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.     

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.     

A model for forecasting public transit

This study develops a model that explains public transit ridership in Orange Country, California over quarterly periods during the 1974–1988 period. The model uses a Cobb-Douglas functional form and a Cochrane-Orcutt iterative procedure to measure the association between public transit ridership and the potential number of users, relative level of public transit service, relative price of public transit, seasonality, and external shocks. Relative measures of the explanatory variables are used to reduce the potential for multicollinearity and give greater confidence in the reliability of the estimated elasticities. The model is then used to prepare conditional quarterly forecasts for ridership in 1988 and unconditional quarterly forecasts during the 1989–1993 period.     

The future of trucking technology in Brazil: results of a technology forecasting model

Abstract

The aim of this article is to identify a set of technological events related to the Brazilian truck fleet that are well placed hierarchically regarding their possibility of occurrence and pertinence for the horizon year of 2021. For this we propose and apply a Technology Forecasting Model for trucks (called TFM/Trucks) based on the Delphi technique, considering 28 technological events associated with six internal forecasting dimensions: safety, efficient use of energy and alternative fuels, materials technology, operational schemes, comfort and environment. The ranking of the technological events, considering hypothetical situations for analysis, indicate significant concern over the safety dimension, with four of the five events (passive safety and active safety) classified among the 10 events with the greatest chance of occurring and pertinence, irrespective of the panelists' degree of specialization. The environmental dimension, with respect to the predominance of electric powered trucks with lower level of atmospheric pollutants, was always in one of the first two positions, regardless of the situation studied. In the final ranking, the five best-classified events represented the dimensions of safety, environment, materials technology and comfort, with environment and passive safety predominating.     

A hierarchical decision-process model for forecasting automobile type-choice

This article presents a hierarchical decision model based on interviews with 45 buyers of new 1978 automobiles. The methodology is borrowed from anthropological decision making studies and focuses on the transportation requirements of the car buyer rather than on characteristics of the automobile. Interior car size is found to be the most constraining decision criterion for this group of buyers. The model accounts for 42 of the 45 cases in the sample.     

A hyperpath-based network generalized extreme-value model for route choice under uncertainties

Previous route choice studies treated uncertainties as randomness; however, it is argued that other uncertainties exist beyond random effects. As a general modeling framework for route choice under uncertainties, this paper presents a model of route choice that incorporates hyperpath and network generalized extreme-value-based link choice models. Accounting for the travel time uncertainty, numerical studies of specified models within the proposed framework are conducted. The modeling framework may be helpful in various research contexts dealing with both randomness and other non-probabilistic uncertainties that cannot be exactly perceived.     

A self-learning advanced booking model for railway arrival forecasting

Accurate short-term arrival forecasting is essential information for railway operators to conduct daily operations such as demand management strategies. Conventional time series methods apply historical arrival data which is the accumulation of reservations to project future arrivals. This study aims to utilize reservation data directly and proposes a novel advanced booking model by using the framework of case-based reasoning. The proposed model contains four modules with distinctive functions for similarity evaluation, instance selection, arrival projection, and parameter search. We have the constructed model tested on fourteen daily arrival series and compared its out-of-sample accuracy with that of four traditional benchmarks. The empirical results show that in average the proposed self-learning model may reduce at least 11% of mean square errors (MSE). Moreover, the learning scheme in the model may achieve significant reduction of MSE comparing with performance of other naïve versions.     

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.     

A model to design a national high-speed rail network for freight distribution

High-speed rail is often touted as a means to reduce congestion on the United States’ highways by removing passenger car traffic. But highway congestion can also be reduced by reducing the amount of freight traffic. So, given the advances in high-speed rail, the potential exists for developing a national high-speed network for freight distribution. To design such a network considering highway traffic and transit times, we present an uncapacitated network design model with a post-processing step for the capacity constraint. To illustrate how our modeling approach could be used by policy makers to evaluate the impacts of a high-speed rail network, we apply our models with preliminary data on high-speed rail operating parameters for freight applications and from current data on shipments from a major truckload carrier and the US Census Bureau.     

A new schedule-based transit assignment model with travel strategies and supply uncertainties

This paper proposes a new scheduled-based transit assignment model. Unlike other schedule-based models in the literature, we consider supply uncertainties and assume that users adopt strategies to travel from their origins to their destinations. We present an analytical formulation to ensure that on-board passengers continuing to the next stop have priority and waiting passengers are loaded on a first-come-first-serve basis. We propose an analytical model that captures the stochastic nature of the transit schedules and in-vehicle travel times due to road conditions, incidents, or adverse weather. We adopt a mean variance approach that can consider the covariance of travel time between links in a space–time graph but still lead to a robust transit network loading procedure when optimal strategies are adopted. The proposed model is formulated as a user equilibrium problem and solved by an MSA-type algorithm. Numerical results are reported to show the effects of supply uncertainties on the travel strategies and departure times of passengers.     

Quantifying errors in micro-scale emissions models using a case-study approach

To quantify the level of uncertainty attached to forecasts of CO₂ emissions, an analysis of errors is undertaken; looking at both errors inherent in the model structure and the uncertainties in the input data. Both error types are treated in relation to CO₂ emissions modelling using a case-study from Brisbane, Australia. To estimate input data uncertainty, an analysis of traffic conditions using Monte Carlo simulation is used. Model structure induced uncertainties are also quantified by statistical analysis for a number of traffic scenarios. To arrive at an optimal overall CO₂ prediction, the interaction between the two components is taken into account. Since a more complex model does not necessarily yield higher overall accuracy, a compromise solution is found. The results suggest that the CO₂ model used in the analysis produces low overall uncertainty under free flow traffic conditions. When average traffic speeds approach congested conditions, however, there are significant errors associated with emissions estimates.     

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.     

The reliability of using the gravity model for forecasting trip distribution

The main purpose of this study is to assess the forecasting capability of the gravity model and to investigate the merit of including K-factors when using the model. Peak hour trip data was obtained for four study year periods 1962, 1971, 1976 and 1981 for the City of Winnipeg. Analysis of the calibration results indicated that the F-factors for the twenty year period were stable within a range of values. In general, however, the K-factors were found to be inconsistent from one prediction period to the next, and when used in forecasting trips they resulted in larger errors than without their use. The validity of using K-factors or the method which has been used to determine them is questionable. It was concluded that while K-factors are very meaningful in theory (as defined), they are not appropriate for use in predicting O-D matrices based on the method by which they are currently estimated (i.e. as a simple ratio). Further study is needed to investigate an alternative method of calibrating the gravity model such as the cell-by-cell regression method.     

Quantifying the effects of input aggregation and model randomness on regional transportation emission inventories

Accurate road-traffic emission inventories are of great interest to metropolitan planning agencies especially in the appraisal of regional transport policies. Integrated road transport emission models are an effective means of establishing emission estimates, yet their development requires significant investments in data and resources. It is therefore important to investigate which data inputs are the most critical to inventory accuracy. To address this issue, an integrated transport and emissions model is developed using the Montreal metropolitan region as a case-study. Daily regional hydrocarbon (HC) emissions from private individual travel are estimated, including the excess emissions due to engine starts. The sensitivity of emission estimates is then evaluated by testing various levels of input aggregation common in practice and in previous research. The evaluated inputs include the effect of start emissions, ambient weather conditions, traffic speed, path choice, and vehicle registry information. Inherent randomness within the integrated model through vehicle selection and path allocation is also evaluated. The inclusion of start emissions is observed to have the largest impact on emission inventories, contributing approximately 67 % of total on-road HC emissions. Ambient weather conditions (season) and vehicle registry data (types, model years) are also found to be significant. Model randomness had a minimal effect in comparison with the impact of other variables.     

灰色BP网络串联式组合模型在铁路客货运输量预测中的应用

针对铁路客货运输量发展趋势的研究,建立一种基于灰色理论和BP神经网络的串联式组合预测模型。该模型首先用同一组数据序列建立不同参数的灰色方程,然后用各灰色方程分别预测,最后将各灰色方程预测的结果进行BP神经网络非线性组合,形成串联式组合预测模型。对湖南省铁路客货运量进行分析预测,结果表明:该组合模型预测的准确性高于单独使用灰色模型的准确性,是一种可靠有效的预测方法。     

The geographical stability of a typical trip production model: Applications of national and local data in four urban areas

Estimates of the numbers of trips likely to be made by individuals and of the modes of transport that will be available to them for those trips are provided by the trip production model. The objective of the work described in this paper was to investigate the geographical stability of the trip production model by comparing the numbers of trips estimated by the model when using national rather than local data. The 1972/3 National Travel Survey was used as the national data. Household interview survey data from the transportation studies of Lincoln, Sheffield/Rotherham, South East Dorset and Bristol were the local data sources. Three home based trip purposes are modelled; 24 hour work, 24 hour shop, 24 hour other.The models calibrated from national and local data perform similarly provided both operate with local trip rates. The car ownership sub-model with national parameters produces similar forecasts to the models with local parameters. There are probably real differences in household trip rates for some trip purposes between urban areas.     

Quantifying traveler information provision in dynamic heterogeneous traffic networks

Information is effectively the same as a change in uncertainty perceived by an observer. This paper adopts the strict definition of information from Shannon’s Information Theory and provides procedures for quantifying effective provision of traveler information, considering it to be equivalent to the change of perceived uncertainty. The proposed method combines a cognitive grouping theory and an information learning scheme at an individual’s level to evaluate the dynamic information provision in the unit of a bit. Such numerical quantification can be meaningful in evaluating alternatives with more fine-grained information provision strategies and understanding their equity impact. Quantifying information in a manner consistent with Information Theory also provides a ‘shared language’ that facilitates more constructive discussion among stakeholders from different backgrounds. The case study is conducted on a heterogeneous dynamic traffic network near Downtown Los Angeles for evaluating different alternatives of a proposed dynamic message board in terms of its location and dynamic content.     

总承包模式下的柬埔寨某国道改建项目设计方案优化

总承包是目前国际工程项目常用的一种建设模式。通过对国内外工程建设程序和承包建设模式特征的分析,结合柬埔寨某国道改建项目的实践总结,探讨了在国际项目中的总承包模式下,如何在实施阶段通过设计方案的优化来降低工程数量、施工难度及对环境的影响。