capture the spatial-temporal dependencies through graph convolution. Since fuzzy theory make it possible to represent uncertain relationships, a simplified fuzzy neural network that integrates fuzzy systems and neural networks is designed to help generating the graph adjacency matrix representing the dynamic adjacency correlations. Experiments on public datasets show that our method outperforms baselines with fast convergence.

Government Digital Communication Management in Facing the Health Crisis (Case Study on the Covid-19 Pandemic in Provincial Government)

This research is motivated by problems with government communication in the Covid-19 pandemic situation that occurred in Indonesia, in a pandemic situation there was an information overload which resulted in unclear information being received by the provincial government from stakeholders so that the government's digital communication management experienced problems. The purpose of this study is to understand and analyze the digital communication management model that has been implemented by the government in handling information during the Covid-19 Pandemic and find the ideal digital communication management model to deal with the pandemic that occurred at the provincial level. The research methodology uses a post-positivist paradigm with a qualitative research type and a case study approach. The theory used in this study is Karl Weick's organizational information theory and is complemented by the four-step communication management model from Cutlip, Center and Broom. The results of the study found that the government had used a digital communication management model during the Covid-19 pandemic, but its implementation needed to be optimized in digital tools, digital communication competencies and also the organizing information system

Persuasive communication and spatial presence: a systematic literature review and conceptual model

ABSTRACT Immersive media forms that can elicit high levels of spatial presence have become popular tools for persuasive communicators. While the research community agrees that immersive persuasive messages should be especially effective, there is less consensus concerning the underlying psychological mechanism. Consequently, it seems necessary to systematize and consolidate the research field. This systematic literature review therefore analyzes 108 empirical articles and identifies four major research strands that focus on (1) affect and emotion, (2) altered perception and storage, (3) depth of processing, and the (4) valence of cognitions. The divergent assumptions are ultimately brought together in a conceptual four-step model of persuasion by spatial presence. Potential inhibitors of persuasion are furthermore discussed and included in the model.

An Improved Model Combining Outlook Attention and Graph Embedding for Traffic Forecasting

Due to the highly non-linear nature of traffic data and the complex structure of road networks, traffic forecasting faces significant challenges. In this paper, we propose an improved model that combines outlook attention and graph embedding (MOAGE) for traffic forecasting, focusing on the construction of reasonable and effective spatio-temporal dependencies. Inspired by the idea of symmetry, MOAGE adopts a symmetrical encoder and decoder structure. Outlook attention blocks are important components of the encoder and decoder, consisting of spatial outlook attention and temporal outlook attention, used to model spatio-temporal dependencies in the road network. Cross attention are added to the model to reduce propagation errors. In addition, we learned the vertex representation of the graph via the node2vec algorithm and integrated the graph information into our model for a better prediction performance. Extensive experiments on two real datasets further demonstrate that the RMSE errors of the MOAGE on PEMS_BAY and METR_LA are reduced by approximately 14.6% and 12.2% for 60 min compared with the latest baseline models. Finally, the methodology used in this study will provide guidance to relevant ministries to better allocate transport resources and improve the efficiency and safety of traffic operations.

Інтелектуалізація управління дорожнім рухом як засіб підвищення ефективності транспортної мережі міста в неординарних ситуаціях

An assessment of modern trends in the development of intelligent traffic management systems and their role in ensuring the efficiency of the functioning of transport networks was carried out. The processes of introducing technologies for expanding the flow of processed data into existing intelligent transport systems (ITS) that ensure an increase in the speed of information transmission in them have been determined. The classification of information sources that become available when the ITS transitions to the 5G standard and provide a basis for the implementation of technologies for avoiding extraordinary situations in transport networks is given.Existing methods of improving the efficiency of the city's transport network are mainly aimed at ensuring the ability of ITS to predict traffic flows. These include statistical and nonlinear methods, simulation-based methods, artificial intelligence methods, and combined methods. The implementation of these methods is achieved by increasing the information flow coming from the system. A comparison of these methods revealed that they can generally make predictions with high accuracy, however, regardless of the chosen standard, some of them are already at the peak of their potential in terms of application in ITS, and the rest still have room for development.The suitability of the forecasting method for working in real-time conditions is a significant advantage in ensuring effective management of traffic flows, allows to increase the stability of the transport network and the efficiency of the ITS, and has a positive effect on the level of traffic jams, road safety and ecological impact on the environment. The most promising in terms of a quick and flexible solution to an extraordinary situation are models with the use of artificial intelligence or a combination thereof, based on deep learning algorithms, which have proven their importance in predicting the results, making decisions regarding traffic flow forecasts and ensuring the elimination and avoidance of traffic jams based on the passage of vehicles through the intersection depending on the length and duration of the traffic light signals.

Adaptive Spatiotemporal Transformer Graph Network for Traffic Flow Forecasting by IoT Loop Detectors

Extensive traffic flow data are received from the loop detector networks every second, which requires us to develop an effective and efficient algorithm to predict future traffic flow. However, dynamic traffic conditions on a road are not just influenced by sequential patterns in the temporal dimension, but also by other roadways in the spatial dimension. Although many successful models have been developed in previous studies to forecast future traffic flows, most of them have shortcomings in modeling spatial and temporal dependencies. In this article, we focus on spatial-temporal factors and propose a new adaptive spatial-temporal transformer graph network (ASTTGN) to improve the accuracy of traffic forecasting by jointly modeling the spatial-temporal information of road networks. Specifically, we propose an adaptive spatial-temporal transformer module, which contains two developed adaptive transformer modules for capturing dynamic spatial dependence and temporal dependence across multiple time steps, respectively. Finally, feature fusion is performed through a gated feature aggregation layer to simulate the effect of complex spatial-temporal factors on traffic conditions. In particular, the multihead attention mechanism employed by the transformer can effectively explore the potential spatial-temporal dependence patterns in different subspaces. Experimental results on two real-world traffic data sets demonstrate the superiority of the proposed model compared to existing techniques.

Formula omitted]-LSTM: An error distribution free deep learning for short-term traffic flow forecasting

Timely and accurate traffic flow forecasting is open challenging. Canonical long short-term memory (LSTM) network is considered qualified to capture the long-term temporal dependencies in traffic flow. However, the training of LSTM networks is often guided by the mean square error (MSE) criterion. Such criterion depends on a strong assumption that the errors between the traffic flow and its predictions are Gaussian independent identically distributed. In this regard, the forecasting performance is seriously deteriorated by non-Gaussian noises inside the traffic flow sequences. To address this issue, we relax the assumption of the prediction errors to arbitrary distribution by a negative guided mixed correntropy criterion. Then, we formulate a robust loss function by the negative guided mixed correntropy criterion. We subsequently equip the loss function in an LSTM network, termed Δfree-LSTM, for short-term traffic flow forecasting. Extensive experiments on four benchmark datasets demonstrate that the Δfree-LSTM network outperforms the traditional parametric and nonparametric models, as well as state-of-the-art LSTM family models. The source code is available athttps://github.com/541764418/Delta-free-LSTM.

EXPLANATORY ANALYSES OF WORK TRIP GENERATION USING MIXED GEOGRAPHICALLY WEIGHTED REGRESSION (MGWR)

Abstract. In transportation planning, forecasts have commonly followed the sequential four-step model in which, trip generation (production and attraction) plays a critical role. Among the methods applied to model trip generation, regression with Gaussian distribution of errors are recognized as the most prevailing techniques to describe the relationships between production/attraction and explanatory variables by estimating the global, fixed coefficients. Considering that, trip generation is almost impressed by spatial factors which vary over the study area; the main objective of this research is to apply Mixed Geographically Weighted Regression (MGWR) on 253 traffic analysis zones (TAZs) in Mashhad, Iran, by applying travel demand data and relating factors in 2018 to investigate the spatial non-stationarity which are not revealed when global specifications are applied. The influence of certain explanatory variables on response variables may be global, whereas others are local, accordingly, MGWR performs better compared with geographically weighted regression. The results of Moran’s I as spatial autocorrelation index performing on residuals of global, mixed models proved the reliability of the proposed model over the traditional one. The spatial model indicated an improvement in model performance using goodness-of-fit criteria with the coefficient of determination varying from 0.84–0.95 compared with 0.76 and 0.6 in the conventional model. The results of such analysis can provide descriptive and predictive tools at the planning-level for decision-makers.

Spatial‐temporal correlation graph convolutional networks for traffic forecasting

AbstractTraffic forecasting, as a fundamental and challenging problem of intelligent transportation systems (ITS), has always been the focus of researchers. Nevertheless, accurate traffic forecasting still exists some problems due to the complex spatial‐temporal dependencies and irregularities of traffic flows. Most of the existing methods typically use the spatial adjacency matrix and complicated mechanism to model spatial‐temporal relationships separately, while ignoring the latent spatial‐temporal correlations. In this paper, a novel architecture is proposed named spatial‐temporal correlation graph convolutional networks (STCGCN) for traffic prediction. First, an informative fused graph structure is constructed to better learn the complex spatial‐temporal correlations, which breaks the limitation that the general spatial adjacency matrix cannot reflect temporal correlations. Moreover, spatial‐temporal correlation graph convolution and gated temporal convolution are performed in parallel and they are integrated into a unified layer, which enables capturing both local and global spatial‐temporal dependencies simultaneously. By stacking multiple layers, STCGCN can learn more long‐range spatial‐temporal dependencies. Experimental results on five public traffic datasets demonstrate the effectiveness and robustness of the proposed STCGCN in urban traffic forecasting.

Autonomous Forecasting of Traffic in Cellular Networks Based on Long-Short Term Memory Recurrent Neural Network

Forecasting of traffic in cellular network is a significant service for management of available resources strategically in an efficient way. Valuable resources such as link bandwidth and energy are increasing exponentially with increase in usage of cellular data. In this paper, we implement the design of Neural Network for identification of recurrent patterns in different metrics that can be then applied in forecasting of traffic in cellular networks. As this Neural Network design is based on memory and custom architecture, it is able to handle task of prediction in a precise and faster mode in real-time applications such as cellular network traffic forecasting. This work involves a Long Short Term Memory design of Recurrent Neural Network for traffic forecasting in cellular networks. It enhances the performance of the cellular network thereby providing a solution for the service providers as the available resources are utilized in an effective way. Same data set is involved for multiple prediction to analyze the performance of the design and found to be robust than the existing algorithms.

The effect of hydrogen addition on methane/air explosion characteristics in a 20-L spherical device

The addition of hydrogen to methane changes its deflagration characteristics and increases the combustion rate. However, studies on the effect of hydrogen on methane deflagration remain insufficient. Therefore, based on the CFD code GASFLOW-MPI, a four-step combustion-mechanism model was established for methane/hydrogen mixtures. The deflagration characteristics of a premixed combustible gas in a 20-L spherical device was numerically simulated using a methane/hydrogen/air equivalence ratio of 1 and hydrogen addition in the range of 0–50%; subsequently. The results were compared with experimental data. The four-step methane/hydrogen combustion-mechanism could effectively reproduce the methane/hydrogen deflagration process on considering the heat losses. With an increase in hydrogen addition, the laminar burning velocity increases, and the deflagration duration reduces. It decreases the explosion heat loss and increased the maximum deflagration pressure. Under adiabatic simulation, the maximum deflagration pressure decreased with an increase in hydrogen addition, in contrast with the experimental results. This indicates that the heat-loss effect of the methane/hydrogen/air-mixture deflagration process should not be ignored. Moreover, the heat loss during the methane/hydrogen/air-mixture deflagration was mainly caused by thermal radiation. Thus, the influence of the thermal-radiation and convective heat-transfer mechanisms should be considered in the numerical simulations of methane/hydrogen/air-mixture deflagration.

Development of a Platform Business Model for Co-creation Ecosystems for Sustainable Furniture

Existing design platforms with multi-dimensional value chains currently have deficits in terms of their business models, resulting in insufficient attention to sustainability goals and individual requirements for products of these platforms. Co-creation approaches, such as the Do-It-Together (DIT) approach for furniture, involve customers and manufacturers as equal partners in the design and production process. This allows customers to have more influence on the sustainability and individualization of products. The existing literature addresses sustainability-oriented design principles for platform business models, but concrete platform business models for multidimensional DIT co-creation of furniture are still missing. Therefore, the objective of this paper is to develop a business model for a DIT co-creation platform for the furniture industry based on a four-step business model innovation framework. This method will then be applied to a specific project scenario to derive a project-specific DIT co-creation business model. This generates knowledge about the collaborative manufacture of sustainable and customized furniture and contributes to the cross-sectoral transfer of platform business models for the development of sustainable products.JEL Codes: L23, O31

Spatial–temporal dependence and similarity aware traffic flow forecasting

Traffic flow forecasting is the cornerstone of the development of intelligent transportation systems. Accurate forecasting is conducive to the control and management of urban traffic. However, it is still a challenge to extract the complex spatial–temporal relationships in the traffic flow. The existing methods based on Graph Convolutional Network (GCN) can effectively extract spatial–temporal dependence, but it is difficult to extract spatial–temporal similarity because of the limitation of the graph structure. In this paper, we propose a spatial–temporal dependence and similarity-aware method called Dependence and Similarity aware Temporal Graph Convolutional Network (DS-TGCN), which combines two modules to extract the complex spatial–temporal relationships and make traffic flow forecasting. One module is our Spatial–Temporal Similarity Feature module (STSF) newly designed for extracting the spatial–temporal similarity directly. Another module is the spatial–temporal convolution module with an attention mechanism, which can extract spatial–temporal dependence dynamically. The experiments on two types of datasets demonstrate that our proposed method outperforms the existing methods in terms of the effectiveness of traffic flow forecasting.

Adaptive dependency learning graph neural networks

Graph Neural Networks (GNN) have recently gained popularity in the forecasting domain due to their ability to model complex spatial and temporal patterns in tasks such as traffic forecasting and region-based demand forecasting. Most of these methods require a predefined graph as input, whereas in real-life multivariate time series problems, a well-predefined dependency graph rarely exists. This requirement makes it harder for GNNs to be utilised widely for multivariate forecasting problems in other domains such as retail or energy. In this paper, we propose a hybrid approach combining neural networks and statistical structure learning models to self-learn the dependencies and construct a dynamically changing dependency graph from multivariate data aiming to enable the use of GNNs for multivariate forecasting even when a well-defined graph does not exist. The statistical structure modeling in conjunction with neural networks provides a well-principled and efficient approach by bringing in causal semantics to determine dependencies among the series. Finally, we demonstrate significantly improved performance using our proposed approach on real-world benchmark datasets without a pre-defined dependency graph.

Long Short-Term Fusion Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting

Traffic flow forecasting, as one of the important components of intelligent transport systems (ITS), plays an indispensable role in a wide range of applications such as traffic management and city planning. However, complex spatial dependencies and dynamic changes in temporal patterns exist between different routes, and obtaining as many spatial-temporal features and dependencies as possible from node data has been a challenging task in traffic flow prediction. Current approaches typically use independent modules to treat temporal and spatial correlations separately without synchronously capturing such spatial-temporal correlations, or focus only on local spatial-temporal dependencies, thereby ignoring the implied long-term spatial-temporal periodicity. With this in mind, this paper proposes a long-term spatial-temporal graph convolutional fusion network (LSTFGCN) for traffic flow prediction modeling. First, we designed a synchronous spatial-temporal feature capture module, which can fruitfully extract the complex local spatial-temporal dependence of nodes. Second, we designed an ordinary differential equation graph convolution (ODEGCN) to capture more long-term spatial-temporal dependence using the spatial-temporal graph convolution of ordinary differential equation. At the same time, by integrating in parallel the ODEGCN, the spatial-temporal graph convolution attention module (GCAM), and the gated convolution module, we can effectively make the model learn more long short-term spatial-temporal dependencies in the processing of spatial-temporal sequences.Our experimental results on multiple public traffic datasets show that our method consistently obtained the optimal performance compared to the other baselines.

Deep Learning Based Fusion Model for Multivariate LTE Traffic Forecasting and Optimized Radio Parameter Estimation

With the evaluation of cellular network internet data traffic, forecasting and understanding traffic patterns become the critical objectives for managing the network-designed Quality of Service (QoS) benchmark. For this purpose, cellular network planners often use different methodologies for predicting data traffic. However, traditional traffic forecasting approaches are erroneous. As well as most of the time, traditional traffic forecasts are high-level or a generously large regional cluster level. Also, eNodeB-level utilization concerning with traffic forecasting is not readily available. As a result, user experience degradation or unnecessary network expansion is triggered based on the traditional method. This research focuses on extensive 6.2 million real network time series Long-Term Evolution (LTE) data traffic and other associate parameters, including eNodeB-wise Physical Resource Block (PRB) utilization, which mainly focuses on building a traffic forecasting model with the help of multivariate feature inputs and deep learning algorithms. A state-of-the-art Deep Learning algorithm-based fusion model is proposed. The combination of different deep learning algorithms, namely Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM) and Gated Recurrent Unit (GRU), enables traffic forecasting at a granular eNodeB-level and also provides eNodeB-wise forecasted PRB utilization. In this research <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula> score value for the proposed fusion model is 0.8034, which outperforms traditional models. Apart from the PRB utilization, QoS threshold was devised as 70% from a real network experience to trigger soft parameter tuning decisions. Based on the forecasted PRB utilization, this research proposed a unique algorithm that estimates eNodeB-level soft capacity parameter optimization for a short-term step-up solution or long-term network expansion to ensure a guaranteed QoS benchmark.

Traffic Forecasting via Dilated Temporal Convolution With Peak-Sensitive Loss

Deep learning-based traffic forecasting methods can capture intricate spatiotemporal features in traffic data and environmental factors. However, they have unsatisfactory performance around the minority peaks and are inefficient for modeling wide-range spatial correlations. This article gives a peak-aware deep learning architecture for traffic forecasting by involving a cost-sensitive loss function called peak-sensitive loss. This method can improve the performance since different costs are employed on the prevalent metrics such as mean-square loss and square of mean absolute percentage loss. A spatiotemporal convolutional architecture based on a dilated convolutional network (DCN) and a temporal convolutional network (TCN) is constructed that models the spatial features (both wide and short range) by the DCN and learns the time characteristics by the TCN. The effectiveness of the model is demonstrated with real-world data sets.