Traffic Prediction Method Research Articles

Short-term traffic flow prediction: An ensemble machine learning approach

The inconvenience of travel, air pollution and consequent economic losses caused by traffic congestion have seriously restricted the healthy and sustainable development of cities in China. In this context, as the main component of current and future urban traffic management measures, intelligent transportation system is an important means to improve the traffic efficiency of road network and alleviate urban traffic congestion. Traffic flow prediction plays an important role in this connection. In this paper, an ensemble short-term traffic flow prediction method based on optimized variational mode decomposition (OVMD) and combined long short-term memory network (LSTM) is proposed. The method consists of three main components: 1. Use the improved bat algorithm to optimize the parameters of VMD to achieve better decomposition effect; 2. Use the optimized variational mode decomposition algorithm (OVMD) to decompose the unstable original traffic flow time series data into relatively stable multiple Intrinsic Mode Functions (IMFs); 3. The optimized L-BILSTM model is established by combining the basic long short-term memory network with the bidirectional long short-term memory network. It can better extract information from traffic flow data and improve the accuracy of prediction results.In the empirical study part, the traffic flow data of Changsha City is used to verify the prediction model proposed in this paper. The influence of the application of the variational mode decomposition algorithm to the training set data and the overall data on the final prediction results is also compared and analysed.

Channel attention-based spatial-temporal graph neural networks for traffic prediction

PurposeTraffic flow prediction has always been a top priority of intelligent transportation systems. There are many mature methods for short-term traffic flow prediction. However, the existing methods are often insufficient in capturing long-term spatial-temporal dependencies. To predict long-term dependencies more accurately, in this paper, a new and more effective traffic flow prediction model is proposed.Design/methodology/approachThis paper proposes a new and more effective traffic flow prediction model, named channel attention-based spatial-temporal graph neural networks. A graph convolutional network is used to extract local spatial-temporal correlations, a channel attention mechanism is used to enhance the influence of nearby spatial-temporal dependencies on decision-making and a transformer mechanism is used to capture long-term dependencies.FindingsThe proposed model is applied to two common highway datasets: METR-LA collected in Los Angeles and PEMS-BAY collected in the California Bay Area. This model outperforms the other five in terms of performance on three performance metrics a popular model.Originality/value(1) Based on the spatial-temporal synchronization graph convolution module, a spatial-temporal channel attention module is designed to increase the influence of proximity dependence on decision-making by enhancing or suppressing different channels. (2) To better capture long-term dependencies, the transformer module is introduced.

Spatio-Temporal AutoEncoder for Traffic Flow Prediction

Forecasting traffic flow is an important task in urban areas, and a large number of methods have been proposed for traffic flow prediction. However, most of the existing methods follow a general technical route to aggregate historical information spatially and temporally. In this paper, we propose a different approach for traffic flow prediction. Our major motivation is to more effectively incorporate various intrinsic patterns in real-world traffic flows, such as fixed spatial distributions, topological correlations, and temporal periodicity. Along this line, we propose a novel autoencoder-based traffic flow prediction method, named Spatio-Temporal AutoEncoder (ST-AE). The core of our method is an autoencoder specially designed to learn the intrinsic patterns from traffic flow data, and encode the current traffic flow information into a low-dimensional representation. The prediction is made by simply projecting the current hidden states to the future hidden states, and then reconstructing the future traffic flows with the trained autoencoder. We have conducted extensive experiments on four real-world data sets. Our method outperforms existing methods in several settings, particularly for long-term traffic flow prediction.

Road section traffic flow prediction method based on the traffic factor state network

Road section traffic flow prediction method based on the traffic factor state network

Traffic flow prediction model based on gated graph convolution with attention

As a significant part, flow forecasting is crucial to road planning, traffic control, and planning. Aiming at the problem of insufficient dependence of traffic prediction methods, we proposes an Attention-based Gating mechanism Graph Convolution Network (AGGCN). Firstly, it constructures traffic flow data and adjacency matrix based on the graph data construction method. Secondly, it utilized the diffusion graph convolution method to model the traffic flow in the traffic road network. Finally, the attention mechanism to predict the traffic flow. The experiments were carried out on two highway datasets PeMS04 and PeMS08 in California, USA. Compared with the 7 commonly used algorithms in traffic flow prediction, the MAE, MAPE, and RMSE of the AGGCN model are better than other baseline experiments.

A Vision Transformer Approach for Traffic Congestion Prediction in Urban Areas

Traffic problems continue to deteriorate because of increasing population in urban areas that rely on many modes of transportation, the transportation infrastructure has achieved considerable strides in the last several decades. This has led to an increase in congestion control difficulties, which directly affect citizens through air pollution, fuel consumption, traffic law breaches, noise pollution, accidents, and loss of time. Traffic prediction is an essential aspect of an intelligent transportation system in smart cities because it helps reduce overall traffic congestion. This article aims to design and enforce a traffic prediction scheme that is efficient and accurate in forecasting traffic flow. Available traffic flow prediction methods are still unsuitable for real-world applications. This fact motivated us to work on a traffic flow forecasting issue using Vision Transformers (VTs). In this work, VTs were used in conjunction with Convolutional neural networks (CNN) to predict traffic congestion in urban spaces on a city-wide scale. In our proposed architecture, a traffic image is fed to a CNN, which generates feature maps. These feature maps are then fed to the VT, which employs the dual techniques of tokenization and projection. Tokenization is used to convert features into tokens containing Vision information, which are then sent to projection, where they are transformed into feature maps and ultimately delivered to LSTM. The experimental results demonstrate that the vision transformer prediction method based on Spatio-temporal characteristics is an excellent way of predicting traffic flow, particularly during anomalous traffic situations. The proposed technology surpasses traditional methods in terms of precision, accuracy and recall and aids in energy conservation. Through rerouting, the proposed work will benefit travellers and reduce fuel use.

A Novel STFSA-CNN-GRU Hybrid Model for Short-Term Traffic Speed Prediction

Short-term traffic speed prediction is fundamental to intelligent transportation systems (ITS), and the accuracy of the model largely determines the performance of real-time traffic control and management. In this study, a short-term traffic speed prediction method based on the spatial-temporal analysis of traffic flow and a combined deep-learning model, and a hybrid spatial-temporal feature selection algorithm (STFSA) of a convolutional neural network–gated recurrent unit (CNN-GRU)) is initially developed. Specifically, the STFSA is firstly employed to reconstruct the spatial-temporal matrix of traffic speed based on temporal continuity and spatial characteristics, and then this matrix is considered as the input feature of the prediction model. After this, the nonlinear fitting ability of the CNN is adopted to extract deep features from the convolutional and pooling layers for model training. Finally, by combining the timing and long-range dependence of the captured data with the forward GRU and the reverse GRU, the accuracy of the prediction result is further improved. The validity of the proposed model can be verified by comparing the prediction results with the actual traffic data. Accordingly, in the case study, the performance is compared with various benchmark methods under the same prediction scenario, verifying the superiority of the proposed model.

Incorporating Multivariate Auxiliary Information for Traffic Prediction on Highways.

Traffic flow prediction is one of the most important tasks of the Intelligent Transportation Systems (ITSs) for traffic management, and it is also a challenging task affected by many complex factors, such as weather and time. Many cities adopt efficient traffic prediction methods to control traffic congestion. However, most of the existing methods of traffic prediction focus on urban road scenarios, neglecting the complexity of multivariate auxiliary information in highways. Moreover, these methods have difficulty explaining the prediction results based only on the historical traffic flow sequence. To tackle these problems, we propose a novel traffic prediction model, namely Multi-variate and Multi-horizon prediction based on Long Short-Term Memory (MMLSTM). MMLSTM can effectively incorporate auxiliary information, such as weather and time, based on a strategy of multi-horizon time spans to improve the prediction performance. Specifically, we first exploit a multi-horizon bidirectional LSTM model for fusing the multivariate auxiliary information in different time spans. Then, we combine an attention mechanism and multi-layer perceptron to conduct the traffic prediction. Furthermore, we can use the information of multivariate (weather and time) to provide interpretability to manage the model. Comprehensive experiments are conducted on Hangst and Metr-la datasets, and MMLSTM achieves better performance than baselines on traffic prediction tasks.

Migration and Energy Aware Network Traffic Prediction Method Based on LSTM in NFV Environment

Migration and Energy Aware Network Traffic Prediction Method Based on LSTM in NFV Environment

On improving the regional transportation efficiency based on federated learning

In recent years, regional traffic congestion has become increasingly frequent, which seriously affects the safety and efficiency of urban vehicles. Therefore, traffic flow prediction methods based on artificial intelligence are widely used in traffic management. However, the existing traffic flow prediction methods need to collect raw data, which involves risks of vehicle privacy leakage. Federated learning, which shares model updates without exchanging local data, has gradually become an effective solution to achieve privacy protection. A federated learning traffic flow prediction model for regional transportation systems is proposed in this paper. At the same time, due to the emergence of highly intelligent automatic driving vehicles, a vehicle scheduling system, which can control the departure and routes of vehicles in urban regions is developed in the proposed approach. A road weight measurement method combined with real time traffic information is introduced to optimize the driving routes of vehicles to reduce the average travel time. Additionally, departure strategy, is another factor that has a great influence on traffic efficiency, but is usually ignored in the past, and is also carefully compared and studied in this paper. The numerical results illustrate that the proposed schemes can effectively improve the privacy protection ability of model updates, reduce the scheduling completion time by using the traffic flow prediction model, and realize the comparative research between departure strategies, which provides a reference for developing a safe and efficient regional transportation system.

AI-assisted traffic matrix prediction using GA-enabled deep ensemble learning for hybrid SDN

A hybrid software-defined network (SDN), which is a network where traditional routers and SDN protocols coexist during the incremental deployment of SDNs, requires real-time link traffic information for effective deployment. This has called for the need of accurate real-time data analytics and traffic prediction methods. To date, various traffic prediction frameworks have been studied to facilitate analysis and extraction of valuable information from huge sets of incomplete and noisy data. However, due to the linear nature of network design, mainly characterized by manual control plane forwarding configurations, existing traffic prediction frameworks cannot perform consistent traffic prediction over multiple datasets in modern dynamic networks. To address this issue, ensemble-driven approaches based on deep learning (DL) have recently been suggested as a promising solution. Nevertheless, determining the most appropriate combination of baseline DL architectures to be adopted for accurate traffic prediction remains a challenge. This paper proposes a novel DL framework for improved traffic prediction in hybrid SDNs. The framework combines a deep ensemble learning model utilizing multiple dimensionality reduction algorithms and a genetic algorithm (GA). The multi-objective GA is used to perform dynamic optimization of the connection weights and thresholds of the deep ensemble learning model while overcoming the local optima problem. Experimental results show that the proposed approach can achieve more accurate forecast of link traffic than the traditional baseline DL frameworks.

A Review of Traffic State Prediction (TSP) Methods in Intelligent Transportation Systems (ITS)

In today’s world, traffic congestion is a major problem in almost all metropolitans. This problem is even becoming more crucial due to increasing numbers of vehicles. Mobility of people, travel time duration, quality of life, transportation planning systems and traffic management are examples which bear the effects of traffic congestion The modern smart technology such as Artificial Intelligence (AI) has reduced traffic congestion by improving traffic monitoring and management technologies. These technologies require sufficient and accurate traffic data such as flow, velocity, and traffic density. Several machine learning-based methods have been proposed to predict the traffic state. Providing accurate prediction is an important stage in the successful implementation of Intelligent Transportation Systems (ITS). In this paper, we summarize the latest approaches in enhancing traffic state prediction, and possible developments in future, which potentially can transform many aspects of traffic management.

A Dynamic Spatio-Temporal Deep Learning Model for Lane-Level Traffic Prediction

Traffic prediction aims to predict the future traffic state by mining features from history traffic information, and it is a crucial component for the intelligent transportation system. However, most existing traffic prediction methods focus on road segment prediction while ignore the fine-grainedlane-level traffic prediction. From observations, we found that different lanes on the same road segment have similar but not identical patterns of variation. Lane-level traffic prediction can provide more accurate prediction results for humans or autonomous driving systems to make appropriate and efficient decisions. In traffic prediction, the mining of spatial features is an important step and graph-based methods are effective methods. While most existing graph-based methods construct a static adjacent matrix, these methods are difficult to respond to spatio-temporal changes in time. In this paper, we propose a deep learning model for lane-level traffic prediction. Specifically, we take advantage of the graph convolutional network (GCN) with a data-driven adjacent matrix for spatial feature modeling and treat different lanes of the same road segment as different nodes. The data-driven adjacent matrix consists of the fundamental distance-based adjacent matrix and the dynamic lane correlation matrix. The temporal features are extracted with the gated recurrent unit (GRU). Then, we adaptively fuse spatial and temporal features with the gating mechanism to get the final spatio-temporal features for lane-level traffic prediction. Extensive experiments on a real-world dataset validate the effectiveness of our model.

LSH-based missing value prediction for abnormal traffic sensors with privacy protection in edge computing

Traffic flow prediction is an important part of intelligent transportation systems (ITS). However, sensor failures or the transmission distortion often occur in the process of data acquisition, which will inevitably cause the loss or abnormality of traffic flow data transmitted to the edge server. In this situation, it is necessary to share traffic flow data among different platforms. However, existing traffic flow prediction methods are facing two challenges in the process of traffic flow data sharing. First, user privacy is often leaked in the process of sharing traffic data on various platforms. Moreover, with the continuous updating of data, the efficiency and scalability of data sharing between different platforms will become lower and lower. In view of the above challenges, in this paper, we propose a novel prediction method for the missing traffic flow data caused by abnormal sensors, named ASMVP_{distr-LSH} based on distributed locality-sensitive hashing (LSH) technique. At last, a case study is presented to illustrate the feasibility and effectiveness of our approach ASMVP_{distr-LSH}.

Limi-TFP: Citywide Traffic Flow Prediction With Limited Road Status Information

Citywide traffic flow prediction is a basic but challenging task in the field of Intelligent Transportation Systems (ITS). Most existing traffic flow prediction methods require historical traffic data of all the target roads in both training and application stages. However, it is not easy, and usually costly, to collect real-time traffic data across the entire road network. Therefore, many existing methods have to narrow down the scope of their prediction on the parts of road networks. In this paper, we propose a deep-learning model, named Limi-TFP, which has the ability to identify a limited number of monitored roads, and achieves citywide traffic flow prediction by using the historical traffic data of these selected roads. Specifically, an embedding module is proposed to capture the spatial context (road topology structure) and the attributes (e.g., road type, length, lanes, etc.) of each road by embedding all road segments into vectors. A road ranking method is then developed for selecting a limited number of roads to be monitored. A group of multi-head attention mechanisms is exploited for capturing the dynamic correlations with each monitored road. Meanwhile, the fusion with external factors, including the point of interests (POIs) and weather data, is also taken into account to further improve the prediction accuracy. Extensive experiments on the real-world datasets demonstrate that the proposed method achieves the superior performance and is robust with the presence of noise compared to the state-of-the-art baselines, with only 5% roads being monitored.

Long-term traffic flow forecasting using a hybrid CNN-BiLSTM model

The increase of road traffic in large cities during the last years has produced that long and short-term traffic flow forecasting is a critical need for the authorities. The availability of good traffic flow prediction methods is a must to make informed decisions concerning (punctual) traffic congestions. Previous work has shown that the accuracy of these methods decreases if we consider urban traffic and long-term predictions. In this paper we present a hybrid model, combining a Convolutional Neural Network and a Bidirectional Long–Short-Term Memory network, and apply it to long-term traffic flow prediction in urban routes. This model combines the capability of CNN to extract hidden valuable features from the input model and the capability of BiLSTM to understand the temporal context. In order to assess the usefulness of our model, we considered four streets of the city of Madrid with different characteristics and compared the results of our proposed model with the ones obtained by eight widely used baseline models. The results show that our hybrid model outperforms the baseline models with respect to three metrics commonly used in regression: mean absolute error, root mean squared error and accuracy.

Cellular Traffic Prediction: A Deep Learning Method Considering Dynamic Nonlocal Spatial Correlation, Self-Attention, and Correlation of Spatiotemporal Feature Fusion

Cellular traffic prediction will play a key role in the deployment of future smart cities. Although the current traffic prediction methods based on deep learning show better performance than traditional prediction methods, they still have the following problems: (1) In spatial domain, the correlations between cellular traffic features cannot be captured accurately in non-local (including “geographic adjacency” and long-distance) spatial areas. (2) In temporal domain, the correlation of different time-grained features is failed to consider. To address these problems, a deep learning method considering dynamic non-local spatial correlation, self-attention, and correlation of spatio-temporal feature fusion is proposed. In spatial domain, our method can accurately capture the spatial correlation and highlight the contribution of more relevant traffic in the non-local area by designing a NLG-NLAM model. In temporal domain, the correlations of time-periodic features with different granularities are considered to clarify the key roles of different periodic features and eliminate the influence of irrelevant cellular traffic features on the prediction by designing a calibration layer. Experimental results indicate that the proposed method shows better performance than other mainstream prediction methods on three real-world cellular traffic datasets.

TAP: Traffic Accident Profiling via Multi-Task Spatio-Temporal Graph Representation Learning

Predicting traffic accidents can help traffic management departments respond to sudden traffic situations promptly, improve drivers’ vigilance, and reduce losses caused by traffic accidents. However, the causality of traffic accidents is complex and difficult to analyze. Most existing traffic accident prediction methods do not consider the dynamic spatio-temporal correlation of traffic data, which leads to unsatisfactory prediction accuracy. To address this issue, we propose a multi-task learning framework (TAP) based on the Spatio-temporal Variational Graph Auto-Encoders (ST-VGAE) for traffic accident profiling. We firstly capture the dynamic spatio-temporal correlation of traffic conditions through a spatio-temporal graph convolutional encoder and embed it as a low-latitude vector. Then, we use a multi-task learning scheme to combine external factors to generate the traffic accident profiling. Furthermore, we propose a traffic accident profiling application framework based on edge computing. This method increases the speed of calculation by offloading the calculation of traffic accident profiling to edge nodes. Finally, the experimental results on real datasets demonstrate that TAP outperforms other state-of-the-art baselines.

Traffic Safety Oriented Multi-Intersection Flow Prediction Based on Transformer and CNN

Intelligent traffic signal control is one of the important means to ensure traffic safety. Effective signal control can make traffic flow fast and smooth, which first needs current and future traffic information. As the control of one intersection may affect adjacent intersections, this paper proposes to predict future traffic flow with consideration of multi-intersections. It can dynamically improve traffic conditions and reduce traffic congestion. Based on various nonlinear spatial relationships at correlated multi-intersections and the potential time-dependent relationship in traffic volume, a traffic flow prediction method named CNNformer which combines transformer with CNN, is proposed. The convolution neural network (CNN) and transformer are used to extract the spatial and temporal features of correlated multiple intersections. The learnable time code is embedded into transformer’s location code, and the location information and time information are injected into the model to help it learn the time characteristics of traffic volume. This study also considers the impact of cyclical traffic flow pattern and proposes CNNformer+. In the method, all of the data from the previous time window, as well as the data from the prior week and month, are correspondingly entered into the network. Finally, the output is generated through average pooling, realizing the learning of cyclical traffic flow characteristics. In the experiment, CNNformer+ and the state-of-the-art traffic flow prediction methods are compared using simulated data. The results show that the proposed model outperforms the existing models in prediction accuracy and efficiency.

Highway Traffic Crash Risk Prediction Method considering Temporal Correlation Characteristics

Crash risk analysis and prediction are considered the premise of highway traffic safety control, which directly affects the accuracy and effectiveness of traffic safety decisions. A highway traffic crash risk prediction method considering temporal correlation characteristics is proposed in this research. Firstly, the case-control sample analysis method is used to extract 6 time series sample data composed of crash traffic flow data and corresponding non-crash traffic flow data for crash risk analysis and prediction. Secondly, the multiparameter fusion clustering analysis method is used to indicate that the sample data of different time series have different effects on the crash risk. Then, the random forest model is used to screen several traffic flow variables that affect the highway crash risk. Thereafter, the downstream mean speed (ASD1D2), the upstream mean occupancy (AOU1U2), and the speed difference (DSU1D1) on the nearest detector were determined as the explanatory variables of the crash risk prediction model. Finally, based on the three variables, the dynamic Bayesian network model for highway traffic crash risk prediction is proposed. The overall prediction accuracy of this model is 84.9%, the crash prediction accuracy is 60.8%, and the non-crash prediction accuracy is 92.3%. Also, the prediction results show that the dynamic Bayesian model has better prediction effect than the static Bayesian model for the same sample data.