New approaches to transportation forecasting models

In 1992, the Federal Highway Administration awarded small research contracts to four teams of transportation researchers to design alternative approaches for improving the urban travel demand forecasting process. The purpose of these contracts was to enable each research team to explain how transportation planning models could and should be improved to meet the new forecasting requirements brought on by recent legislation, to address the impacts of new transportation technology, and to exploit the travel behavior theories and methodologies that have developed over the past two decades.This paper presents a summary and synthesis of the ideas which emerged from the four research reports. Its purpose is to identify common themes suggested by several of the research teams, to point out what appear to be critical elements missing from some approaches, and to combine the best aspects of the four approaches into a research plan for improving the current generation of travel demand models.Abbreviations CAAA Clean Air Act Amendments - FHWA Federal Highway Administration - GIS Geographic Information System - IIA Independence of Irrelevant Alternatives - IT Information Technology - IVHS Intelligent Vehicle Highway System - SUE Stochastic User Equilibrium - TCM Transportation Control Measures - UTPS Urban Transportation Planning System - VMT Vehicle Miles of Travel The paper was prepared as a report for the Federal Highway Administration.     

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).     

The usefulness of the Sequence Alignment Methods in validating rule-based activity-based forecasting models

This research paper aims at achieving a better understanding of rule-based activity-based models, by proposing a new level of validation at the process model level in the A Learning-based Transportation Oriented Simulation System (ALBATROSS) model. To that effect, the work activity process model, which includes six decision steps, has been investigated. Each decision step is evaluated during the prediction of the individuals?? schedules. There are specific decision steps that affect the execution pattern of the work activity process model. So, the comportment of execution in the process model contains activation dependency. This branches the execution and evaluation of each agent under examination. Sequence Alignment Methods (SAM) can be used to evaluate how similar/dissimilar the predicted and observed decision sequences are on an agent level. The original Chi-squared Automatic Interaction Detector decision trees at each decision step utilized in ALBATROSS are compared with other well known induction methods chosen to appraise the purpose of the analyses. The models are validated at four levels: the classifier or decision step level whereby confusion matrix statistics are used; The work activity trips Origin?CDestination matrix level; the time of day work activity start time level, using a correlation coefficient; and the process model level, using SAM. The results of validation on the proposed process model level show conformity to all validation levels. In addition, the results provide additional information in better understanding the process model??s behavior. Hence, introducing a new level of validation incur new knowledge and assess the predictive performance of rule-based activity-based models. And assist in identifying critical decision steps in the work activity process model.     

On the development of time period and mode choice models for use in large scale modelling forecasting systems

A substantial amount of research is presently being carried out to understand the complexities involved in modelling the choice of departure time and mode of travel. Many of these models tend to be far too complex and far too data intensive to be of use for application in large scale model forecasting systems, where socio-economic detail is limited and detailed scheduling information is rarely available in the model implementation structure. Therefore, these models generally work on the basis of a set of mutually exclusive time periods, rather than making use of continuous departure time information. Two important questions need to be addressed in the use of such models, namely the specification used for the time periods (in terms of length), and the ordering of the levels of nesting, representing the difference in the sensitivities to shifts in departure time and changes in the mode of travel. This paper aims to provide some answers to these two questions on the basis of an extensive analysis making use of three separate Stated Preference (SP) datasets, collected in the United Kingdom and in the Netherlands. In the analysis, it has proved possible to develop models which allow reasonably sound predictions to be made of these choices. With a few exceptions, the results show higher substitution between alternative time periods than between alternative modes. Furthermore, the results show that the degree of substitution between time periods is reduced when making use of a more coarse specification of the time periods. These results are intended for use by practitioners, and form an important part of the evidence base supporting the UK Department for Transport’s advice for practical UK studies in the WebTAG system.¹     

Micro-simulation of daily activity-travel patterns for travel demand forecasting

The development and initial validation results of a micro-simulator for the generation of daily activity-travel patterns are presented in this paper. The simulator assumes a sequential history and time-of-day dependent structure. Its components are developed based on a decomposition of a daily activity-travel pattern into components to which certain aspects of observed activity-travel behavior correspond, thus establishing a link between mathematical models and observational data. Each of the model components is relatively simple and is estimated using commonly adopted estimation methods and existing data sets. A computer code has been developed and daily travel patterns have been generated by Monte Carlo simulation. Study results show that individuals' daily travel patterns can be synthesized in a practical manner by micro-simulation. Results of validation analyses suggest that properly representing rigidities in daily schedules is important in simulating daily travel patterns. This revised version was published online in June 2006 with corrections to the Cover Date.     

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.     

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.     

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.     

VMT, energy consumption, and GHG emissions forecasting for passenger transportation

Globalization, greenhouse gas emissions and energy concerns, emerging vehicle technologies, and improved statistical modeling capabilities make the present moment an opportune time to revisit aggregate vehicle miles traveled (VMT), energy consumption, and greenhouse gas (GHG) emissions forecasting for passenger transportation. Using panel data for the 48 continental states during the period 1998-2008, the authors develop simultaneous equation models for predicting VMT on different road functional classes and examine how different technological solutions and changes in fuel prices can affect passenger VMT. Moreover, a random coefficient panel data model is developed to estimate the influence of various factors (such as demographics, socioeconomic variables, fuel tax, and capacity) on the total amount of passenger VMT in the United States. To assess the influence of each significant factor on VMT, elasticities are estimated. Further, the authors investigate the effect of different policies governing fuel tax and population density on future energy consumption and GHG emissions. The presented methodology and estimation results can assist transportation planners and policy-makers in determining future energy and transportation infrastructure investment needs.     

A real time forecasting tool for dynamic travel time from clustered time series

This paper addresses the problem of dynamic travel time (DTT) forecasting within highway traffic networks using speed measurements. Definitions, computational details and properties in the construction of DTT are provided. DTT is dynamically clustered using a K-means algorithm and then information on the level and the trend of the centroid of the clusters is used to devise a predictor computationally simple to be implemented. To take into account the lack of information in the cluster assignment for the new predicted values, a weighted average fusion based on a similarity measurement is proposed to combine the predictions of each model. The algorithm is deployed in a real time application and the performance is evaluated using real traffic data from the South Ring of the Grenoble city in France.     

Coordinated scheduling models for allied airlines

Recently, as a means of forming global networks and improving operation efficiency, major air carriers have increasingly entered into alliances with other carriers. Fleet routing and flight scheduling are not only important in individual airline operations, but also affect the alliances. The setting of a good flight schedule can not only enhance allied airline operating performance, but can also be a useful reference for alliance decision-making. In this research, we develop several coordinated scheduling models, which will help the allied airlines solve for the most satisfactory fleet routes and timetables under the alliance. We employ network flow techniques to construct the models. The models are formulated as multiple commodity network flow problems which can be solved using a mathematical programming solver. Finally, to evaluate the models, we perform a case study based on real operating data from two Taiwan airlines. The preliminary results are good, showing that the models could be useful for airline alliances.     

Defining domains for models of travel demand

Travel demand models implicitly assume that people respond to changes in a continuous way. This is in contrast to the physical sciences, where discontinuous response is a common phenomenon and is embodied in such concepts as sub-critical and supercritical states.Recent studies have shown that responses to transport policies differ in degree and kind according to the nature and severity of the stimulus and the types of people affected. Response patterns may be categorised by the extent to which they involve adjustments to spatio-temporal or inter-personal linkages. This paper identifies four response domains, with a further distinction between permissive and forced changes.Most travel demand models are designed to operate within an independent, forced (and to a less extent independent permissive) domain and their forecasts become unreliable when responses lie outside that domain. Conversely, a model designed for a more complex domain is unnecessarily cumbersome where simpler responses apply. This paper describes the types of model which are appropriate for each domain and discusses how the effects of a policy may be assigned to the correct domain(s).     

Mathematical programming models for airport site selection

Three mathematical programming models are developed in this paper, using different criteria, for the airport site selection problem in developing countries. Estimation of parameters, based on Turkish data, and the sensitivity analyses are presented. The first is a typical set covering model used to determine the minimum number of airports required for a given population of passengers. The other two are location-allocation type models used to find the optimal airport location patterns, the number of passengers to be bussed to cities having airports, and the optimal frequencies of transportation modes between the city pairs.     

Goodness-of-fit measures for probabilistic travel demand models

This paper is concerned with the assessment of the goodness-of-fit of nonlinear models of the type currently being used in the development of the disaggregate, behavioral travel demand approach. These models are emerging as a potential new technique for many transportation planning problems, although much research is yet needed before they are sufficiently developed for operational use. In order to pursue the necessary research, and also for the later assessment of operational models, it is necessary to have adequate measures of the goodness-of-fit.The paper examines the adequacy of standard measures of goodness-of-fit as applied to any nonlinear estimating equation and they are found to be inappropriate and inadequate. A little-known statistic, called the correlation ratio, is then defined and derived, and is explored as a substitute for the standard measures. In both theoretical and empirical tests, the correlation ratio is found to be a significantly more useful and appropriate measure of goodness-of-fit.Some further properties of the correlation ratio are examined, and the ratio is found to possess some degree of arbitrariness when applied to typical travel demand models. This arbitrariness, however, only impairs the usefulness of the correlation ratio in the absolute assessment of a model, but not for the comparative assessment of two or more models. Finally, a number of research tasks, relating to the correlation ratio, are identified.     

岩爆预测及防治方法综述

岩爆是一种地质灾害,极大地威胁着地下工程施工人员和设备的安全.文章主要介绍了岩爆预测及防治方面的理论研究和实践探索的部分成果,可供地下工程设计和施工人员参考.     

Application of time series techniques for forecasting truck traffic attracted by the Bombay metropolitan region

Knowledge of future traffic flow is an essential input in the planning, implementation and development of a transportation system. It also helps in its operation, management and control. Time series analysis techniques have been extensively adopted for this purpose in the fields of economics, social sciences and in other fields of technology. An attempt has been made in this study to apply the techniques of time series analysis to goods traffic, particularly truck traffic. Four predominant corridors, N.H.3, N.H.4, N.H.8 and Lal Bahadur Shastri Road (L.B. S. Rd.), accounting for majority of truck movement in the Bombay Metropolitan Region (BMR), have been considered for modeling. Raw data was processed initially, to obtain an insight into the structure of time series. Ten candidate models of the Auto-Regressive Moving Average (ARMA) and Auto-Regressive Integrated Moving Average (ARIMA) family are investigated to represent each of the four corridors. Models finally proposed, to represent each of the four corridors have been selected based on Minimum Mean Square Error (MMSE) and Maximum Likelihood Rule (MLR) criteria. Models ARIMA (2, 1, 0), ARMA (1.0), ARMA (1, 1) and ARIMA (1, 1, 0) are proposed for N.H.3, N.H.4, N.H.8 and L.B.S. Rd. respectively, based on significant weekly periodicity.     

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.

The digital revolution and worthwhile use of travel time: implications for appraisal and forecasting

Savings in travel time and more specifically their monetary value typically constitute the main benefit to justify major investment in transport schemes. However, worthwhile use of travel time is an increasingly prominent phenomenon of the digital age. Accordingly, questions are increasingly being asked regarding whether values of time used by countries around the world based on their appraisal approaches are too high. This paper offers the most comprehensive examination of our theoretical and empirical understandings of international appraisal approaches and how they account for worthwhile use of travel time. It combines the economics perspective with wider social science insight and reaches the conclusion that past revolutions in transport that have made longer and quicker journeys possible are now joined by a digital revolution that is reducing the disutility of travel time. This revolution offers potential economic benefit that comes at a fraction of the cost of major investments in transport that are predicated on saving travel time. The paper highlights the challenges faced in both current and indeed potential alternative future appraisal approaches. Such challenges are rooted in the difficulty of measuring time use and productivity with sufficient accuracy and over time to credibly account for how travel time factors into the economic outcomes from social and working practices in the knowledge economy. There is a need for further research to: establish how improvements in the opportunities for and the quality of worthwhile use of travel time impact on the valuation of travel time savings for non-business travel; improve our understanding of how productive use of time impacts on the valuation of time savings for business travellers; and estimate how these factors have impacted on the demand for different modes of travel.