Susan Grant-Muller

Use of sequential learning for short-term traffic flow forecasting

Abstract 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and Performance Indicator development, Institute for Transport Studies, University of Leeds Technical Note 418, 1998 (unpublished)] was based on simulated data (generated using a Hermite polynomial with random noise) that had a profile similar to that of traffic flows in real data.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.

Economic appraisal of European transport projects: The state-of-the-art revisited

Substantial investment has been made at national and European level in transport infrastructure over the past 50 years and is likely to continue in the future. The need to appraise transport projects in economic and social terms has developed alongside this in both scope and complexity. The state-of-the-art in the economic appraisal of transport projects is reviewed, progress is assessed and future challenges are identified. The review addresses the general framework, treatment of major impacts, presentation of outputs and issues such as uncertainty. It draws on national practice in Western European countries, which varies substantially reflecting a range of cultural and economic differences. Some points of commonality exist and the principle of monetizing direct transport impacts is generally accepted. Progress has been made towards the measurement of environmental impacts, but the assessment of the wider impacts remains under-developed. Increased sophistication and complexity has brought increasing data...

A STUDY OF HYBRID NEURAL NETWORK APPROACHES AND THE EFFECTS OF MISSING DATA ON TRAFFIC FORECASTING

In this paper we present an application of hybrid neural network approaches and an assessment of the effects of missing data on motorway traffic flow forecasting. Two hybrid approaches are developed using a Self-Organising Map (SOM) to initially classify traffic into different states. The first hybrid approach includes four Auto-Regressive Integrated Moving Average (ARIMA) models, whilst the second uses two Multi-Layer Perception (MLP) models. It was found that the SOM/ARIMA hybrid approach out-performs all individual ARIMA models, whilst the SOM/MLP hybrid approach achieves superior forecasting performance to all models used in this study, including three naïve models. The effects of different proportions of missing data on Neural Network (NN) performance when forecasting traffic flow are assessed and several initial substitution options to replace missing data are discussed. Over-all, it is shown that ARIMA models are more sensitive to the percentage of missing data than neural networks in this context.

Incorporating equity considerations in transport infrastructure evaluation: Current practice and a proposed methodology.

Interest has re-emerged on the issue of how to incorporate equity considerations in the appraisal of transport projects and large road infrastructure projects in particular. This paper offers a way forward in addressing some of the theoretical and practical concerns that have presented difficulties to date in incorporating equity concerns in the appraisal of such projects. Initially an overview of current practice within transport regarding the appraisal of equity considerations in Europe is offered based on an extensive literature review. Acknowledging the value of a framework approach, research towards introducing a theoretical framework is then presented. The proposed framework is based on the well established MCA Analytic Hierarchy Process and is also contrasted with the use of a CBA based approach. The framework outlined here offers an additional support tool to decision makers who will be able to differentiate choices based on their views on specific equity principles and equity types. It also holds the potential to become a valuable tool for evaluators as a result of the option to assess predefined equity perspectives of decision makers against both the project objectives and the estimated project impacts. This framework may also be of further value to evaluators outside transport.

The Role of Tradable Credit Schemes in Road Traffic Congestion Management

Abstract Road traffic congestion is not yet reflected in current market prices within the sector and has given rise to a number of instruments to mitigate the resulting negative impacts. The focus of this paper is the tradable credit scheme — an incentive-based economic measure — in order to address traffic congestion. The research questions are (1) whether the state-of-the-art in the literature suggests that tradable credit schemes could be feasibly introduced to mitigate congestion, and (2) whether a tradable credit scheme could have advantages over other instruments. A brief outline of congestion mitigation approaches is provided first to position this type of economic instrument with respect to other measures. The broad issues in the design of a tradable credit scheme are then presented. Most research to date has focused on the use of tradable credits to manage related pollution, but it is clear there is potential to design a scheme for traffic congestion management. To date this is a novel review of tradable credit schemes that has focused specifically on their role in road traffic congestion management.

Cleaning of Matched License Plate Data

Three methods for identifying outlying journey time observations collected as part of a motorway license plate matching exercise are presented. Each method is examined to ensure that it is comprehensible to transport practitioners, is able to correctly classify outliers, and is efficient in its application. The first method is a crude method based on percentiles. The second uses a mean absolute deviation test. The third method is a modification of a traditional z- or t-statistical test. Results from each method and combinations of methods are compared. The preferred method is judged to be the third method alone, which uses the median rather than the mean as its measure of location and the inter-quartile range rather than the standard deviation as its measure of variability. This method is seen to be robust to both the outliers themselves and the presence of incident conditions. The effectiveness of the method is demonstrated under a number of typical and atypical road traffic conditions. In particular, the method is applied to a different section of motorway and is shown to still produce useful results.

Transport management measures in the post-Olympic Games period: supporting sustainable urban mobility for Beijing?

After decades of rapid economic growth, the municipality of Beijing is now facing serious urban transport challenges with rapid motorization and travel demand growth. Designing and implementing efficient and equitable urban transport policies are essential to achieve the sustainable urban mobility target of the city. The success of transport management around the 2008 Olympic Games has left policymakers with the confidence to develop various efficient policies for congestion mitigation. Following a resume of the characteristics of fast development, this paper investigates the transport management measures used following the Olympic Games. These are analyzed using an ASIF approach within the framework of urban transport sustainability. The policies examined include a priority to develop mass transit systems, small passenger car purchase policy, a staggered peak-hour plan, new charging policies for parking, and traffic restrictions based on license plate numbers. Proposals for enhancing the effectiveness of these policies and recommendations on future policy development are also presented.

A Macroscopic Forecasting Framework for Estimating Socioeconomic and Environmental Performance of Intelligent Transport Highways

The anticipated introduction of new forms of intelligent transport systems (ITS) represents a significant opportunity for increased cooperative mobility and sociotechnical changes within the transport system. Although such technologies are currently technically feasible, various socioeconomic and environmental barriers impede their arrival. This paper uses a recently developed ITS performance assessment framework, i.e., Environmental Fusion (EnvFUSION), to perform dynamic forecasting of the performance for three key ITS technologies: active traffic management (ATM), intelligent speed adaptation (ISA), and an automated highway system (AHS) using a mathematical theory of evidence. A consequential lifecycle assessment (c-LCA) is undertaken, which forms part of a data fusion process using data from various sources. The models forecast improvements for the three ITS technologies in line with social acceptability, economic profitability, and major carbon reduction scenarios up to 2050 on one of the U.K.s most congested highways. An analytical hierarchy process (AHP) and the Dempster-Shafer theory (DST) are used to weight criteria that form part of an intelligent transport sustainability index (ITSI). Overall performance is then synthesized. Results indicate that there will be a substantial increase in socioeconomic and emissions benefits, provided that the policies are in place and targets are reached, which would otherwise delay their realization.

Approaches and Techniques for Modelling CO2 Emissions from Road Transport

Abstract Transport accounts for around a quarter of CO2 emissions globally. Transport modelling provides a useful means to explore the dynamics, scale and magnitude of transport-related emissions. This paper explores the modelling tools available for analysing the emissions of CO2 from transport. Covering a range of techniques from transport microsimulation to global techno-economic models, this review provides insights into the various advantages and shortcomings of these tools. The paper also examines the value of having a broad range of perspectives for analysing emissions from transport. The paper concludes by suggesting that the broad range of models creates a rich environment for exploring a spectrum of policy questions around the emissions from transport, and the potential for combining modelling approaches further enhances the understanding that can be attained.

A Neural Network Approach to Motorway OD Matrix Estimation from Loop Counts

A method has been developed to estimate Origin Destination (OD) matrices using a neural network (NN) model and loop traffic data collected from a UK motorway site (M42) as the primary input. The estimated ODs were validated against matched vehicle number plate data derived from the ANPR (Automatic Number Plate Recognition) cameras which were installed at all the slip roads between junctions 3a and 7 of the motorway. Key research questions were: whether it is realistic to use the full loop data, whether particular features of the data influenced modelling success, whether data transformation could improve modelling performance through variance stabilization and whether individual ODs should be estimated separately or simultaneously. The method has been shown to work well and the best results were obtained using a square root transformation of the training data and individual models for each OD.