A neural network model for enhanced operation of midblock signalled pedestrian crossings
Lyons, Glenn, Hunt, John and McLeod, Fraser (2001) A neural network model for enhanced operation of midblock signalled pedestrian crossings. European Journal of Operational Research, 129, (2), 346-354. (doi:10.1016/S0377-2217(00)00232-0).
Full text not available from this repository.
UK transport policy has shifted dramatically in recent years. The new policy direction to promote walking as an alternative to car for short trips. previous termMidblock signalled pedestrian crossings are anext term common method of resolving the conflict between previous termpedestriansnext term and vehicles. This paper considers alternative operating strategies for previous termmidblock signalled pedestrian crossingsnext term that are more responsive to the needs of previous termpedestriansnext term without increasing the delay to motorists and freight traffic. previous termAnext term succession of artificial previous termneural networknext term (ANN) previous termmodelsnext term is developed and factors influencing the performance of previous termpedestriannext term gap acceptance previous termmodelsnext term both in terms of accuracy and processing requirements are considered in detail. The paper concludes that previous termanext term feedforward ANN using backpropagation can deliver previous termanext term gap acceptance previous termmodel with anext term high degree of accuracy with acceptable constraints.
|Digital Object Identifier (DOI):||doi:10.1016/S0377-2217(00)00232-0|
|Keywords:||pedestrians, neural networksnext term|
|Subjects:||H Social Sciences > HE Transportation and Communications
T Technology > TE Highway engineering. Roads and pavements
B Philosophy. Psychology. Religion > BF Psychology
|Divisions :||University Structure - Pre August 2011 > School of Civil Engineering and the Environment
|Accepted Date and Publication Date:||
|Date Deposited:||22 Jul 2008|
|Last Modified:||06 Aug 2015 02:43|
|RDF:||RDF+N-Triples, RDF+N3, RDF+XML, Browse.|
Actions (login required)