Statistical methods for detecting nonlinearity and non-stationarity in univariate short-term time-series of traffic volume

Short-term traffic volume data are characterized by rapid and intense fluctuations with frequent shifts to congestion. Currently, research in short-term traffic forecasting deals with these phenomena either by smoothing them or by accounting for them by nonlinear models. But, these approaches lead to inefficient predictions particularly when the data exhibit intense oscillations or frequent shifts to boundary conditions (congestion). This paper offers a set of tools and methods to assess on underlying statistical properties of short-term traffic volume data, a topic that has largely been overlooked in traffic forecasting literature. Results indicate that the statistical characteristics of traffic volume can be identified from prevailing traffic conditions; for example, volume data exhibit frequent shifts from deterministic to stochastic structures as well as transitions between cyclic and strongly nonlinear behaviors. These findings could be valuable in the implementation of a variable prediction strategy according to the statistical characteristics of the prevailing traffic volume states.     

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.     

Border crossing delay prediction using transient multi-server queueing models

As a result of the continued increase in travel demand coupled with the need for tighter security and inspection procedures after September 11, border crossing delay has recently become a critical issue with tremendous economic and social costs. The current paper develops multi-server queuing models to estimate border crossing delay in support of a predictive traveler information system for the crossings. Two classes of multi-server models are considered: (1) models with exponential inter-arrival times and Erlang service times; and (2) a more generic model with a Batch Markovian Arrival Process (BMAP) and phase types (PH) services. As a case study, the models are developed based on real-time traffic volume and inspection time data collected at one of the major US–Canada border crossings, the Peace Bridge, and their transient solution is obtained using heuristic methods. For validation, the queueing models’ estimates are compared to the results from a detailed microscopic traffic simulation model of the Peace Bridge border crossing. The comparison shows that the transient queueing model, along its heuristic solution algorithm, is capable of predicting border crossing delay. Finally, a set of sensitivity analysis tests are conducted, and the developed models are incorporated within an optimization framework to help inform border crossing management strategies.     

黄浦江首座公轨双层桥——闵浦二桥引桥工程总体方案研究

上海市轨道交通5号线南延伸工程跨越黄浦江节点与沪闵路一沪杭公路地方交通越江工程结合（即闵浦二桥新建工程），采用上下双层一体化结构形式。结合一体化区间引桥段桥梁型式，对各种方案的结构合理性、交通功能、对景观与环境的影响、工程量以及车站布置等方面进行了研究和论证，最终推荐“干”字形的独柱桥墩为实施方案。     

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.     

Delay-based passenger car equivalents for trucks at signalized intersections

This paper presents a new methodology for computing passenger car equivalents at signalized intersections that is based on the delay concept. Unlike the commonly used headway-based methods that consider only the excess headway consumed by trucks, the delay-based approach fully considers the additional delay heavy vehicles cause on traffic stream. Delay-based passenger car equivalents are not constant, but depend on traffic volume, truck type and truck percentage. The field data indicated that the passenger car equivalents increase as the traffic volume and the percentage of heavy vehicles increase. The field data were used to calibrate TRAF-NETSIM simulation model that was used to cover a broad range of traffic conditions. Mathematical models to estimate the equivalencies were developed. The passenger car equivalent for single unit trucks vary from 1.00 to 1.37, and for combination trucks 1.00–2.18 depending on traffic volume and truck percentage. The passenger car equivalents are highly correlated with traffic volume and, to some degree, with percentage of heavy vehicles. Although the PCE of 1.5 recommended in the 1985 HCM seems to be more reasonable than the 2.0 recommended in the 1994 and 1997 HCM, both overestimate the impact of single unit trucks. For combination trucks, the 1997 HCM overestimates the capacity reduction effects of the trucks in most cases.     

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.     

Characteristics of truck traffic in Singapore

This paper presents the results of a project conducted to study the characteristics of truck traffic in Singapore. Detailed traffic surveys recording counts of vehicles by axle-configuration were performed at 219 sites over a period of nearly two years. The surveys covered 5 different road classes, namely expressways, arterials, collectors, industrial roads and local roads. It was found that the time distribution of truck travel were not the same among the five road classes. The peaking characteristics of truck traffic were less pronounced compared to passenger car traffic. The peak hour truck volume varied from 67.0% to 9.7% of the daily truck traffic as compared to 13.8% for passenger car traffic. The lane distribution pattern of truck traffic was studied in detail by road class, and was found to be a function of total directional traffic volume, total directional truck volume and the number of traffic lanes. Composition analysis was also carried out to study the lane use characteristics of single- and multiple-unit trucks.     

A multivariate state space approach for urban traffic flow modeling and prediction

Urban traffic congestion is one of the most severe problems of everyday life in Metropolitan areas. In an effort to deal with this problem, intelligent transportation systems (ITS) technologies have concentrated in recent years on dealing with urban congestion. One of the most critical aspects of ITS success is the provision of accurate real-time information and short-term predictions of traffic parameters such as traffic volumes, travel speeds and occupancies. The present paper concentrates on developing flexible and explicitly multivariate time-series state space models using core urban area loop detector data. Using 3-min volume measurements from urban arterial streets near downtown Athens, models were developed that feed on data from upstream detectors to improve on the predictions of downstream locations. The results clearly suggest that different model specifications are appropriate for different time periods of the day. Further, it also appears that the use of multivariate state space models improves on the prediction accuracy over univariate time series ones.     

A novel forecasting approach inspired by human memory: The example of short-term traffic volume forecasting

Short-term traffic volume forecasting represents a critical need for Intelligent Transportation Systems. This paper develops a novel forecasting approach inspired by human memory, called the spinning network (SPN). The approach is then used for short-term traffic volume forecasting, utilizing a data set compiled from real-world traffic volume data obtained from the Hampton Roads traffic operations center in Virginia. To assess the accuracy of the SPN approach, its performance is compared to two other approaches, namely a back propagation neural network and a nearest neighbor approach. The transferability of the SPN approach and its ability to forecast for longer time periods into the future is also assessed. The results of the performance testing conducted in this paper demonstrates the superior predictive accuracy and drastically lower computational requirements of the SPN compared to either the neural network or the nearest neighbor approach. The tests also confirm the ability of the SPN to predict traffic volumes for longer time periods into the future, as well as the transferability of the approach to other sites.     

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.     

Crossing the bridge: The effects of time-varying tolls on curbing congestion

This paper estimates the traffic volume and travel time effects of the road congestion pricing implemented on the San Francisco-Oakland Bay Bridge. I employ both difference-in-differences and regression discontinuity approaches to analyze previously unexploited data for the two years spanning the price change and obtain causal estimates of the hourly average treatment effects of the policy. I find evidence of peak spreading in traffic volume and decreases in travel time during peak hours. I also find suggestive evidence of substitution to a nearby bridge and decreases in travel time variability. In addition, I calculate own- and cross-price elasticities.     

A multi-objective approach for Dynamic Airspace Sectorization using agent based and geometric models

A key limitation when accommodating the continuing air traffic growth is the fixed airspace structure including sector boundaries. The geometry of sectors has stayed relatively constant despite the fact that route structures and demand have changed dramatically over the past decade. Dynamic Airspace Sectorization is a concept where the airspace is redesigned dynamically to accommodate changing traffic demands. Various methods have been proposed to dynamically partition the airspace to accommodate the traffic growth while satisfying other sector constraints and efficiency metrics. However, these approaches suffer from several operational drawbacks, and their computational complexity increases fast as the airspace size and traffic volume increase. In this paper, we evaluate and identify the gaps in existing 3D sectorization methods, and propose an improved Agent Based Model (iABM) to address these gaps. We also propose three additional models using KD-Tree, Bisection and Voronoi Diagrams in 3D, to partition the airspace to satisfy the convexity constraint and reduce computational cost. We then augment these methods with a multi-objective optimization approach that uses four objectives: minimizing the variance of controller workload across the sectors, maximizing the average sector flight time, and minimizing the distance between sector boundaries and the traffic flow crossing points. Experimental results show that iABM has the best performance on workload balancing, but it is restrictive when it comes to the convexity constraint. Bisection- and Voronoi Diagram-based models perform worse than iABM on workload balancing but better on average sector flight time, and they can satisfy the convexity constraint. The KD-tree-based model has a lower computational cost, but with a poor performance on the given objectives.     

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.     

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.     

通渭路黄河大桥交通影响评价

文章基于现阶段兰州市道路、桥梁交通量情况,对拟建的通渭路黄河大桥设计方案进行了交通影响评价,并探讨了项目建成后可能存在的问题及相应的解决措施。     

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.     

The effect of the competition between cars and trucks on the evolution of the motorway transport system

Motorways, which were devised at the beginning of their history as dedicated roads intended to be traveled by cars only, are at present also traveled by considerable flows of trucks. This fact has deeply changed the motorway transport system with respect to its original conception, owing to the interactions between two categories of vehicles whose characteristics are very different. These interactions greatly increase the transport cost perceived by car drivers with respect to truck drivers. This paper studies the consequences of this cost asymmetry on the evolution of the transport system when the geometric characteristics of a motorway remain unchanged in time, while transport demand increases. By using a theoretical model of competition between cars and trucks, it is shown that, if both the geometric characteristics of a motorway and the increase rate of the activities that feed the transport demand remain unchanged over time, the competition between cars and trucks, as well as the fact that in general passengers have better transport alternatives than freight, make the increase rate of truck traffic greater than that of cars, causing a progressive increase in the proportion of trucks in the time periods in which a motorway is traveled by both the vehicle categories. Since truck traffic on motorways, at least in Europe, is very scarce on weekends and in holiday periods, in which motorways are traveled almost only by cars, these results seem to indicate a tendency to the specialization of motorways, which are likely to be used in the future mostly by only one category of vehicles in different periods of time.     

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).