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. Overall, it is shown that ARIMA models are more sensitive to the percentage of missing data than neural networks in this context.
This is an author produced version of an article published in Accident and Analysis Journal. It has been peer reviewed but does not contain the publishers formatting or pagination.
AbstractThis paper reports on the development of a method for automatic monitoring of safety at Pelican crossings. Historically, safety monitoring has typically been carried out using accident data, though given the rarity of such events it is difficult to quickly detect change in accident risk at a particular site. An alternative indicator sometimes used is traffic conflicts, though this data can be time consuming and expensive to collect. The method developed in this paper uses vehicle speeds and decelerations collected using standard in-situ loops and tubes, to determine conflicts using vehicle decelerations and to assess the possibility of automatic safety monitoring at Pelican crossings. Information on signal settings, driver crossing behaviour, pedestrian crossing behaviour and delays, and pedestrian-vehicle conflicts was collected synchronously through a combination of direct observation, video analysis, and analysis of output from tube and loop detectors. Models were developed to predict safety, i.e. pedestrian-vehicle conflicts using vehicle speeds and decelerations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.