TY - GEN
T1 - Feature selection with genetic algorithms for accident duration forecasting on freeway
AU - Lee, Ying
AU - Wei, Chien Hung
PY - 2007
Y1 - 2007
N2 - This study develops two Artificial Neural Network-based models to provide a sequential forecast of accident duration from the accident notification to the accident site clearance. With these two models, the estimated duration time can be provided by plugging in relevant traffic data as soon as an accident is notified. To select suitable data features, Genetic Algorithm is employed to decrease the number of model inputs while preserving relevant traffic characteristics with fewer inputs. This study shows the proposed models are feasible ones in the Intelligent Transportation Systems (ITS) context.
AB - This study develops two Artificial Neural Network-based models to provide a sequential forecast of accident duration from the accident notification to the accident site clearance. With these two models, the estimated duration time can be provided by plugging in relevant traffic data as soon as an accident is notified. To select suitable data features, Genetic Algorithm is employed to decrease the number of model inputs while preserving relevant traffic characteristics with fewer inputs. This study shows the proposed models are feasible ones in the Intelligent Transportation Systems (ITS) context.
UR - http://www.scopus.com/inward/record.url?scp=84893806304&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84893806304&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84893806304
SN - 9781617387777
T3 - 14th World Congress on Intelligent Transport Systems, ITS 2007
SP - 3773
EP - 3780
BT - 14th World Congress on Intelligent Transport Systems, ITS 2007
PB - Intelligent Transportation Society of Japan (ITS Japan)
T2 - 14th World Congress on Intelligent Transport Systems, ITS 2007
Y2 - 9 October 2007 through 13 October 2007
ER -