Use of sequential learning for short-term traffic flow forecasting

Accurate short-term traffic flow forecasting has become a crucial step in the overall goal of better road network management. Previous research [H. Kirby, M. Dougherty, S. Watson, Should we use neural networks or statistical models for short term motorway traffic forecasting, International Journal of Forecasting 13 (1997) 43–50.] has demonstrated that a straightforward application of neural networks can be used to forecast traffic flows along a motorway link. The objective of this paper is to report on the application and performance of an alternative neural computing algorithm which involves ‘sequential or dynamic learning’ of the traffic flow process. Our initial work [H. Chen, S. Clark, M.S. Dougherty, S.M. Grant-Muller, Investigation of network performance prediction, Report on Dynamic Neural Network and Performance Indicator development, Institute for Transport Studies, University of Leeds Technical Note 418, 1998 (unpublished)] was based on simulated data (generated using a Hermite polynomial with random noise) that had a profile similar to that of traffic flows in real data. This indicated the potential suitability of dynamic neural networks with traffic flow data. Using the Kalman filter type network an initial application with M25 motorway flow data suggested that a percentage absolute error (PAE) of approximately 9.5% could be achieved for a network with five hidden units (compared with 11% for the static neural network model). Three different neural networks were trained with all the data (containing an unknown number of incidents) and secondly using data wholly obtained around incidents. Results showed that from the three different models, the ‘simple dynamic model’ with the first five units fixed (and subsequent hidden units distributed amongst these) had the best forecasting performance. Comparisons were also made of the networks’ performance on data obtained around incidents. More detailed analysis of how the performance of the three networks changed through a single day (including an incident) showed that the simple dynamic model again outperformed the other two networks in all time periods. The use of ‘piecewise’ models (i.e. where a different model is selected according to traffic flow conditions) for data obtained around incidents highlighted good performance again by the simple dynamic network. This outperformed the standard Kalman filter neural network for a medium-sized network and is our overall recommendation for any future application.     

A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting

The k-nearest neighbor (KNN) model is an effective statistical model applied in short-term traffic forecasting that can provide reliable data to guide travelers. This study proposes an improved KNN model to enhance forecasting accuracy based on spatiotemporal correlation and to achieve multistep forecasting. The physical distances among road segments are replaced with equivalent distances, which are defined by the static and dynamic data collected from real road networks. The traffic state of a road segment is described by a spatiotemporal state matrix instead of only a time series as in the original KNN model. The nearest neighbors are selected according to the Gaussian weighted Euclidean distance, which adjusts the influences of time and space factors on spatiotemporal state matrices. The forecasting accuracies of the improved KNN and of four other models are compared, and experimental results indicate that the improved KNN model is more appropriate for short-term traffic multistep forecasting than the other models are. This study also discusses the application of the improved KNN model in a time-varying traffic state.     

Short-term traffic flow rate forecasting based on identifying similar traffic patterns

The ability to timely and accurately forecast the evolution of traffic is very important in traffic management and control applications. This paper proposes a non-parametric and data-driven methodology for short-term traffic forecasting based on identifying similar traffic patterns using an enhanced K-nearest neighbor (K-NN) algorithm. Weighted Euclidean distance, which gives more weight to recent measurements, is used as a similarity measure for K-NN. Moreover, winsorization of the neighbors is implemented to dampen the effects of dominant candidates, and rank exponent is used to aggregate the candidate values. Robustness of the proposed method is demonstrated by implementing it on large datasets collected from different regions and by comparing it with advanced time series models, such as SARIMA and adaptive Kalman Filter models proposed by others. It is demonstrated that the proposed method reduces the mean absolute percent error by more than 25%. In addition, the effectiveness of the proposed enhanced K-NN algorithm is evaluated for multiple forecast steps and also its performance is tested under data with missing values. This research provides strong evidence suggesting that the proposed non-parametric and data-driven approach for short-term traffic forecasting provides promising results. Given the simplicity, accuracy, and robustness of the proposed approach, it can be easily incorporated with real-time traffic control for proactive freeway traffic management.     

Hybrid artificial neural network and locally weighted regression models for lane-based short-term urban traffic flow forecasting

ABSTRACT

In recent years, there has been considerable research interest in short-term traffic flow forecasting. However, forecasting models offering a high accuracy at a fine temporal resolution (e.g. 1 or 5?min) and lane level are still rare. In this study, a combination of genetic algorithm, neural network and locally weighted regression is used to achieve optimal prediction under various input and traffic settings. The genetically optimized artificial neural network (GA-ANN) and locally weighted regression (GA-LWR) models are developed and tested, with the former forecasting traffic flow every 5-min within a 30-min period and the latter for forecasting traffic flow of a particular 5-min period of each for four lanes of an urban arterial road in Beijing, China. In particular, for morning peak and off-peak traffic flow prediction, the GA-ANN 5-min traffic flow model results in average errors of 3–5% and most 95th percentile errors of 7–14% for each of the four lanes; for the peak and off-peak time traffic flow predictions, the GA-LWR 5-min traffic flow model results in average errors of 2–4% and most 95th percentile errors are lower than 10% for each of the four lanes. When compared to previous models that usually offer average errors greater than 6–15%, such empirical findings should be of interest to and instrumental for transportation authorities to incorporate in their city- or state-wide Advanced Traveller Information Systems (ATIS).     

Capacity-constrained traffic forecasting model

Projecting future traffic is an important stage in any traffic and transportation planning study. Accurate traffic forecasting is vital for transportation planning, highway safety evaluation, traffic operations analysis, and geometric and pavement design among others. In view of its importance, this paper introduces a regression-based traffic forecasting methodology for a one dimensional capacity-constrained highway. Five different prediction functions are tested; the best was selected according to the accuracy of projections against historical traffic data. The three-parameter logistic function produced more accurate projections compared to other functions tested when highway capacity constraints were taken into consideration. The R ² values at various test locations ranged from 88% to 98%, indicating good prediction capability. Using the Fisher's information matrix approach, the t-statistic test showed all parameters in the logistic function were highly statistically significant. To evaluate reliability of projections, predictive intervals were calculated at a 95% level of confidence. Predictions using the logistic function were also compared to those predicted using the compound growth rate and linear regression methods. The results show that the proposed methodology generates much more reasonable projections than current practices.     

Local online kernel ridge regression for forecasting of urban travel times

Accurate and reliable forecasting of traffic variables is one of the primary functions of Intelligent Transportation Systems. Reliable systems that are able to forecast traffic conditions accurately, multiple time steps into the future, are required for advanced traveller information systems. However, traffic forecasting is a difficult task because of the nonlinear and nonstationary properties of traffic series. Traditional linear models are incapable of modelling such properties, and typically perform poorly, particularly when conditions differ from the norm. Machine learning approaches such as artificial neural networks, nonparametric regression and kernel methods (KMs) have often been shown to outperform linear models in the literature. A bottleneck of the latter approach is that the information pertaining to all previous traffic states must be contained within the kernel, but the computational complexity of KMs usually scales cubically with the number of data points in the kernel. In this paper, a novel kernel-based machine learning (ML) algorithm is developed, namely the local online kernel ridge regression (LOKRR) model. Exploiting the observation that traffic data exhibits strong cyclic patterns characterised by rush hour traffic, LOKRR makes use of local kernels with varying parameters that are defined around each time point. This approach has 3 advantages over the standard single kernel approach: (1) It allows parameters to vary by time of day, capturing the time varying distribution of traffic data; (2) It allows smaller kernels to be defined that contain only the relevant traffic patterns, and; (3) It is online, allowing new traffic data to be incorporated as it arrives. The model is applied to the forecasting of travel times on London’s road network, and is found to outperform three benchmark models in forecasting up to 1 h ahead.     

Comparison of parametric and nonparametric models for traffic flow forecasting

Single point short-term traffic flow forecasting will play a key role in supporting demand forecasts needed by operational network models. Seasonal autoregressive integrated moving average (ARIMA), a classic parametric modeling approach to time series, and nonparametric regression models have been proposed as well suited for application to single point short-term traffic flow forecasting. Past research has shown seasonal ARIMA models to deliver results that are statistically superior to basic implementations of nonparametric regression. However, the advantages associated with a data-driven nonparametric forecasting approach motivate further investigation of refined nonparametric forecasting methods. Following this motivation, this research effort seeks to examine the theoretical foundation of nonparametric regression and to answer the question of whether nonparametric regression based on heuristically improved forecast generation methods approach the single interval traffic flow prediction performance of seasonal ARIMA models.     

Integrated model for traffic flow forecasting under rainy conditions

Inclement weather, such as heavy rain, significantly affects road traffic flow operation, which may cause severe congestion in road networks in cities. This study investigates the effect of inclement weather, such as rain events, on traffic flow and proposes an integrated model for traffic flow parameter forecasting during such events. First, an analysis of historical observation data indicates that the forecasting error of traffic flow volume has a significant linear correlation with mean precipitation, and thus, forecasting accuracy can be considerably improved by applying this linear correlation to correct forecasting values. An integrated online precipitation‐correction model was proposed for traffic flow volume forecasting based on these findings. We preprocessed precipitation data transformation and used outlier detection techniques to improve the efficiency of the model. Finally, an integrated forecasting model was designed through data fusion methods based on the four basic forecasting models and the proposed online precipitation‐correction model. Results of the model validation with the field data set show that the designed model is better than the other models in terms of overall accuracy throughout the day and under precipitation. However, the designed model is not always ideal under heavy rain conditions. Copyright © 2016 John Wiley & Sons, Ltd.     

Spatiotemporal traffic forecasting: review and proposed directions

This paper systematically reviews studies that forecast short-term traffic conditions using spatial dependence between links. We extract and synthesise 130 research papers, considering two perspectives: (1) methodological framework and (2) methods for capturing spatial information. Spatial information boosts the accuracy of prediction, particularly in congested traffic regimes and for longer horizons. Machine learning methods, which have attracted more attention in recent years, outperform the naïve statistical methods such as historical average and exponential smoothing. However, there is no guarantee of superiority when machine learning methods are compared with advanced statistical methods such as spatiotemporal autoregressive integrated moving average. As for the spatial dependency detection, a large gulf exists between the realistic spatial dependence of traffic links on a real network and the studied networks as follows: (1) studies capture spatial dependency of either adjacent or distant upstream and downstream links with the study link, (2) the spatially relevant links are selected either by prejudgment or by correlation-coefficient analysis, and (3) studies develop forecasting methods in a corridor test sample, where all links are connected sequentially together, assume a similarity between the behaviour of both parallel and adjacent links, and overlook the competitive nature of traffic links.     

Development and evaluation of a hybrid travel time forecasting model

The purpose of this paper is to develop and evaluate a hybrid travel time forecasting model with geographic information systems (GIS) technologies for predicting link travel times in congested road networks. In a separate study by You and Kim (cf. You, J., Kim, T.J., 1999b. In: Proceedings of the Third Bi-Annual Conference of the Eastern Asia Society for Transportation Studies, 14–17 September, Taipei, Taiwan), a non-parametric regression model has been developed as a core forecasting algorithm to reduce computation time and increase forecasting accuracy. Using the core forecasting algorithm, a prototype hybrid forecasting model has been developed and tested by deploying GIS technologies in the following areas: (1) storing, retrieving, and displaying traffic data to assist in the forecasting procedures, (2) building road network data, and (3) integrating historical databases and road network data. This study shows that adopting GIS technologies in link travel time forecasting is efficient for achieving two goals: (1) reducing computational delay and (2) increasing forecasting accuracy.     

Probe data-driven travel time forecasting for urban expressways by matching similar spatiotemporal traffic patterns

Travel time is an effective measure of roadway traffic conditions. The provision of accurate travel time information enables travelers to make smart decisions about departure time, route choice and congestion avoidance. Based on a vast amount of probe vehicle data, this study proposes a simple but efficient pattern-matching method for travel time forecasting. Unlike previous approaches that directly employ travel time as the input variable, the proposed approach resorts to matching large-scale spatiotemporal traffic patterns for multi-step travel time forecasting. Specifically, the Gray-Level Co-occurrence Matrix (GLCM) is first employed to extract spatiotemporal traffic features. The Normalized Squared Differences (NSD) between the GLCMs of current and historical datasets serve as a basis for distance measurements of similar traffic patterns. Then, a screening process with a time constraint window is implemented for the selection of the best-matched candidates. Finally, future travel times are forecasted as a negative exponential weighted combination of each candidate’s experienced travel time for a given departure. The proposed approach is tested on Ring 2, which is a 32km urban expressway in Beijing, China. The intermediate procedures of the methodology are visualized by providing an in-depth quantitative analysis on the speed pattern matching and examples of matched speed contour plots. The prediction results confirm the desirable performance of the proposed approach and its robustness and effectiveness in various traffic conditions.     

Classification modeling approach for vehicle dynamics model‐integrated traffic simulation assessing surrogate safety

To assess safety impacts of untried traffic control strategies, an earlier study developed a vehicle dynamics model‐integrated (i.e., VISSIM‐CarSim‐SSAM) simulation approach and evaluated its performance using surrogate safety measures. Although the study found that the integrated simulation approach was a superior alternative to existing approaches in assessing surrogate safety, the computation time required for the implementation of the integrated simulation approach prevents it from using it in practice. Thus, this study developed and evaluated two types of models that could replace the integrated simulation approach with much faster computation time, feasible for real‐time implementation. The two models are as follows: (i) a statistical model (i.e., logit model) and (ii) a nonparametric approach (i.e., artificial neural network). The logit model and the neural network model were developed and trained on the basis of three simulation data sets obtained from the VISSIM‐CarSim‐SSAM integrated simulation approach, and their performances were compared in terms of the prediction accuracy. These two models were evaluated using six new simulation data sets. The results indicated that the neural network approach showing 97.7% prediction accuracy was superior to the logit model with 85.9% prediction accuracy. In addition, the correlation analysis results between the traffic conflicts obtained from the neural network approach and the actual traffic crash data collected in the field indicated a statistically significant relationship (i.e., 0.68 correlation coefficient) between them. This correlation strength is higher than that of the VISSIM only (i.e., the state of practice) simulation approach. The study results indicated that the neural network approach is not only a time‐efficient way to implementing the VISSIM‐CarSim‐SSAM integrated simulation but also a superior alternative in assessing surrogate safety. Copyright © 2014 John Wiley & Sons, Ltd.     

Short-term prediction of border crossing time and traffic volume for commercial trucks: A case study for the Ambassador Bridge

Short-term forecasting of traffic characteristics, such as traffic flow, speed, travel time, and queue length, has gained considerable attention from transportation researchers and practitioners over past three decades. While past studies primarily focused on traffic characteristics on freeways or urban arterials this study places particular emphasis on modeling the crossing time over one of the busiest US–Canada bridges, the Ambassador Bridge. Using a month-long volume data from Remote Traffic Microwave Sensors and a yearlong Global Positioning System data for crossing time two sets of ANN models are designed, trained, and validated to perform short-term predictions of (1) the volume of trucks crossing the Ambassador Bridge and (2) the time it takes for the trucks to cross the bridge from one side to the other. The prediction of crossing time is contingent on truck volume on the bridge and therefore separate ANN models were trained to predict the volume. A multilayer feedforward neural network with backpropagation approach was used to train the ANN models. Predicted crossing times from the ANNs have a high correlation with the observed values. Evaluation indicators further confirmed the high forecasting capability of the trained ANN models. The ANN models from this study could be used for short-term forecasting of crossing time that would support operations of ITS technologies.     

Measuring and enhancing the transferability of hidden Markov models for dynamic travel behavioral analysis

As an emerging dynamic modeling method that incorporates time-dependent heterogeneity, hidden Markov models (HMM) are receiving increased research attention with regards to travel behavior modeling and travel demand forecasting. This paper focuses on the model transferability of HMM. Based on a series of transferability and goodness-of-fit measures, it finds that HMMs have a superior performance in predicting future transportation mode choice, compared to conventional choice models. Aimed at further enhancing its transferability, this paper proposes a Bayesian conditional recalibration approach that maps the model prediction directly to the context data. Compared to traditional model transferring methods, the proposed approach does not assume fixed parameterization and recalibrates the utilities and the prediction directly. A comparison between the proposed approach and the traditional transfer-scaling favors our approach, with higher goodness-of-fit. This paper fills the gap in understanding the transferability of HMM and proposes a practical method that enables potential applications of HMM.

     

Identifying optimal data aggregation interval sizes for link and corridor travel time estimation and forecasting

With the recent increase in the deployment of ITS technologies in urban areas throughout the world, traffic management centers have the ability to obtain and archive large amounts of data on the traffic system. These data can be used to estimate current conditions and predict future conditions on the roadway network. A general solution methodology for identifying the optimal aggregation interval sizes for four scenarios is proposed in this article: (1) link travel time estimation, (2) corridor/route travel time estimation, (3) link travel time forecasting, and (4) corridor/route travel time forecasting. The methodology explicitly considers traffic dynamics and frequency of observations. A formulation based on mean square error (MSE) is developed for each of the scenarios and interpreted from a traffic flow perspective. The methodology for estimating the optimal aggregation size is based on (1) the tradeoff between the estimated mean square error of prediction and the variance of the predictor, (2) the differences between estimation and forecasting, and (3) the direct consideration of the correlation between link travel time for corridor/route estimation and forecasting. The proposed methods are demonstrated using travel time data from Houston, Texas, that were collected as part of the automatic vehicle identification (AVI) system of the Houston Transtar system. It was found that the optimal aggregation size is a function of the application and traffic condition.

Estimating historical hourly traffic volumes via machine learning and vehicle probe data: A Maryland case study

This paper focuses on the problem of estimating historical traffic volumes between sparsely-located traffic sensors, which transportation agencies need to accurately compute statewide performance measures. To this end, the paper examines applications of vehicle probe data, automatic traffic recorder counts, and neural network models to estimate hourly volumes in the Maryland highway network, and proposes a novel approach that combines neural networks with an existing profiling method. On average, the proposed approach yields 24% more accurate estimates than volume profiles, which are currently used by transportation agencies across the US to compute statewide performance measures. The paper also quantifies the value of using vehicle probe data in estimating hourly traffic volumes, which provides important managerial insights to transportation agencies interested in acquiring this type of data. For example, results show that volumes can be estimated with a mean absolute percent error of about 21% at locations where average number of observed probes is between 30 and 47 vehicles/h, which provides a useful guideline for assessing the value of probe vehicle data from different vendors.     

Shipment forecasting for supply chain collaborative transportation management using grey models with grey numbers

The sharing of forecasts is vital to supply chain collaborative transportation management (CTM). Shipment forecasting is fundamental to CTM, and is essential to carrier tactical and operational planning processes such as network planning, routing, scheduling, and fleet planning and assignment. By applying and extending grey forecasting theory, this paper develops a series of shipment forecasting models for supply chain CTM. Grey time-series forecasting and grey systematic forecasting models are developed for shipment forecasting under different collaborative frameworks. This paper also integrates grey numbers with grey models for analyzing shipment forecasting under partial information sharing in CTM frameworks. An example of an integrated circuit (IC) supply chain and relevant data are provided. The proposed models yield more accurate prediction results than regression, autoregressive integrated moving average (ARIMA), and neural network models. Finally, numerical results indicate that as the degree of information sharing increases under CTM, carrier prediction accuracy increases. This paper demonstrates how the proposed forecasting models can be applied to the CTM system and provides the theoretical basis for the forecasting module developed for supply chain CTM.     

Traffic volume forecasting based on radial basis function neural network with the consideration of traffic flows at the adjacent intersections

The forecasting of short-term traffic flow is one of the key issues in the field of dynamic traffic control and management. Because of the uncertainty and nonlinearity, short-term traffic flow forecasting could be a challenging task. Artificial Neural Network (ANN) could be a good solution to this issue as it is possible to obtain a higher forecasting accuracy within relatively short time through this tool. Traditional methods for traffic flow forecasting generally based on a separated single point. However, it is found that traffic flows from adjacent intersections show a similar trend. It indicates that the vehicle accumulation and dissipation influence the traffic volumes of the adjacent intersections. This paper presents a novel method, which considers the travel flows of the adjacent intersections when forecasting the one of the middle. Computational experiments show that the proposed model is both effective and practical.     

Short‐term prediction of traffic parameters—performance comparison of a data‐driven and less‐data‐required approaches

The travel decisions made by road users are more affected by the traffic conditions when they travel than the current conditions. Thus, accurate prediction of traffic parameters for giving reliable information about the future state of traffic conditions is very important. Mainly, this is an essential component of many advanced traveller information systems coming under the intelligent transportation systems umbrella. In India, the automated traffic data collection is in the beginning stage, with many of the cities still struggling with database generation and processing, and hence, a less‐data‐demanding approach will be attractive for such applications, if it is not going to reduce the prediction accuracy to a great extent. The present study explores this area and tries to answer this question using automated data collected from field. A data‐driven technique, namely, artificial neural networks (ANN), which is shown to be a good tool for prediction problems, is taken as an example for data‐driven approach. Grey model, GM(1,1), which is also reported as a good prediction tool, is selected as the less‐data‐demanding approach. Volume, classified volume, average speed and classified speed at a particular location were selected for the prediction. The results showed comparable performance by both the methods. However, ANN required around seven times data compared with GM for comparable performance. Thus, considering the comparatively lesser input requirement of GM, it can be considered over ANN in situations where the historic database is limited. Copyright © 2016 John Wiley & Sons, Ltd.     

Estimation of AADT from short period counts in hong kong — A comparison between neural network method and regression analysis

The average annual daily traffic (AADT) volumes can be estimated by using a short period count of less than twenty‐four hour duration. In this paper, the neural network method is adopted for the estimation of AADT from short period counts and for the determination of the most appropriate length of counts. A case study is carried out by analysing data at thirteen locations on trunk roads and primary roads in urban area of Hong Kong. The estimation accuracy is also compared with the one obtained by regression analysis approach. The results show that the neural network approach consistently performed better than the regression analysis approach.