Traffic Forecasting Research Articles

Multi-Slice Privacy-Aware Traffic Forecasting at RAN Level: A Scalable Federated-Learning Approach

Next-generation mobile networks are expected to meet the requirements of a wide range of new vertical services. Hence, the network slicing concept has been introduced, in which Mobile Virtual Network Operators (MVNOs) are allowed to provide various types of services over the same physical infrastructure, owned by an Infrastructure Provider (InP). To cope with an ever-changing traffic demand, MVNOs seek to pre-allocate/reconfigure the resources at the base stations in an anticipatory manner, based on traffic demand predictions. Ideally, conducting per-slice traffic forecasting requires information that is likely to disclose MVNO confidential information (i.e., business strategy or private user data). To secure data ownership while conducting traffic forecasting, we propose the Federated Proximal Long Short-Term Memory (FPLSTM) framework, which allows MVNOs to train their local models with their private dataset at each base station; subsequently, an associated InP global model can be updated through the aggregation of the local models. The results obtained by training the models on a real-world dataset indicate that the forecasting performance of our proposed approach is as accurate as state-of-the-art centralized solutions, while improving data privacy. To enable scalability, we further propose the Information-based Clustering FPLSTM (IC-FPLSTM) and Random Clustering FPLSTM (RC-FPLSTM) frameworks, dealing with large-scale cellular networks. These solutions demonstrate computation and communication cost efficiency significantly above the state-of-the-art.

Traffic Flow Forecast using Time Series Analysis based on Machine Learning Algorithm

Time series forecasting plays a critical role in predicting future trends and making informed decisions across various domains. In this research paper, we present a multi-model approach to improve the accuracy and robustness of time series forecasting. Our methodology involves integrating two powerful models, Long Short-Term Memory (LSTM) and Seasonal Autoregressive Integrated Moving Average (SARIMA), to capture complex temporal patterns and seasonality in the data. We leverage real-world traffic data from different junctions and employ a comprehensive pipeline for data preprocessing, including data selection, resampling, and sequence generation. Our study focuses on four junctions, and for each junction, we individually train LSTM models, followed by SARIMA models for comparison. The LSTM models are designed to capture long-term dependencies in the time series data, while the SARIMA models are tailored to handle seasonality and autocorrelation. We implement a custom sequence generation process and split the dataset into training and testing sets for model evaluation. The LSTM models are trained using Pytorch, optimizing them for accurate short-term predictions. Our results show that the combination of LSTM and SARIMA models yields superior forecasting performance compared to using each model individually. We present a detailed analysis of the forecasted results, including Root Mean Square Error (RMSE) calculations and visualizations to demonstrate the effectiveness of our multi-model approach. This research contributes to the field of time series forecasting by showcasing the benefits of combining deep learning and classical statistical methods. The proposed approach provides a flexible and robust framework applicable to various time series prediction tasks, offering improved accuracy and reliability in forecasting future trends.

Spatial matrices for short-term traffic forecasting based on time series

Spatial matrices for short-term traffic forecasting based on time series

Trip Distribution and Modal Choice in the Taman Mini LRT Station Area

The surrounding Taman Mini LRT station boasts a diverse range of land uses, primarily characterized by residential zones, interspersed with dynamic activity hubs such as tourist attractions, shopping malls, and hospitals. The prevailing issue in this area relates to persistent traffic congestion, stemming from the overreliance on private vehicles, inadequate public transportation infrastructure, disjointed intermodal connections, and the lack of seamless integration between transportation modes and activity centers. This study endeavors to comprehensively analyze pedestrian and vehicular movement in the periphery of the Taman Mini LRT station. This analysis is pivotal in assessing the current mobility landscape. Notably, the intensity of activity within a particular land use directly correlates with its ability to draw vehicular traffic, consequently leading to prolonged waiting times for pedestrians at crosswalks. Employing a four-step model, this research methodically defines pedestrian and vehicular flow within the region. This model incorporates output distribution of trips and origin-destination graphs. Additionally, stated preference techniques are employed to discern respondents’ inclinations when making travel decisions. This involves evaluating key factors like travel time, fares, frequency, accessibility level, comfort, and safety – categories that significantly influence their preferences when selecting between LRT and other transportation modes.

Understanding regional variation in euthanasia using geomedical frameworks: a critical ethical reflection

Considerable geographical variation in the uptake of euthanasia has been reported: some municipalities in the Netherlands have a 25 times higher euthanasia rate than other municipalities. Current ‘geomedical’ frameworks for interpreting practice variation in health care utilization seem inadequately tailored to understand regional variation in morally controversial procedures such as euthanasia. The aim of this conceptual article is threefold: i) to add relevant medical ethical principles to current frameworks; ii) to provide a four-step ethical-geomedical model for the interpretation of geographical differences in the utilization of health care in general and for ethically controversial treatments in specific; iii) to gain better understanding of the existing geographical variation in the incidence of euthanasia by using this framework in our analysis.

Contrastive learning for traffic flow forecasting based on multi graph convolution network

AbstractContrastive learning is an increasingly important research direction and has attracted considerable attention in the field of computer vision. It can greatly improve the representativeness of image features through data augmentation, unsupervised learning, and pre‐trained models. However, in the field of traffic flow forecasting, most graph‐based models focus on the construct of spatial–temporal relationships between road segments and ignore the use of temporal data augmentation and pre‐trained models, which can improve the representation ability of the forecasting model. Therefore, in this work, contrastive learning are used to expand the distribution of sequence samples and improve the quality and generalization of forecasting models. Based on this, a novel forecasting model called contrastive learning based on multi graph convolution network (CLMGCN) is proposed, which is combined with four components: multi graph convolution network, which learns the spatial–temporal feature of the input traffic data; temporal data augmentation, which obtains the augmentation data of the input traffic data; contrastive learning, which achieves the pre‐training phase and improve the quality of output feature of multi graph convolution network; output block, which utilizes the enhanced output feature of multi graph convolution network for predicting the future traffic data. Finally, by the experimental results of four public traffic flow datasets, it can be shown that CLMGCN achieves higher traffic forecasting accuracy with lower model complexity.

Adaptive Joint Spatio-Temporal Graph Learning Network for Traffic Data Forecasting

Traffic data forecasting has become an integral part of the intelligent traffic system. Great efforts are spent developing tools and techniques to estimate traffic flow patterns. Many existing approaches lack the ability to model the complex and dynamic spatio-temporal relations in the traffic data, which are crucial in capturing the traffic dynamic. In this work, we propose a novel adaptive joint spatio-temporal graph learning network (AJSTGL) for traffic data forecasting. The proposed model utilizes static and adaptive graph learning modules to capture the static and dynamic spatial traffic patterns and optimize the graph learning process. A sequence-to-sequence fusion model is proposed to learn the temporal correlation and combine the output of multiple parallelized encoders. We also develop a spatio-temporal graph transformer module to complement the sequence-to-sequence fusion module by dynamically capturing the time-evolving node relations in long-term intervals. Experiments on three large-scale traffic flow datasets demonstrate that our model could outperform other state-of-the-art baseline methods.

Spatio-temporal Fourier enhanced heterogeneous graph learning for traffic forecasting

Traffic flow prediction is of paramount importance in the field of spatio-temporal forecasting. In recent years, research efforts have primarily been directed towards developing intricate graph convolutional networks (GCNs) to capture spatial complexities. However, this has inadvertently led to the neglect of the inherent temporal correlations in traffic prediction, as well as the heterogeneity of graph structures. As a result, existing models show limited efficacy when dealing with the complex nature of traffic data. To address this issue, this paper introduces a novel traffic prediction model: the Fourier-enhanced heterogeneous graph convolution attention recurrent network (FEHGCARN). This model integrates historical information and incorporates a graph convolution attention recurrent unit (GCARU), meticulously engineered to effectively capture spatio-temporal dependencies. Additionally, it features a Fourier-enhanced heterogeneous graph learning module, which facilitates the acquisition of complex relationships among nodes in the frequency domain. Notably, this memory network excels at recognizing abrupt traffic conditions. To validate our approach, we conducted comprehensive comparisons using three authentic datasets and benchmarked our model against six state-of-the-art baseline methods. The experimental results unequivocally demonstrate the superior performance of our model across all evaluation metrics.

Experimental Analysis of Time Series Models for Traffic Flow Prediction

Traffic flow prediction is a research topic signified by several researchers in a league span of disciplines. In this context, one of the most in-demand techniques of Machine Learning, especially time series-based techniques, helps in predicting traffic flow forecasting and increases the accuracy of the prediction model. In order to deliver extremely precise traffic forecasts, it is crucial that we put the prediction system into practice in the actual world. We aim to perform computations related to traffic on the traffic datasets and determine the accuracy of each model. For this purpose, we are using three distinct time series models: Long Short Term Memory (LSTM), the Autoregressive Integrated Moving Average (ARIMA), and the Seasonal Autoregressive Integrated Moving Average (SARIMA). From the results obtained, it is concluded that the proposed model achieves the highest prediction accuracy with the lowest root mean squared error.

Traffic Prediction using Machine Learning

The traffic is one of the major issues faced by people in almost every city. Predicting the traffic has always been very challenging for transportation planning as well as the city manager. The growth of population and usage of vehicles has increased the need for a reliable traffic prediction system. The system should reduce congestion, avoid accidents, and optimize the traffic flow that enhance road safety. The use of machine learning algorithms would be more suitable in handling the traffic and maintaining the flow of vehicles. The paper focuses on the work related to handling the traffic using machine learning principles such as LSTM and Random Forest (RF) algorithm. The advanced online dataset for traffic forecasts is used. The system is tested to have improved accuracy with the help of feature engineering. The basic dataset had the following fields: Vehicle Id, Time, Date, Junction Id are the primary and significant parameters considered to anticipate the traffic at each zone. With this we have added the day and weekend component to enhance our result.

Unlocking the Full Potential of Deep Learning in Traffic Forecasting Through Road Network Representations: A Critical Review

Research in short-term traffic forecasting has been blooming in recent years due to its significant implications in traffic management and intelligent transportation systems. The unprecedented advancements in deep learning have provided immense opportunities to leverage traffic data sensed from various locations of the road network, yet significantly increased the models’ complexity and data and computational requirements, limiting the actionability of the models. Consequently, the meaningful representation of traffic flow data and the road network has been highlighted as a key challenge in improving the efficiency, as well as the accuracy and reliability of forecasting models. This paper provides a systematic review of literature dedicated to spatiotemporal traffic forecasting. Three main representation approaches are identified, namely the stacked vector, image/grid, and graph, and are critically analyzed and compared in relation to their efficiency, accuracy and associated modeling techniques. Based on the findings, future research directions in traffic forecasting are proposed, aiming to increase the adoption of the developed models in real-world applications.

Enhancing Traffic Density Detection and Synthesis through Topological Attributes and Generative Methods

This study investigates the utilization of Graph Neural Networks (GNNs) within the realm of traffic forecasting, a critical aspect of intelligent transportation systems. The accuracy of traffic predictions is pivotal for various applications, including trip planning, road traffic control, and vehicle routing. The research comprehensively explores three notable GNN architectures—Graph Convolutional Networks (GCNs), GraphSAGE (Graph Sample and Aggregation), and Gated Graph Neural Networks (GGNNs)—specifically in the context of traffic prediction. Each architecture's methodology is meticulously examined, encompassing layer configurations, activation functions, and hyperparameters. With the primary aim of minimizing prediction errors, the study identifies GGNNs as the most effective choice among the three models. The outcomes, presented in terms of Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE), reveal intriguing insights. While GCNs exhibit an RMSE of 9.25 and an MAE of 8.2, GraphSAGE demonstrates improved performance with an RMSE of 8.5 and an MAE of 7.6. Gated Graph Neural Networks (GGNNs) emerge as the leading model, showcasing the lowest RMSE of 9.2 and an impressive MAE of 7.0. However, the study acknowledges the dynamic nature of these results, emphasizing their dependency on factors such as the dataset, graph structure, feature engineering, and hyperparameter tuning.

Multi-view spatiotemporal learning for traffic forecasting

The spatiotemporal learning has been one of the most burning research topics in traffic data analytics for traffic forecasting, which is instrumental in developing the intelligent transportation systems. Capturing accurately and efficiently complex spatiotemporal dependencies of the road network is a critical prerequisite of the traffic spatiotemporal forecasting. This study proposes a multi-view spatiotemporal learning (MVSTL) framework, which combines the fast parallel learning (FPL) and the serial learning (SL) to juggle the receptive field with the fitting capability of the model. The FPL is proposed to capture the spatiotemporal correlations synchronously and efficiently by reducing the number of parameters significantly. As a supplement to the FPL, the SL, which extracts the spatial and temporal features serially, can expand the spatial/temporal receptive fields and avoid information overwriting. The evaluation of the MVSTL is carried out by employing four sets of traffic data from the LA freeway system, and the experiment results reveal that the MVSTL is able to perform better than the advanced methods in prediction accuracy.

Traffic flow matrix-based graph neural network with attention mechanism for traffic flow prediction

Traffic flow forecasting is of great importance in intelligent transportation systems for congestion mitigation and intelligent traffic management. Most of the existing methods depend on deep learning to extract the spatial–temporal correlation of traffic nodes but ignore the traffic flow characteristics. In this paper, we design three traffic congestion indexes to reflect the operational status of nodes based on traffic flow theory and design a traffic flow matrix to better represent the relationship between nodes. We also design a novel graph convolution network with attention mechanisms called TFM-GCAM to better capture the spatial–temporal features and dynamic characteristics of nodes. A novel Fusion Attention mechanism is proposed to effectively fuse the dynamic characteristics and the spatial–temporal features for improvement. Experiments and ablation studies on the public dataset show the superiority of TFM-GCAM. We also discuss it with our previous works for a better understanding. Our research proposes to better integrate traffic flow theory into deep learning models and to better combine the respective strengths of attention mechanisms and graph neural networks for more effective traffic flow prediction.

Designing the Distribution Network of Essential Items in the Critical Conditions of Earthquakes and COVID-19 Simultaneously

Current societies must make the necessary plans for effective responses and to reduce the destructive effects of disasters. For this reason, this research has developed a mathematical programming model under uncertainty for earthquake relief and response during COVID-19. In the presented model, the possibility of facility failure is considered according to the intensity of the earthquake and COVID-19 to increase reliability. The simultaneous occurrence of these disasters presents unique challenges in ensuring the timely delivery of essential supplies to affected regions. Distribution centers (DCs) are considered to be of two types: the first type is local DCs, which use public centers and are close to accident points. These types of centers are prone to failure because they use public facilities. Another type is the reliable DCs built outside the disrupted area, which have a very low probability of loss due to spending more money to build them. In addition, to consider the reliability capabilities, the new model has tried to provide a complete model for transportation planning by considering the multi-trip mode of vehicles. Moreover, this model considers distance restriction at the demand point for the first time because of COVID-19 during the earthquake. The proposed network design aims to offer effective solutions in promptly delivering essential items to affected areas, thereby enhancing disaster management strategies and minimizing the impact of these crises on vulnerable populations. Uncertainty is presented using the probability approach based on the modeling scenario and a case study from the city of Istanbul to illustrate the performance of the suggested model. Finally, the suggested mode is solved with an Lp-metric and goal programming (GP) approach. The results show that in this case, the proposed model shows that effective and efficient aid delivery is possible in terms of time and cost. Therefore, it can help crisis managers respond by providing the required budget and appropriate logistics planning.

Research on Traffic Flow Forecasting Based on Dynamic Spatial-Temporal Transformer

Accurate traffic flow forecasting is crucial for urban traffic control and route planning. Aiming at the difficulty in capturing dynamic spatio-temporal complexity of traffic flow, a dynamic spatio-temporal transformer (DST-Trans) model capable of modeling dynamic correlation of traffic flow is proposed, which consists of gated temporal convolutional network (GTCN), graph convolutional network (GCN), and spatio-temporal transformer (ST-TF). GTCN and GCN are utilized to capture the temporal and spatial characteristics of traffic flow, respectively. ST-TF includes a temporal transformer using temporal gated convolution and temporal multi-head self-attention to capture short-long term temporal features, and spatial transformer using spatial gated graph convolution and spatial multi-head self-attention to capture local-global dynamic spatial features. In addition, to take full advantage of the dynamic and static associations of road networks, multi-graph models of road relationship graph, similarity graph, and adaptive dynamic graph with SGGC are constructed. Experimental results show that the DST-Trans model in this paper shows good prediction performance in short-term (15 min), medium-term (30 min), and long-term (60 min) prediction, outperforming existing state-of-the-art models by up to approximately 7%.

Dynamic spatial–temporal graph convolutional recurrent networks for traffic flow forecasting

Traffic flow forecasting is crucial for making appropriate route guidance and vehicle scheduling schemes in intelligent transportation systems. However, recent graph-based methods leverage pre-defined static graphs to describe the spatial–temporal characteristic of road networks. The interactions of two road segments are changeable under the influence of natural environmental and socioeconomic factors, while these methods are not sufficient to capture the complicated dynamic correlations of different nodes. To address these problems, we propose a novel dynamic graph-based deep learning framework with dynamic graph recurrent network for traffic flow forecasting, called Dynamic Spatial–temporal Graph Recurrent Neural Networks. In this framework, a novel dynamic graph generator is designed to obtain the dynamic representation of nodes, which employs multi-head attention network and dynamic node embedding to capture hidden spatial dependency more effectively. To infer the edge status of dynamic graph at different times, the generated dynamic graph is trained as special time series data via dynamic graph recurrent neural network for downstream time-series prediction. In contrast to methods straightforwardly concatenating static graphs and dynamic graphs, a novel fusion framework integrates two-channel convolutional networks with penalty terms and a gate fusion layer to extract dynamic spatial dependency from multiple graphs for improving forecasting accuracy and reducing computational consumption. Experiments on three real-world datasets are carried out to evaluate the superior performance of our model. Compared with previous state-of-the-art baselines, the proposed method performs much better with 10%–26% improvements on three datasets. The results also indicate that our model is robust against emergent traffic situations.

GSAA: A Novel Graph Spatiotemporal Attention Algorithm for Smart City Traffic Prediction

With the development of 5G and Internet of Things technologies, the application process of smart transportation in smart cities continues to advance. Sensors are a key source of information for smart transportation, and their data commonly includes complicated traffic scene information. Urban traffic scheduling and efficiency can be significantly increased by deploying data from smart sensors to forecast traffic flows. Despite the fact that some related works have focused on the prediction task of traffic flows, they have not completely mined the traffic spatiotemporal information present in smart sensor data. We offer a novel graph spatio-temporal attention algorithm (GSAA) for traffic prediction in this paper. To completely exploit the geographical and temporal correlations among complicated roadways for traffic forecast, the algorithm combines a spatiotemporal attention mechanism with a graph neural network.To take full advantage of how much effect various hyperparameters provide, deep reinforcement learning is used to obtain the optimal hyperparameters while the predictive model is trained. Experimental results on real-world public datasets show that the algorithm proposed in this paper achieves performance improvements of about 5.47% and 13.10% over the MAE (mean absolute error) than the best baseline strategies for short-term and long-term traffic forecasting, respectively.

CROSSING SPEEDS OF CARS THROUGH SIGNALIZED INTERSECTIONS

The article deals with the problem of traffic in three traffic-light intersections in the street network of Iasi city. Usually, the existing traffic lights do not fully take into account the size, structure and parameters of the queue of vehicles waiting at intersections; which in turn affects the traffic capacity of the intersection. In the study, we used a representative set of measurements taken at the three intersections to interpret the variation in the crossing speeds of the traffic light intersection space by the vehicle columns using the linear regression method. We studied several categories of vehicles queuing before the stop line at the intersection. We made a statistical analysis of the time taken to cross three intersections by vehicles in different starting positions. The main results of the research showed estimates in good agreement with observational data as well as a significant reduction in vehicle speed (to 58%) when there are different categories of vehicles queuing at the intersection. This study can be used in the urban traffic diagnosis method, being part of a traffic study together with urban traffic forecasting and therapy.

A Secure Intelligent System for Internet of Vehicles: Case Study on Traffic Forecasting

Significant efforts have been made for vehicle-to-vehicle communications that now enable the Internet of Vehicles (IoV). However, current IoV solutions are unable to capture traffic data both accurately and securely. Another drawback of current IoV models that are based on deep learning is that the methods used do not tune hyperparameters efficiently. In this paper, a new system known as Secure and Intelligent System for the Internet of Vehicles (SISIV) is developed. A deep learning architecture based on graph convolutional networks and an attention mechanism are implemented. In addition, blockchain technology is used to protect data transmission between nodes in the IoV system. Moreover, the hyperparameters of the generated deep learning model are intelligently selected using a branch-and-bound technique. To validate SISIV, experiments were conducted on four networked vehicle databases dealing with prediction problems. In terms of forecasting rate ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$&gt;$</tex-math> </inline-formula> 90%), F-measure ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$&gt;$</tex-math> </inline-formula> 80%), and attack detection ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$&lt;$</tex-math> </inline-formula> 75%), the results clearly show the superiority of SISIV over baseline systems. Moreover, compared to state-of-the-art solutions based on traffic prediction, SISIV enables efficient and reliable prediction of traffic flow in an IoV context.