A neural network model for enhanced operation of midblock signalled pedestrian crossings

UK transport policy has shifted dramatically in recent years. The new policy direction is to promote walking as an alternative to car for short trips. Midblock signalled pedestrian crossings are a common method of resolving the conflict between pedestrians and vehicles. This paper considers alternative operating strategies for midblock signalled pedestrian crossings that are more responsive to the needs of pedestrians without increasing the delay to motorists and freight traffic. A succession of artificial neural network (ANN) models is developed and factors influencing the performance of pedestrian gap acceptance models both in terms of accuracy and processing requirements are considered in detail. The paper concludes that a feedforward ANN using backpropagation can deliver a gap acceptance model with a high degree of accuracy with acceptable constraints.