Short-term Traffic Prediction Research Articles

A Hybrid Model for Short-Term Traffic Volume Prediction in Massive Transportation Systems

The prediction of short-term volatile traffic becomes increasingly critical for efficient traffic engineering in intelligent transportation systems. Accurate forecast results can assist in traffic management and pedestrian route selection, which will help alleviate the huge congestion problem in the system. This paper presents a novel hybrid DTMGP model to accurately forecast the volume of passenger flows multi-step ahead with the comprehensive consideration of factors from temporal, origin-destination spatial, and frequency and self-similarity perspectives. We first apply discrete wavelet transform to decompose the traffic volume series into an appropriation component and several detailed components. Then we propose a more efficient tracking model to forecast the appropriation component and a novel Gaussian process model to forecast the detailed components. The forecasting performance is evaluated with real-time passenger flow data in Chongqing, China. Simulation results demonstrate that our hybrid model can achieve on average 20%–50% accuracy improvement, especially during rush hours.

A Spatial-Temporal Hybrid Model for Short-Term Traffic Prediction

Accurate and timely short-term traffic prediction is important for Intelligent Transportation System (ITS) to solve the traffic problem. This paper presents a hybrid model called SpAE-LSTM. This model considers the temporal and spatial features of traffic flow and it consists of sparse autoencoder and long short-term memory (LSTM) network based on memory units. Sparse autoencoder extracts the spatial features within the spatial-temporal matrix via full connected layers. It cooperates with the LSTM network to capture the spatial-temporal features of traffic flow evolution and make prediction. To validate the performance of the SpAE-LSTM, we implement it on the real-world traffic data from Qingyang District of Chengdu city, China, and compare it with advanced traffic prediction models, such as models only based on LSTM or SAE. The results demonstrate that the proposed model reduces the mean absolute percent error by more than 15%. The robustness of the proposed model is also validated and the mean absolute percent error on more than 86% road segments is below 20%. This research provides strong evidence suggesting that the proposed SpAE-LSTM effectively captures the spatial-temporal features of the traffic flow and achieves promising results.

Predicting Fine-Grained Traffic Conditions via Spatio-Temporal LSTM

Predicting traffic conditions for road segments is the prelude of working on intelligent transportation. Many existing methods can be used for short-term or long-term traffic prediction, but they focus more on regions than on road segments. The lack of fine-grained traffic predicting approach hinders the development of ITS. Therefore, MapLSTM, a spatio-temporal long short-term memory network preluded by map-matching, is proposed in this paper to predict fine-grained traffic conditions. MapLSTM first obtains the historical and real-time traffic conditions of road segments via map-matching. Then LSTM is used to predict the conditions of the corresponding road segments in the future. Breaking the single-index forecasting, MapLSTM can predict the vehicle speed, traffic volume, and the travel time in different directions of road segments simultaneously. Experiments confirmed MapLSTM can not only achieve prediction for road segments based a large scale of GPS trajectories effectively but also have higher predicting accuracy than GPR and ConvLSTM. Moreover, we demonstrate that MapLSTM can serve various applications in a lightweight way, such as cognizing driving preferences, learning navigation, and inferring traffic emissions.

Short-Term Traffic Prediction by Two-Level Data Driven Model in 5G-Enabled Edge Computing Networks

Real-time and accurate short-term traffic prediction can effectively improve traffic efficiency, reduce accidents, and facilitate relevant departments to take reasonable traffic guidance measures. Therefore, we propose a two-level data driven model for short-term traffic prediction in an edge computing environment. Firstly, a Deep Belief Network (DBN) is developed to extract the traffic characteristics between the road occupancy and road flow collected by the deployed detectors. Then, we predict the developed future road flow of each road segment based on the output of the DBN, which would be used as one of the inputs of a Hidden Markov Model (HMM). Finally, a HMM is developed to predict the future road speed of each road segment characterizing the statistical relationship between the road flow and road speed. To validate the effectiveness of our proposed model, the data from the Performance Measurement System (PeMS) of the California Department of Transportation is applied. Simulation results show that our proposed model has better prediction performance in short-term traffic prediction than other models.

A Special Event-Based K-Nearest Neighbor Model for Short-Term Traffic State Prediction

Recently, short-term traffic state prediction for urban transportation networks has become a popular topic. However, due to the uncontrollable and unpredictable elements of special events, it is difficult to get abundant data and desired predictions under such condition. As k-nearest neighbor (KNN) has a competitive advantage over other approaches, it could predict traffic state based on a small correlative part of data. Thus, a special event-based KNN (SEKNN) model is proposed for the short-term traffic state prediction with three key points presented in this paper. First, the evolution of the traffic states is redefined as a multipart object, state unit, which includes the benchmark state and the trend vector. Second, to select the nearest neighbors, the state distances of the state units are designed to be compatible with the benchmark states and the trend vectors by fusing the Euclidean distance and the cosine distance. Finally, the prediction results are forced to adjust the benchmark states based on the prediction function using the Gaussian weighted method. The proposed SEKNN is implemented in the district of the Beijing Workers' Stadium (257 links), where special events occur frequently. The results show that the proposed model performs significantly better under special events than the other traditional machine-learning approaches and state-of-the-art deep-learning approaches.

Predictive Control for Distributed Smart Street Light Network

With the advent of smart city that embedded with smart technology, namely, smart streetlight, in urban development, the quality of living for citizens has been vastly improved. TALiSMaN is one of the promising smart streetlight schemes to date, however, it possesses certain limitation that led to network congestion and packet dropped during peak road traffic periods. Traffic prediction is vital in network management, especially for real-time decision-making and latency-sensitive application. With that in mind, this paper analyses three real-time short-term traffic prediction models, specifically simple moving average, exponential moving average and weighted moving average to be embedded onto TALiSMaN, that aim to ease network congestion. Additionally, the paper proposes traffic categorisation and packet propagation control mechanism that uses historical road traffic data to manage the network from overload. In this paper, we evaluate the performance of these models with TALiSMaN in simulated environment and compare them with TALiSMaN without traffic prediction model. Overall, weighted moving average showed promising results in reducing the packet dropped while capable of maintaining the usefulness of the streetlight when compared to TALiSMaN scheme, especially during rush hour.

Short-Term Vehicle Traffic Prediction for Terahertz Line-of-Sight Estimation and Optimization in Small Cells

Significant efforts have been made and are still being made on short-term traffic prediction methods, especially for highway traffic based on punctual measurements. The literature on predicting the spatial distribution of the traffic in urban intersections is, however, very limited. This paper presents a novel data-driven prediction algorithm based on random forests regression over spatiotemporal aggregated data of vehicle counts inside a grid. The proposed approach aims to estimate the future distribution of vehicle to everything (V2X) traffic demand, providing valuable input for dynamic management of radio resources in small cells. Radio access networks (RANs) working in the terahertz band and deployed in small cells are expected to meet the high-demanding data rate requirements of connected vehicles. However, terahertz frequency propagation has important limitations in outdoor scenarios, including distance propagation, high-absorption coefficients values, and low-reflection properties. More concretely, in settings such as complex road intersections, dynamic signal blockage, and shadowing effects may cause significant power losses and compromise the quality of service for some vehicles. The forthcoming network demand estimated from the regression algorithm is used to compute the losses expected due to other vehicles potentially located between the transmitter and the receiver. We conclude that our approach, which is designed from a grid-like perspective, outperforms other traffic prediction methods and the combined result of these predictions with a dynamic reflector orientation algorithm, as a use case application, allows reducing the ratio of vehicles that do not receive minimum signal power.

PATTERN RECOGNITION BASED SPEED FORECASTING METHODOLOGY FOR URBAN TRAFFIC NETWORK

A full methodology of short-term traffic prediction is proposed for urban road traffic network via Artificial Neural Network (ANN). The goal of the forecasting is to provide speed estimation forward by 5, 15 and 30 min. Unlike similar research results in this field, the investigated method aims to predict traffic speed for signalized urban road links and not for highway or arterial roads. The methodology contains an efficient feature selection algorithm in order to determine the appropriate input parameters required for neural network training. As another contribution of the paper, a built-in incomplete data handling is provided as input data (originating from traffic sensors or Floating Car Data (FCD)) might be absent or biased in practice. Therefore, input data handling can assure a robust operation of speed forecasting also in case of missing data. The proposed algorithm is trained, tested and analysed in a test network built-up in a microscopic traffic simulator by using daily course of real-world traffic.

Short-term traffic volume prediction by ensemble learning in concept drifting environments

Because of the rapid changes in traffic conditions caused by various circumstances, such as road construction and traffic jams, the distribution of the traffic volume data changes over time. The performances of traditional traffic volume prediction methods, with fixed model types and parameter settings, suffer from gradual degradation during these concept drift processes. In this paper, a novel incremental regression framework under the concept drifting environment is proposed, with ensemble learning as the major solution for updating the distribution representation. First, we transform the regression problem of traffic volume forecasting into a binary classification problem. Second, loss functions for incremental and ensemble learning are constructed based on this transformation. Finally, the incremental learning of the regression function is formulated as stepwise updating of the decision hyperplane. The experimental results show that our method is more stable and accurate than the existing incremental and ensemble regression methods.

Short term traffic flow prediction based on multiple time series data and improved Elman neural network

To improve the short term traffic prediction precision, this paper proposes an improved Elman neural network (ELMNN) model for the prediction work. The model input includes two parts: the measured flow data and the theoretical flow data obtained by traffic occupancy and speed. Furthermore, in order to capture the inner regularity of the time series data, the theoretical flow data and the measured flow data are both reconstructed using a phase space reconstruction method. Finally, the reconstructed data are put into the improved ELMNN model, which is developed by employing the mind evolution algorithm (MEA). Compared with the original models, the results of the case study show that the proposed model can obviously improve the prediction accuracy.

PCNN: Deep Convolutional Networks for Short-Term Traffic Congestion Prediction

Traffic problems have seriously affected people's life quality and urban development, and forecasting the short-term traffic congestion is of great importance to both individuals and governments. However, understanding and modeling the traffic conditions can be extremely difficult, and our observations from real traffic data reveal that (1) similar traffic congestion patterns exist in the neighboring time slots and on consecutive workdays; (2) the levels of traffic congestion have clear multiscale properties. To capture these characteristics, we propose a novel method named PCNN based on deep Convolutional Neural Network, modeling Periodic traffic data for short-term traffic congestion prediction. PCNN has two pivotal procedures: time series folding and multi-grained learning. It first temporally folds the time series and constructs a two-dimensional matrix as the network input, such that both the real-time traffic conditions and past traffic patterns are well considered; then with a series of convolutions over the input matrix, it is able to model the local temporal dependency and multiscale traffic patterns. In particular, the global trend of congestion can be addressed at the macroscale; whereas more details and variations of the congestion can be captured at the microscale. Experimental results on a real-world urban traffic dataset confirm that folding time series data into a two-dimensional matrix is effective and PCNN outperforms the baselines significantly for the task of short-term congestion prediction.

Construction of traffic state vector using mutual information for short-term traffic flow prediction

Short-term traffic flow prediction is an integral part in most of Intelligent Transportation Systems (ITS) research and applications. Many researchers have already developed various methods that predict the future traffic condition from the historical database. Nevertheless, there has not been sufficient effort made to study how to identify and utilize the different factors that affect the traffic flow. In order to improve the performance of short-term traffic flow prediction, it is necessary to consider sufficient information related to the road section to be predicted. In this paper, we propose a method of constructing traffic state vectors by using mutual information (MI). First, the variables with different time delays are generated from the historical traffic time series, and the spatio-temporal correlations between the road sections in urban road network are evaluated by the MI. Then, the variables with the highest correlation related to the target traffic flow are selected by using a greedy search algorithm to construct the traffic state vector. The K-Nearest Neighbor (KNN) model is adapted for the application of the proposed state vector. Experimental results on real-world traffic data show that the proposed method of constructing traffic state vector provides good prediction accuracy in short-term traffic prediction.

Machine Learning Approach to Short-Term Traffic Congestion Prediction in a Connected Environment

Traffic congestion is a complex phenomenon triggered by a combination of multiple interacting factors. One of the main factors is the disturbances caused by individual vehicles, which cannot be identified in aggregate traffic data. Advances in vehicle wireless communications present new opportunities to measure traffic perturbations at the individual vehicle level. The key question is whether it is possible to find the relationship between these perturbations and shockwave formation and utilize this knowledge to improve the identification and prediction of congestion formation. Accordingly, this paper explores the use of three machine learning techniques, logistic regression, random forests, and neural networks, for short-term traffic congestion prediction using vehicle trajectories available through connected vehicles technology. Vehicle trajectories provided by the Next Generation SIMulation (NGSIM) program were utilized in this study. Two types of predictive models were developed in this study: (1) offline models which are calibrated based on historical data and are updated (re-trained) whenever significant changes occur in the system, such as changes/updates to the infrastructure, and (2) online models which are calibrated using historical data and updated regularly using real-time information on prevailing traffic conditions obtained through V2V/V2I communications. Results show that the accuracy of the models built in this study to predict the congested traffic state can reach 97%. The models presented can be used in various potential applications including improving road safety by warning drivers of upcoming traffic slowdowns and improving mobility through integration with traffic control systems.

Short-Term Traffic State Prediction Based on the Spatiotemporal Features of Critical Road Sections.

Recently, short-term traffic prediction under conditions with corrupted or missing data has become a popular topic. Since a road section has predictive power regarding the adjacent roads at a specific location, this paper proposes a novel hybrid convolutional long short-term memory neural network model based on critical road sections (CRS-ConvLSTM NN) to predict the traffic evolution of global networks. The critical road sections that have the most powerful impact on the subnetwork are identified by a spatiotemporal correlation algorithm. Subsequently, the traffic speed of the critical road sections is used as the input to the ConvLSTM to predict the future traffic states of the entire network. The experimental results from a Beijing traffic network indicate that the CRS-ConvLSTM outperforms prevailing deep learning (DL) approaches for cases that consider critical road sections and the results validate the capability and generalizability of the model when predicting with different numbers of critical road sections.

Quantifying uncertainty in short-term traffic prediction and its application to optimal staffing plan development

In this paper, we aim to quantify uncertainty in short-term traffic volume prediction by enhancing a hybrid machine learning model based on Particle Swarm Optimization (PSO) and Extreme Learning Machine (ELM) neural network. Different from the previous studies, the PSO-ELM models require no statistical inference nor distribution assumption of the model parameters, but rather focus on generating the prediction intervals (PIs) that can minimize a multi-objective function which considers two criteria, reliability and interval sharpness. The improved PSO-ELM models are developed for an hourly border crossing traffic dataset and compared to: (1) the original PSO-ELMs; (2) two state of the art models proposed by Zhang et al. (2014) and Guo et al. (2014) separately; and (3) the traditional ARMA and Kalman filter models. The results show that the improved PSO-ELM can always keep the mean PI length the lowest, and guarantee that the PI coverage probability is higher than the corresponding PI nominal confidence, regardless of the confidence level assumed. The study also probes the reasons that led to a few points being not covered by the PIs of PSO-ELMs. Finally, the study proposes a comprehensive optimization framework to make staffing plans for border crossing authority based on bounds of PIs and point predictions. The results show that for holidays, the staffing plans based on PI upper bounds generated much lower total system costs, and that those plans derived from PI upper bounds of the improved PSO-ELM models, are capable of producing the lowest average waiting times at the border. For a weekday or a typical Monday, the workforce plans based on point predictions from Zhang et al. (2014) and Guo et al. (2014) models generated the smallest system costs with low border crossing delays. Moreover, for both holiday and normal Monday scenarios, if the border crossing authority lacked the required staff to implement the plans based on PI upper bounds or point predictions, the staffing plans based on PI lower bounds from the improved PSO-ELMs performed the best, with an acceptable level of service and total system costs close to the point prediction plans.

Predictor fusion for short-term traffic forecasting

• A novel prediction fusion framework is proposed in short-term traffic prediction. • The proposed framework cam combine multiple individual predictors. • A generic fusion framework for prediction under different traffic conditions. • The kNN fusion method can improve final accuracy, especially during incidents.

Feature selection‐based approach for urban short‐term travel speed prediction

This study proposes a feature selection-based approach to identify reasonable spatial-temporal traffic patterns related to the target link, in order to improve the online-prediction performance. The prediction task is composed of two steps: one hybrid intelligent algorithm-based feature selector (FS) is proposed to optimise original state vectors, which are designed empirically during the offline process and optimised state vectors are employed to carry out the online prediction. Numerical experiments by three non-parametric algorithms are conducted with taxis' global positioning system data in an urban road network of Changsha, China. It is concluded that: (i) under optimised state vectors, the prediction accuracies improve or almost maintain the same; (ii) K-nearest neighbour (KNN) with the simplest state vectors obtains the greatest improvement of prediction performance; (iii) although the performance improvement of e-support vector regression is limited with optimised state vectors, it always outperforms backward-propagation neural network and KNN; and (iv) three non-parametric approaches with optimised state vectors outperform auto-regressive integrated moving average in relatively longer prediction horizons. In conclusion, such FS-based approach is able to improve or guarantee the prediction performance under the remarkably reduced model complexity, and is a promising methodology for short-term traffic prediction.

Transmission power control of wireless sensor networks based on optimal connectivity

To develop a short-term traffic load prediction model for satellite networks, a prediction algorithm based on spatiotemporal correlation and least square support vector machine (STLS-SVM) is presented. The prediction model fully exploits the regularity and periodicity of satellite constellations and uses the lag correlation coefficients to determine which satellite pairs have the highest spatiotemporal correlation. Then, the traffic time sequences of the most highly correlated satellites are taken as input feature vectors for training the LS-SVM for short-term traffic prediction. A simulation test shows that the algorithm has higher network flow prediction accuracy and that using the spatiotemporal correlation improves the predictive performance.

High-Speed Data-Driven Methodology for Real-Time Traffic Flow Predictions: Practical Applications of ITS

Despite the achievements of academic research on data-driven k-nearest neighbour nonparametric regression (KNN-NPR), the low-speed computational capability of the KNN-NPR method, which can occur during searches involving enormous amounts of historical data, remains a major obstacle to improvements of real-system applications. To overcome this critical issue successfully, a high-speed KNN-NPR framework, capable of generating short-term traffic volume predictions, is proposed in this study. The proposed method is based on a two-step search algorithm, which has the two roles of building promising candidates for input data during nonprediction times and identifying decision-making input data for instantaneous predictions at the prediction point. To prove the efficacy of the proposed model, an experimental test was conducted with large-size traffic volume data. It was found that the performance of the model not only at least equals that of linear-search-based KNN-NPR in terms of prediction accuracy, but also shows a substantially reduced execution time in approximating real-time applications. This result suggests that the proposed algorithm can be also effectively employed as a preprocess to select useful past cases for advanced learning-based forecasting models.

基于K邻近算法的城市道路短时交通预测

基于K邻近算法的城市道路短时交通预测