Howard R. Kirby

SHOULD WE USE NEURAL NETWORKS OR STATISTICAL MODELS FOR SHORT-TERM MOTORWAY TRAFFIC FORECASTING?

This paper discusses conceptual and practical advantages and disadvantages of neural networks and time series methods in forecasting traffic. It then summarizes the findings from empirical investigations on motorway traffic.

Recent advances and applications in the field of short-term traffic forecasting

Frequent road traffic congestion is now a global issue. One of the proposed solutions to this problem is dynamic traffic management (DTM): the management of traffic flows, vehicles and traffic demand based on data representing the current and near expected traffic situation. A key ingredient for DTM is accurate network-wide short-term traffic forecasts. This article gives a general overview of the state of the art together with some recent advances and applications derived from a number of field trials conducted as part of the DRIVE-II programme of the Commission of the European Communities. The article gives an introduction to DTM, and reviews the nature of traffic demand and supply and the traffic measurement process. The statistical methodology of short-term forecasts applied in transport is discussed and the articles in this issue are introduced. Mention is made of as yet unresolved problems. The article concludes that a great deal of work still remains to be done before the current methodology can consistently provide the desired level of accuracy needed for DTM. In the near future, more research will be needed and carried out, both with respect to methods already available, to methods available but not yet applied and perhaps to develop new methodology.

Vehicle classification by acoustic signature

The aim of this research is to investigate the feasibility of developing a traffic monitoring detector for the purpose of reliable on-line vehicle classification to aid traffic management systems. The detector used was a directional microphone connected to a DAT (Digital Audio Tape) recorder. The digital signal was preprocessed by LPC (Linear Predictive Coding) parameter conversion based on autocorrelation analysis. A Time Delay Neural Network (TDNN) was chosen to classify individual travelling vehicles based on their speed-independent acoustic signature. The paper provides a description of the TDNN architecture and training algorithm, and an overview of the LPC preprocessing and feature extraction technique as applied to audio monitoring of road traffic. The performance of TDNN vehicle classification, convergence, and accuracy for the training patterns are fully illustrated. To establish the viability of this classification approach, initially, recordings were carried out on a strip of airfield for four types of vehicles under controlled conditions. A TDNN network was successfully trained with 100% accuracy in classification for the training patterns, as well as the test patterns. The net was also robust to changes in the starting position of the acoustic waveforms with 86% accuracy for the same test data set. In the second phase of the experiment, roadside recordings were made at a two-way urban road site in the city of Leeds with no control over the environmental parameters such as background noise, interference from other travelling vehicles, or the speed of the recorded vehicle. A second TDNN network was also successfully trained with 96% accuracy for the training patterns and 84% accuracy for the test patterns.

THE MEASUREMENT OF VEHICULAR DRIVING CYCLE WITHIN THE CITY OF EDINBURGH

In this paper, the development of a driving cycle for the urban area of the city of Edinburgh is presented. The driving cycle was obtained from recorded data in actual traffic conditions, using the car chase technique. A new statistical method of analysing the recorded data was developed. The proposed TRAffic Flow IndeX (TRAFIX) enables the calculation of a representative driving cycle from the various measurements undertaken during two stages of experiments. Data from the City of Edinburgh Council traffic monitoring stations were weighted in proportion to traffic flows on the constituent driving routes. A comparison between the European ECE cycle and the presently proposed Edinburgh driving cycle (EDC) has also been made.

A FIELD TRIAL OF ACOUSTIC SIGNATURE ANALYSIS FOR VEHICLE CLASSIFICATION

The aim of this research is to investigate the feasibility of developing a traffic monitoring detector for the purpose of reliable on-line vehicle classification to aid traffic management systems. The detector used was a directional microphone connected to a DAT (Digital Audio Tape) recorder. The digital signal was pre-processed by LPC (Linear Predictive Coding) parameter conversion based on autocorrelation analysis. A Time Delay Neural Network (TDNN) was chosen to classify individual travelling vehicles based on their speed-independent acoustic signature. Locations for data acquisition included roadside recordings at a number of two-way urban road sites in the city of Leeds with no control over the environmental parameters such as background noise, interference from other travelling vehicles or the speed of the recorded vehicles. The results and performance analysis of TDNN vehicle classification, the convergence for training patterns and accuracy of test patterns are fully illustrated. The paper also provides a description of the TDNN architecture and training algorithm, and an overview of the LPC pre-processing and feature extraction technique as applied to audio monitoring of road traffic. In the final phase of the experiment, the four broad categorisations of vehicles for training the network consisted of: buses or lorries; small or large saloons; various types of motorcycles; and light goods vehicles or vans. A TDNN network was successfully trained with 94% accuracy for the training patterns and 82.4% accuracy for the test patterns.

A review of vehicular emission models and driving cycles

Abstract This article reviews the latest and relevant work on both vehicular emission models and driving cycles. The three main types of emission models, namely emission factor models, average speed models and modal models, are covered. Each project is analysed regarding its characteristic parameters, such as data collection technique, methodology, statistical analysis and pollutants covered, where appropriate. Other parameters were taken into account, such as the project objectives, results and relevance regarding the wider spectrum of the road traffic situation.

The use of geographical information systems to enhance road safety analysis

The use of Geographic Information Systems (GIS) in road safety analysis has increased rapidly in recent years. They have proved to be effective in answering simple accident enquiries and identifying single sites with a high number of accidents; however, this nowhere near represents their full potential. This paper describes a number of additional applications that make use of a GIS and include methods to better identify mistakes in the police accident report forms, improve the selection of routes and areas suitable for remedial treatment, provide additional information on the safety of school based journeys and identify the home location of road accident casualties. These improvements in the quantity and quality of information should lead to a more accurate and efficient selection of engineering measures and road safety campaigns.

Modelling the effects of transport policy levers on fuel efficiency and national fuel consumption

The paper provides an overview of the main features of a Vehicle Market Model (VMM) which estimates changes to vehicle stock/kilometrage, fuel consumed and CO2 emitted. It is disaggregated into four basic vehicle types. The model includes: the trends in fuel consumption of new cars, including the role of fuel price; a sub-model to estimate the fuel consumption of vehicles on roads characterised by user-defined driving cycle regimes; procedures that reflect distribution of traffic across different area/road types; and the ability to vary the speed (or driving cycle) from one year to another, or as a result of traffic growth. The most significant variable influencing fuel consumption of vehicles was consumption in the previous year, followed by dummy variables related to engine size, the time trend (a proxy for technological improvements), and then fuel price. Indeed the effect of fuel price on car fuel efficiency was observed to be insignificant (at the 95% level) in two of the three versions of the model, and the size of fuel price term was also the smallest. This suggests that the effectiveness of using fuel prices as a direct policy tool to reduce fuel consumption may be limited. Fuel prices may have significant indirect impacts (such as influencing people to purchase more fuel efficient cars and vehicle manufacturers to invest in developing fuel efficient technology) as may other factors such as the threat of legislation.

The effects of detector spacing on traffic forecasting performance using neural networks

An investigation was made as to how short-term traffic forecasting on motorways and other trunk roads is related to the density of detectors. Forecasting performances with respect to different detector spaces have been investigated with both simulated data and real data. Pruning techniques to the input variables used for neural networks were applied to the simulated data. The real data were collected from the M25 motorway and included flow, speed, and occupancy. With the data used in our study, the forecasting performances decrease with the increase of detector spaces. However, by taking the assumed costs of detector infrastructure into account, it may be concluded from this study that increasing coverage to a spacing of 500 m gives little extra benefit and may actually be counter productive in certain circumstances. It was concluded that, on the basis of current evidence, a detector spacing of between 1 and 1.5 km might be optimal.

Prospects for progressing research through partnership : Comment on trends in the United Kingdom and the technology foresight program

The mechanisms that have been developed in recent years in the United Kingdom to encourage partnerships in research among government, industry, and the research community in universities and elsewhere are reviewed. The influence of the 1993 White Paper on Science, Engineering, and Technology, the development of the recent technology foresight exercise, and the processes and outcomes of that exercise are reviewed. The implications for the transport sector and the treatment of issues generic to several sectors are summarized. Some anomalies are noted in the development of the partnership theme, and questions are raised as to whether and how the cultural change desired by government is to be progressed further.