Traffic Forecasting Research Articles

Dynamic temporal position observant graph neural network for traffic forecasting

Dynamic temporal position observant graph neural network for traffic forecasting

Spatial-temporal hypergraph convolutional network for traffic forecasting.

Accurate traffic forecasting plays a critical role in the construction of intelligent transportation systems. However, due to the across road-network isomorphism in the spatial dimension and the periodic drift in the temporal dimension, existing traffic forecasting methods cannot satisfy the intricate spatial-temporal characteristics well. In this article, a spatial-temporal hypergraph convolutional network for traffic forecasting (ST-HCN) is proposed to tackle the problems mentioned above. Specifically, the proposed framework applies the K-means clustering algorithm and the connection characteristics of the physical road network itself to unify the local correlation and across road-network isomorphism. Then, a dual-channel hypergraph convolution to capture high-order spatial relationships in traffic data is established. Furthermore, the proposed framework utilizes a long short-term memory network with a convolution module (ConvLSTM) to deal with the periodic drift problem. Finally, the experiments in the real world demonstrate that the proposed framework outperforms the state-of-the-art baselines.

Spatiotemporal Residual Graph Attention Network for Traffic Flow Forecasting

Accurate spatio-temporal traffic flow forecasting is significant for the modern traffic management and control. In order to capture the spatio-temporal characteristics of the traffic flow simultaneously, we propose a novel spatio-temporal residual graph attention network (STRGAT). First, the network adopts a deep full residual graph attention block, which performs a dynamic aggregation of spatial features regarding the node information of the traffic network. Second, a sequence-to-sequence block is designed to capture the temporal dependence in the traffic flow. The traffic flow data with weekly periodic dependencies are also integrated and STRGAT is used for traffic forecasting of traffic road networks. The experiments are conducted on three real datasets in California, USA. Results verify that our proposed STRGAT is able to learn the spatio-temporal correlation of traffic flow well and outperforms the state-of-the-art methods.

A connectivity-based methodology for new air route identification

The change of routes at an airport has a huge impact on airlines’ revenue and city economy where the airport is located. Planning a successful route is a complicated decision-making process that involves considerations beyond the origin and destination. Past studies rarely consider how the addition of new routes or revision of existing routes affects the global aviation network and consequently impacts direct and transfer demands. A new data analytic approach is proposed to identify new and long-lasting routes and to assess connection quality from the global network perspective. It includes a comprehensive methodology for analysing the aviation network, evaluating potential route quality, deciding which routes warrant the selection, and estimating the long-and-short term traffic volume forecasts of the selected new routes. Seven attributes have been developed for route selection, covering growth, volume and connectivity-potential. Assessing connectivity potential permits the evaluation of the importance of a potential destination airport by considering the changes in competitive position that other airports connected to the same destination can expect when that new route is added to the network. This approach exploits the geographical relationships between airports and combines the network route supply data over a 9-year period to make assessment decisions on new destinations. A list of promising new destinations is created that can enhance the origin airport’s connectivity-potential and improve the competitive advantage of airports. Managerial implications are also proposed for different aviation stakeholders to facilitate their strategic planning on airport facility and capacity expansion, airline competition, multi-airport region collaboration and air service agreements.

Adaptive Graph Fusion Convolutional Recurrent Network for Traffic Forecasting

Traffic flow prediction is the foundation of urban traffic guidance and control, as well as the main function of an intelligent transportation system (ITS). Accurate traffic flow prediction is important for road users, traffic management departments and private enterprises. However, traffic flows usually show a high degree of variability, correlation and complex patterns in both temporal and spatial domain, which makes accurate traffic flow prediction a challenging task. How to capture the potential and dynamic spatial-temporal relationships of traffic data has been the bottleneck issue for intelligent transportation researchers. To solve the above problems, this paper proposes an Adaptive Graph Fusion Convolutional Recurrent Network (AGFCRN) to model the temporal and spatial characteristics of traffic flow data dynamically and adaptively. An adaptive graph fusion convolution is proposed to discover the changing relationships between traffic volumes without a priori knowledge. It uses a self-learned node embedding to generate static graphs and combines current and historical states to generate dynamic graphs at each time step. A gated recurrent layer with residual structure is designed to mitigate the decay of prediction effects in long-term modeling. In addition, an attention layer incorporating self-learned node embedding is introduced in the AGFCRN to efficiently adjust the prediction pattern of each node. Experiments on several public datasets demonstrate that AGFCRN can achieve competitive performance compared to other typical and state-of-the-art methods.

TRAFFIC FLOW PREDICTION BASED ON VANET DATA BY COMBINING ARTIFICIAL NEURAL NETWORK AND GENETIC ALGORITHM

In many developing countries, predicting traffic flow is one of the solutions to prevent congestion on highways and routes, and the intelligent transportation system is considered one of the solutions to problems related to transportation and traffic. Knowledge of the predicted situation for traffic flow is essential in traffic management and informing passengers. This research presents a short-term intelligent transportation traffic flow forecasting model, which first examines how traffic forecasting can improve the performance of intelligent transportation system applications. Then the method and basic concepts of traffic flow forecasting are introduced, and the two main categories of forecasting, statistical models and machine learning-based forecasting methods (supervised and unsupervised) are discussed. Finally, a method based on machine learning using a genetic algorithm is Presented. The prediction was used as a powerful method for the mathematical modeling of traffic data in the proposed genetic algorithm method to select important traffic data features and neural networks for classification. The simulation and results presented in this research show a 3 percent improvement in traffic flow prediction with the proposed method, which uses SVM as a classifier in the primary method, and the simulation of this method has output a value of 93.6, But the suggested method has an output of 96.6

Role of excited states in helium-like ions on high-order harmonic generation

We theoretically investigate high-order harmonic generation (HHG) of helium (He), lithium cation (Li+), and beryllium dication (Be2+) using the time-dependent Hartree–Fock method to solve the three-dimensional time-dependent Schrödinger equation. It is found that the intensity of the HHG increases significantly from a certain harmonic order below the ionization threshold, and the initial position of the enhancement does not depend on the intensity or the wavelength of the driving laser field. Further analysis shows that excited states play an important role on this enhancement, consistent with the excited-state tunneling mechanism [Phys. Rev. Lett. 116 123901 (2016)]. Our results unambiguously show that excited-state tunneling is essential for understanding the enhancement of HHG. Accordingly, a four-step model is herein proposed to illustrate the multiphoton excitation effect in helium-like ions, which enriches the physics of HHG enhancement.

Multi-spatio-temporal Fusion Graph Recurrent Network for Traffic Forecasting

Accurate traffic forecasting is crucial for smart city development in the new era. However, the intricate spatial and temporal dependencies in traffic data present significant challenges for prediction accuracy. Existing methods often rely on predefined adjacency matrices to capture Spatio-temporal dependencies, which may not adapt well to the dynamic nature of road traffic. To address these challenges, we propose the Multi-Spatio-temporal Fusion Graph Recurrent Network (MSTFGRN). This innovative approach introduces a data-driven method for generating a weighted adjacency matrix, effectively capturing real-time spatial dependencies that are not adequately captured by predefined matrices. The MSTFGRN also incorporates a novel two-way Spatio-temporal fusion operation to learn hidden dependencies between parallel Spatio-temporal relations at different time points. Additionally, a global attention mechanism is integrated into the Spatio-temporal fusion module, enabling the simultaneous capture of global Spatio-temporal dependencies. Through extensive trials on publicly available highway traffic datasets, our method demonstrates state-of-the-art performance compared to alternative baselines.

The Power of Data: How Traffic Demand and Data Analytics Are Driving Network Evolution toward 6G Systems

The evolution of communication systems always follows data traffic evolution and further influences innovations that are unlocking new markets and services. While 5G deployment is still ongoing in various countries, data-driven considerations (extracted from forecasts at the macroscopic level, detailed analysis of live network traffic patterns, and specific measures from terminals) can conveniently feed insights suitable for many purposes (B2B e.g., operator planning and network management; plus also B2C e.g., smarter applications and AI-aided services) in the view of future 6G systems. Moreover, technology trends from standards and research projects (such as Hexa-X) are moving with industry efforts on this evolution. This paper shows the importance of data-driven insights, by first exploring network evolution across the years from a data point of view, and then by using global traffic forecasts complemented by data traffic extractions from a live 5G operator network (statistical network counters and measures from terminals) to draw some considerations on the possible evolution toward 6G. It finally presents a concrete case study showing how data collected from the live network can be exploited to help the design of AI operations and feed QoS predictions.

Spatial–Temporal Dynamic Graph Differential Equation Network for Traffic Flow Forecasting

Traffic flow forecasting is the foundation of intelligent transportation systems. Accurate traffic forecasting is crucial for intelligent traffic management and urban development. However, achieving highly accurate traffic flow prediction is challenging due to road networks’ complex dynamic spatial and temporal dependencies. Previous work using predefined static adjacency matrices in graph convolutional networks needs to be revised to reflect the dynamic spatial dependencies in the traffic system. In addition, most current methods ignore the hidden dynamic spatial–temporal correlations between road network nodes as they evolve. We propose a spatial–temporal dynamic graph differential equation network (ST-DGDE) for traffic prediction to address the above problems. First, the model captures the dynamic changes between spatial nodes over time through a dynamic graph learning network. Then, dynamic graph differential equations (DGDE) are used to learn the spatial–temporal dynamic relationships in the global space that change continuously over time. Finally, static adjacency matrices are constructed by static node embedding. The generated dynamic and predefined static graphs are fused and input into a gated temporal causal convolutional network to jointly capture the fixed long-term spatial association patterns and achieve a global receiver domain that facilitates long-term prediction. Experiments of our model on two natural traffic flow datasets show that ST-DGDE outperforms other baselines.

Easy Begun Is Half Done: Spatial-Temporal Graph Modeling with ST-Curriculum Dropout

Spatial-temporal (ST) graph modeling, such as traffic speed forecasting and taxi demand prediction, is an important task in deep learning area. However, for the nodes in the graph, their ST patterns can vary greatly in difficulties for modeling, owning to the heterogeneous nature of ST data. We argue that unveiling the nodes to the model in a meaningful order, from easy to complex, can provide performance improvements over traditional training procedure. The idea has its root in Curriculum Learning, which suggests in the early stage of training models can be sensitive to noise and difficult samples. In this paper, we propose ST-Curriculum Dropout, a novel and easy-to-implement strategy for spatial-temporal graph modeling. Specifically, we evaluate the learning difficulty of each node in high-level feature space and drop those difficult ones out to ensure the model only needs to handle fundamental ST relations at the beginning, before gradually moving to hard ones. Our strategy can be applied to any canonical deep learning architecture without extra trainable parameters, and extensive experiments on a wide range of datasets are conducted to illustrate that, by controlling the difficulty level of ST relations as the training progresses, the model is able to capture better representation of the data and thus yields better generalization.

The profit-oriented hub line location problem with elastic demand

This paper deals with an extension of the hub line location problem considering demand elasticity with respect to travel times. The proposed model aims to capture the impact the hub network topology has on demand. The objective is to maximize the total revenue generated by each unit of demand using the hub line. We propose mixed-integer nonlinear formulations to model this problem. We study some properties of the nonlinear objective function associated with these formulations. Due to the inherent complexity involved in solving these nonlinear formulations with state-of-the-art solvers, we also present alternative mixed-integer linear programming formulations. Computational results compare the proposed formulations and the benefits of the presented model using benchmark instances commonly used in hub location. Moreover, a sensitivity analysis study is carried out with real data from the city of Montreal, Canada, to demonstrate the added value of incorporating demand elasticity when using the proposed model for public transportation planning.

Sustainable Traffic Management for Smart Cities Using Internet-of-Things-Oriented Intelligent Transportation Systems (ITS): Challenges and Recommendations

The emergence of smart cities has addressed many critical challenges associated with conventional urbanization worldwide. However, sustainable traffic management in smart cities has received less attention from researchers due to its complex and heterogeneous nature, which directly affects smart cities’ transportation systems. The study aimed at addressing traffic-related issues in smart cities by focusing on establishing a sustainable framework based on the Internet of Things (IoT) and Intelligent Transportation System (ITS) applications. To sustain the management of traffic in smart cities, which is composed of a hybridized stream of human-driven vehicles (HDV) and connected automated vehicles (CAV), a dual approach was employed by considering traffic as either modeling- and analysis-based, or/and the decision-making issues of previous research works. Moreover, the two techniques utilized real-time traffic data, and collected vehicle and road users’ information using AI sensors and ITS-based devices. These data can be processed and transmitted using machine learning algorithms and cloud computing for traffic management, traffic decision-making policies, and documentation for future use. The proposed framework suggests that deploying such systems in smart cities’ transportation could play a significant role in predicting traffic outcomes, traffic forecasting, traffic decongestion, minimizing road users’ lost hours, suggesting alternative routes, and simplifying urban transportation activities for urban dwellers. Also, the proposed integrated framework adopted can address issues related to pollution in smart cities by promoting public transportation and advocating low-carbon emission zones. By implementing these solutions, smart cities can achieve sustainable traffic management and reduce their carbon footprint, making them livable and environmentally friendly.

Graph convolutional dynamic recurrent network with attention for traffic forecasting

Graph convolutional dynamic recurrent network with attention for traffic forecasting

PMGCN: Progressive Multi-Graph Convolutional Network for Traffic Forecasting

Traffic forecasting has always been an important part of intelligent transportation systems. At present, spatiotemporal graph neural networks are widely used to capture spatiotemporal dependencies. However, most spatiotemporal graph neural networks use a single predefined matrix or a single self-generated matrix. It is difficult to obtain deeper spatial information by only relying on a single adjacency matrix. In this paper, we present a progressive multi-graph convolutional network (PMGCN), which includes spatiotemporal attention, multi-graph convolution, and multi-scale convolution modules. Specifically, we use a new spatiotemporal attention multi-graph convolution that can extract extensive and comprehensive dynamic spatial dependence between nodes, in which multiple graph convolutions adopt progressive connections and spatiotemporal attention dynamically adjusts each item of the Chebyshev polynomial in graph convolutions. In addition, multi-scale time convolution was added to obtain an extensive and comprehensive dynamic time dependence from multiple receptive field features. We used real datasets to predict traffic speed and traffic flow, and the results were compared with a variety of typical prediction models. PMGCN has the smallest Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) results under different horizons (H = 15 min, 30 min, 60 min), which shows the superiority of the proposed model.

Kinetic model-based group contribution method for derived cetane number prediction of oxygenated fuel components and blends

A four-step autoignition model was used to derive an expression for the ignition delay (ID) measured in ignition quality testers (IQT) with the derived cetane number (DCN) determined from this ID using the ASTM D6890 standard correlation. The model predicts DCN for individual compounds and blends as a function of each compound's global initiation and net chain branching rate constants. Expressions for these values were determined assuming they could be related to the functional groups present in each compound. Measurement data for 125 compounds and 94 binary and ternary blends (including oxygenates: alcohols, aldehydes, esters, ethers, and ketones), from literature and from measurements performed in our lab, were used to obtain the dependence of the measured ignition delay on each functional group. The new kinetic model-based group contribution method was able to predict the ignition delay of both pure compounds and blends, with an average DCN error of 4.4 (19%) and 2.8 (11%), respectively. The blend model was also used to develop an ID mixing rule by incorporating existing IQT ignition delay data for each compound. Use of the mixing rule gave an average DCN error of 3.6 (16%) for blends. Both the blend model and mixing rule were found to be superior compared to standard linear by volume fraction or mole fraction mixing rules commonly used to estimate the DCN of mixtures.

A Long-Term Traffic Flow Prediction Model Based on Variational Mode Decomposition and Auto-Correlation Mechanism

Traffic flow forecasting, as an integral part of intelligent transportation systems, plays a critical part in traffic planning. Previous studies have primarily focused on short-term traffic flow prediction, paying insufficient attention to long-term prediction. In this study, we propose a hybrid model that utilizes variational mode decomposition (VMD) and the auto-correlation mechanism for long-term prediction. In view of the periodic and stochastic characteristics of traffic flow, VMD is able to decompose the data into intrinsic mode functions with different frequencies, which in turn helps the model extract the internal features of the data and better capture the changes of traffic flow data in the cycle. Additionally, we improve the residual structure by adding a convolutional layer to propose a correction module and use it together with the auto-correlation mechanism to jointly build an encoder and decoder to extract features from different data components (intrinsic mode functions) and fuse the extracted features for output. To meet the requirements of long-term forecasting, we set the traffic flow forecast length to 4 levels: 96, 192, 336, and 720. We validated our model using the departure statistics dataset of a taxi parking lot at Beijing Capital International Airport and achieved the best prediction performance in terms of mean squared error and mean absolute error, compared to the baseline model.

Attention-Based Spatial-Temporal Convolution Gated Recurrent Unit for Traffic Flow Forecasting.

Accurate traffic flow forecasting is very important for urban planning and traffic management. However, this is a huge challenge due to the complex spatial-temporal relationships. Although the existing methods have researched spatial-temporal relationships, they neglect the long periodic aspects of traffic flow data, and thus cannot attain a satisfactory result. In this paper, we propose a novel model Attention-Based Spatial-Temporal Convolution Gated Recurrent Unit (ASTCG) to solve the traffic flow forecasting problem. ASTCG has two core components: the multi-input module and the STA-ConvGru module. Based on the cyclical nature of traffic flow data, the data input to the multi-input module are divided into three parts, near-neighbor data, daily-periodic data, and weekly-periodic data, thus enabling the model to better capture the time dependence. The STA-ConvGru module, formed by CNN, GRU, and attention mechanism, can capture both temporal and spatial dependencies of traffic flow. We evaluate our proposed model using real-world datasets and experiments show that the ASTCG model outperforms the state-of-the-art model.

GSTC-Unet: A U-shaped multi-scaled spatiotemporal graph convolutional network with channel self-attention mechanism for traffic flow forecasting

Accurate forecasting of traffic flows remains a significant challenge owing to its complex spatiotemporal dependencies. Although existing methods capture some spatiotemporal dependencies and stack them in a channel dimension, long-range sequences, implicit patterns, hidden fine-grained features and multi-scaled spatiotemporal dependencies are often ignored, which makes it difficult to represent the spatiotemporal dependencies comprehensively. To overcome these limitations, a novel deep learning model named Graph Spatiotemporal Channel Unet (U-shaped network) is proposed to achieve accurate and reliable traffic flow forecasting. First, a new temporal encoder-decoder module with causal convolution and transposed convolution is proposed, which can efficiently alleviate the gradient explosion/vanishing in capturing long-range sequences during encoding and decoding. Secondly, a new channel self-attention mechanism is proposed, which can efficiently capture the implicit patterns and hidden fine-grained features between channels and enhance the representation ability of the spatiotemporal dependencies. Thirdly, a new U-shaped multi-scaled spatiotemporal graph convolutional network is proposed to effectively capture the multi-scaled spatiotemporal dependencies. Experiments on two real-world datasets show that the proposed model outperforms baseline models and achieves accurate traffic flow forecasting.

Deep Learning on Traffic Prediction Methods Analysis and Future Directions

Accurate traffic forecasting is essential for intelligent transportation frameworks. Course arranging, vehicle dispatch, and facilitating gridlock may all profit from precise traffic anticipating. This challenge is difficult due to the complex and dynamic spatiotemporal relationships that exist between various segments of the road network. This topic has recently received a lot of research attention, particularly the deep learning method, which has significantly improved traffic forecasting abilities. This work expects to introduce a far reaching assessment of traffic prediction strategies in view of deep gaining according to different points of view. To get things started, we'll summarize and classify the current methods for traffic forecasting. Second, we discuss the most recent approaches utilized in various applications for traffic prediction. Thirdly, to help different specialists, we gather and organize generally utilized public datasets from the ongoing writing. In addition, we conduct extensive investigations to evaluate the display of various methodologies on a genuine public dataset in order to provide an evaluation and examination. In conclusion, we examine irritating issues in this area.