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.     

Transfer demand prediction for timed transfer coordination in public transport operational control

Timed transfer coordination in public transit reduces passenger transfer time by providing seamless interconnected transfers. The problem arises when a Receiving Vehicle (RV) arrives to the transfer stop before a Feeding Vehicle (FV) carrying transferring passengers. Timed transfer coordination in operational control dynamically decides whether a RV is held at the transfer stop to allow transfers, or departs as scheduled. While transfer demand is essential for implementing timed transfer coordination, this variable is generally not available in public transit because of the lack of passenger transfer plans. The problem of acquiring this variable in real‐time has also received limited attention in the related literature. This paper proposes a new method to dynamically predict the transfer demand. We anticipate the transferring probability from each individual passenger by examining historical travel itineraries. Three different types of models (simple analytical, statistical, and computation intelligence model) are developed to forecast the number of transferring passengers. Numerical experiments using observed Automatic Vehicle Location and Automatic Fare Collection data from South East Queensland, Australia show the accuracy and applicability of the proposed models in timed transfer coordination. Copyright © 2017 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.     

The station-free sharing bike demand forecasting with a deep learning approach and large-scale datasets

The station-free sharing bike is a new sharing traffic mode that has been deployed in a large scale in China in the early 2017. Without docking stations, this system allows the sharing bike to be parked in any proper places. This study aimed to develop a dynamic demand forecasting model for station-free bike sharing using the deep learning approach. The spatial and temporal analyses were first conducted to investigate the mobility pattern of the station-free bike sharing. The result indicates the imbalanced spatial and temporal demand of bike sharing trips. The long short-term memory neural networks (LSTM NNs) were then developed to predict the bike sharing trip production and attraction at TAZ for different time intervals, including the 10-min, 15-min, 20-min and 30-min intervals. The validation results suggested that the developed LSTM NNs have reasonable good prediction accuracy in trip productions and attractions for different time intervals. The statistical models and recently developed machine learning methods were also developed to benchmark the LSTM NN. The comparison results suggested that the LSTM NNs provide better prediction accuracy than both conventional statistical models and advanced machine learning methods for different time intervals. The developed LSTM NNs can be used to predict the gap between the inflow and outflow of the sharing bike trips at a TAZ, which provide useful information for rebalancing the sharing bike in the system.     

A gradient boosting logit model to investigate driver’s stop-or-run behavior at signalized intersections using high-resolution traffic data

Driver’s stop-or-run behavior at signalized intersection has become a major concern for the intersection safety. While many studies were undertaken to model and predict drivers’ stop-or-run (SoR) behaviors including Yellow-Light-Running (YLR) and Red-Light-Running (RLR) using traditional statistical regression models, a critical problem for these models is that the relative influences of predictor variables on driver’s SoR behavior could not be evaluated. To address this challenge, this research proposes a new approach which applies a recently developed data mining approach called gradient boosting logit model to handle different types of predictor variables, fit complex nonlinear relationships among variables, and automatically disentangle interaction effects between influential factors using high-resolution traffic and signal event data collected from loop detectors. Particularly, this research will first identify a series of related influential factors including signal timing information, surrounding traffic information, and surrounding drivers’ behaviors using thousands drivers’ decision events including YLR, RLR, and first-to-stop (FSTP) extracted from high-resolution loop detector data from three intersections. Then the research applies the proposed data mining approach to search for the optimal prediction model for each intersection. Furthermore, a comparison was conducted to compare the proposed new method with the traditional statistical regression model. The results show that the gradient boosting logit model has superior performance in terms of prediction accuracy. In contrast to other machine learning methods which usually apply ‘black-box’ procedures, the gradient boosting logit model can identify and rank the relative importance of influential factors on driver’s stop-or-run behavior prediction. This study brings great potential for future practical applications since loops have been widely implemented in many intersections and can collect data in real time. This research is expected to contribute to the improvement of intersection safety significantly.     

Modelling the effects of road pricing on traffic using ERP traffic data

Singapore’s Electronic Road Pricing (ERP) system involves time-variable charges which are intended to spread the morning traffic peak. The charges are revised every three months and thus induce regular motorists to re-think their travel decisions. ERP traffic data, captured by the system, provides a valuable source of information for studying motorists’ travel behaviour. This paper proposes a new modelling methodology for using these data to forecast short-term impacts of rate adjustment on peak period traffic volumes. Separate models are developed for different categories of vehicles which are segmented according to their demand elasticity with respect to road pricing. A method is proposed for estimating the maximum likelihood value of preferred arrival time (PAT) for each vehicle’s arrivals at a particular ERP gantry under different charging conditions. Iterative procedures are used in both model calibration and application. The proposed approach was tested using traffic datasets recorded in 2003 at a gantry located on Singapore’s Central Expressway (CTE). The model calibration and validation show satisfactory results.     

Travel demand forecasts improved by using cross-sectional data from multiple time points

Forecasts of travel demand are often based on data from the most recent time point, even when cross-sectional data is available from multiple time points. This is because forecasting models with similar contexts have higher transferability, and the context of the most recent time point is believed to be the most similar to the context of a future time point. In this paper, the author proposes a method for improving the forecasting performance of disaggregate travel demand models by utilising not only the most recent dataset but also an older dataset. The author assumes that the parameters are functions of time, which means that future parameter values can be forecast. These forecast parameters are then used for travel demand forecasting. This paper describes a case study of journeys to work mode choice analysis in Nagoya, Japan, using data collected in 1971, 1981, 1991, and 2001. Behaviours in 2001 are forecast using a model with only the most recent 1991 dataset and models that combine the 1971, 1981, and 1991 datasets. The models proposed by the author using data from three time points can provide better forecasts. This paper also discusses the functional forms for expressing parameter changes and questions the temporal transferability of not only alternative-specific constants but also level-of-service and socio-economic parameters.     

Quantifying uncertainties in a national forecasting model

Uncertainties related to demand model system outputs is an important issue in travel demand models. This paper focuses on uncertainties arisen from the fact that models are estimated on a sample of the population (and not the whole population). Forecasting systems can be quite complex, and may contain procedures that not easily permit analytically derived statistical measures of uncertainty. In this paper, the possibilities to use computer-intensive numerical methods to compute statistical measures for very complex systems, without being bound to an analytical approach, are explored. Here, the bootstrap method is used to obtain statistical measures of outputs produced by the forecasting system SAMPERS. The SAMPERS system is used by Swedish transport authorities. The bootstrap method is briefly described as well as the procedure of applying bootstrap on the SAMPERS system. Numerical results are presented for selected forecast results at different levels such as total traffic demand, origin–destination demand, train line demand and the demand on specific links. Also, the uncertainty related to the value of time estimate is analysed.     

Real time transit demand prediction capturing station interactions and impact of special events

Demand for public transportation is highly affected by passengers’ experience and the level of service provided. Thus, it is vital for transit agencies to deploy adaptive strategies to respond to changes in demand or supply in a timely manner, and prevent unwanted deterioration in service quality. In this paper, a real time prediction methodology, based on univariate and multivariate state-space models, is developed to predict the short-term passenger arrivals at transit stations. A univariate state-space model is developed at the station level. Through a hierarchical clustering algorithm with correlation distance, stations with similar demand patterns are identified. A dynamic factor model is proposed for each cluster, capturing station interdependencies through a set of common factors. Both approaches can model the effect of exogenous events (such as football games). Ensemble predictions are then obtained by combining the outputs from the two models, based on their respective accuracy. We evaluate these models using data from the 32 stations on the Central line of the London Underground (LU), operated by Transport for London (TfL). The results indicate that the proposed methodology performs well in predicting short-term station arrivals for the set of test days. For most stations, ensemble prediction has the lowest mean error, as well as the smallest range of error, and exhibits more robust performance across the test days.     

Estimation of bus dwell time using univariate time series models

A significant proportion of bus travel time is contributed by dwell time for passenger boarding and alighting. More accurate estimation of bus dwell time (BDT) can enhance efficiency and reliability of public transportation system. Regression and probabilistic models are commonly used in literatures where a set of independent variables are used to define the statistical relationship between BDT and its contributing factors. However, due to technical and monetary constraints, it is not always feasible to collect all the data required for the models to work. More importantly, the contributing factors may vary from one bus route to another. Time series based methods can be of great interest as they require only historical time series data, which can be collected using a facility known as automatic vehicle location (AVL) system. This paper assesses four different time series based methods namely random walk, exponential smoothing, moving average (MA), and autoregressive integrated moving average to model and estimate BDT based on AVL data collected from Auckland. The performances of the proposed methods are ranked based on three important factors namely prediction accuracy, simplicity, and robustness. The models showed promising results and performed differently for central business district (CBD) and non‐CBD bus stops. For CBD bus stops, MA model performed the best, whereas for non‐CBD bus stops, ARIMA model performed the best compared with other time series based models. Copyright © 2014 John Wiley & Sons, Ltd.     

Enhanced transport-related air pollution prediction through a novel metamodel approach

This research proposes a novel approach to improve the ability to forecast low frequency extreme events of transport-related pollution in urban areas using a limited input data set. The approach is based on the idea of a self-managing model, able to adapt to unexpected changes in pollution level. In more detail, for a given combination of variables, it selects the most suitable prediction model within a set of alternative air quality models, estimated for a wider range of locations and conditions.In this study, the new approach is tested for the prediction of nitrogen dioxide concentration in the United Kingdom (UK), specifically in an air quality monitoring site of the Greater Manchester Area, by comparing it with a context-specific statistical model (ARIMAX). The analysis results show that the two methods are similar in terms of global covariance and difference between observed and simulated concentrations, however the performance of the new approach in the prediction of extreme air pollution events is up to 27% better than the standard statistical approach and up to 113% better than the artificial neural network method.     

Short-term forecasting of high-speed rail demand: A hybrid approach combining ensemble empirical mode decomposition and gray support vector machine with real-world applications in China

Short-term forecasting of high-speed rail (HSR) passenger flow provides daily ridership estimates that account for day-to-day demand variations in the near future (e.g., next week, next month). It is one of the most critical tasks in high-speed passenger rail planning, operational decision-making and dynamic operation adjustment. An accurate short-term HSR demand prediction provides a basis for effective rail revenue management. In this paper, a hybrid short-term demand forecasting approach is developed by combining the ensemble empirical mode decomposition (EEMD) and grey support vector machine (GSVM) models. There are three steps in this hybrid forecasting approach: (i) decompose short-term passenger flow data with noises into a number of intrinsic mode functions (IMFs) and a trend term; (ii) predict each IMF using GSVM calibrated by the particle swarm optimization (PSO); (iii) reconstruct the refined IMF components to produce the final predicted daily HSR passenger flow, where the PSO is also applied to achieve the optimal refactoring combination. This innovative hybrid approach is demonstrated with three typical origin–destination pairs along the Wuhan-Guangzhou HSR in China. Mean absolute percentage errors of the EEMD-GSVM predictions using testing sets are 6.7%, 5.1% and 6.5%, respectively, which are much lower than those of two existing forecasting approaches (support vector machine and autoregressive integrated moving average). Application results indicate that the proposed hybrid forecasting approach performs well in terms of prediction accuracy and is especially suitable for short-term HSR passenger flow forecasting.     

Short/medium-term prediction for the aviation emissions in the en route airspace considering the fluctuation in air traffic demand

This paper proposes a novel short/medium-term prediction method for aviation emissions distribution in en route airspace. An en route traffic demand model characterizing both the dynamics and the fluctuation of the actual traffic demand is developed, based on which the variation and the uncertainty of the short/medium-term traffic growth are predicted. Building on the demand forecast the Boeing Fuel Flow Method 2 is applied to estimate the fuel consumption and the resulting aviation emissions in the en route airspace. Based on the traffic demand prediction and the en route emissions estimation, an aviation emissions prediction model is built, which can be used to forecast the generation of en route emissions with uncertainty limits. The developed method is applied to a real data set from Hefei Area Control Center for the en route emission prediction in the next 5 years, with time granularities of both months and years. To validate the uncertainty limits associated with the emission prediction, this paper also presents the prediction results based on future traffic demand derived from the regression model widely adopted by FAA and Eurocontrol. The analysis of the case study shows that the proposed method can characterize well the dynamics and the fluctuation of the en route emissions, thereby providing satisfactory prediction results with appropriate uncertainty limits. The prediction results show a gradual growth at an average annual rate of 7.74%, and the monthly prediction results reveal distinct fluctuation patterns in the growth.     

Path flow estimator for planning applications in small communities

This paper presents an alternative planning framework to model and forecast network traffic for planning applications in small communities, where limited resources debilitate the development and applications of the conventional four-step travel demand forecasting model. The core idea is to use the Path Flow Estimator (PFE) to estimate current and forecast future traffic demand while taking into account of various field and planning data as modeling constraints. Specifically, two versions of PFE are developed: a base year PFE for estimating the current network traffic conditions using field data and planning data, if available, and a future year PFE for predicting future network traffic conditions using forecast planning data and the estimated base year origin–destination trip table as constraints. In the absence of travel survey data, the proposed method uses similar data (traffic counts and land use data) as a four-step model for model development and calibration. Since the Institute of Transportation Engineers (ITE) trip generation rates and Highway Capacity Manual (HCM) are both utilized in the modeling process, the analysis scope and results are consistent with those of common traffic impact studies and other short-range, localized transportation improvement programs. Solution algorithms are also developed to solve the two PFE models and integrated into a GIS-based software called Visual PFE. For proof of concept, two case studies in northern California are performed to demonstrate how the tool can be used in practice. The first case study is a small community of St. Helena, where the city’s planning department has neither an existing travel demand model nor the budget for developing a full four-step model. The second case study is in the city of Eureka, where there is a four-step model developed for the Humboldt County that can be used for comparison. The results show that the proposed approach is applicable for small communities with limited resources.     

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.

     

A bayesian dynamic linear model approach for real-time short-term freeway travel time prediction

This paper presents a Bayesian inference-based dynamic linear model (DLM) to predict online short-term travel time on a freeway stretch. The proposed method considers the predicted freeway travel time as the sum of the median of historical travel times, time-varying random variations in travel time, and a model evolution error, where the median is employed to recognize the primary travel time pattern while the variation captures unexpected supply (i.e. capacity) reduction and demand fluctuations. Bayesian forecasting is a learning process that revises sequentially the state of a priori knowledge of travel time based on newly available information. The prediction result is a posterior travel time distribution that can be employed to generate a single-value (typically but not necessarily the mean) travel time as well as a confidence interval representing the uncertainty of travel time prediction. To better track travel time fluctuations during non-recurrent congestion due to unforeseen events (e.g., incidents, accidents, or bad weather), the DLM is integrated into an adaptive control framework that can automatically learn and adjust the system evolution noise level. The experiment results based on the real loop detector data of an I-66 segment in Northern Virginia suggest that the proposed method is able to provide accurate and reliable travel time prediction under both recurrent and non-recurrent traffic conditions.     

Real-time prediction of extreme ambient carbon monoxide concentrations due to vehicular exhaust emissions using univariate linear stochastic models

Historical data of the time-series of carbon monoxide (CO) concentration was analysed using Box–Jenkins modelling approach. Univariate Linear Stochastic Models (ULSMs) were developed to examine the degree of prediction possible for situations where only a limited data set, restricted only to the past record of pollutant data are available. The developed models can be used to provide short-term, real-time forecast of extreme CO concentrations for an Air Quality Control Region (AQCR), comprising a major traffic intersection in a Central Business District of Delhi City, India.     

Forecasting demand for high speed rail

It is sometimes argued that standard state-of-practice logit-based models cannot forecast the demand for substantially reduced travel times, for instance due to High Speed Rail (HSR). The present paper investigates this issue by reviewing the literature on travel time elasticities for long distance rail travel and comparing these with elasticities observed when new HSR lines have opened. This paper also validates the Swedish long distance model, Sampers, and its forecast demand for a proposed new HSR, using aggregate data revealing how the air–rail modal split varies with the difference in generalized travel time between rail and air. The Sampers long distance model is also compared to a newly developed model applying Box–Cox transformations. The paper contributes to the empirical literature on long distance travel, long distance elasticities and HSR passenger demand forecasts. Results indicate that the Sampers model is indeed able to predict the demand for HSR reasonably well. The new non-linear model has even better model fit and also slightly higher elasticities.     

基于桥梁挠度长期监测值的动态预测

文章针对重庆高家花园嘉陵江大桥实时健康监测系统的挠度长期监测数据,根据监测信息的时间序列呈季节、循环等非平稳状态特点,介绍采用ARMA时间序列预测模型,对挠度监测数据中所包含的外荷载的变化趋势及结构抗力的衰变信息进行动态预测,同时建立了结构外效应的预测函数。结果表明,采用低阶模型能对挠度监测值进行较好的动态预测。     

The treatment of uncertainty in the dynamic origin–destination estimation problem using a fuzzy approach

Regardless of existing types of transportation and traffic model and their applications, the essential input to these models is travel demand, which is usually described using origin–destination (OD) matrices. Due to the high cost and time required for the direct development of such matrices, they are sometimes estimated indirectly from traffic measurements recorded from the transportation network. Based on an assumed demand profile, OD estimation problems can be categorized into static or dynamic groups. Dynamic OD demand provides valuable information on the within-day fluctuation of traffic, which can be employed to analyse congestion dissipation. In addition, OD estimates are essential inputs to dynamic traffic assignment (DTA) models. This study presents a fuzzy approach to dynamic OD estimation problems. The problems are approached using a two-level model in which demand is estimated in the upper level and the lower level performs DTA via traffic simulation. Using fuzzy rules and the fuzzy C-Mean clustering approach, the proposed method treats uncertainty in historical OD demand and observed link counts. The approach employs expert knowledge to model fitted link counts and to set boundaries for the optimization problem by defining functions in the fuzzification process. The same operation is performed on the simulation outputs, and the entire process enables different types of optimization algorithm to be employed. The Box-complex method is utilized as an optimization algorithm in the implementation of the approach. Empirical case studies are performed on two networks to evaluate the validity and accuracy of the approach. The study results for a synthetic network and a real network demonstrate the robust performance of the proposed method even when using low-quality historical demand data.