Title :
Estimation of trip O-D matrix when input and output are fuzzy
Author :
Nanda, Raman ; Kikuchi, Shinya
Author_Institution :
Dept. of Civil Eng., Delaware Univ., Newark, DE, USA
Abstract :
An origin-destination (O-D) table represents the travel pattern of a region in a matrix form. A method is presented to estimate the trip O-D matrix when trip generation and trip attraction counts are approximate. This is a two step process. In the first step the existence of a consistent travel pattern is examined. If a pattern is found to exist then, in the second step, a backpropagation neural network is used to identify the O-D matrix. This method can be used to estimate the input-output relationship for any general system problem
Keywords :
backpropagation; fuzzy systems; neural nets; system theory; transportation; backpropagation neural network; consistent travel pattern; fuzzy input; fuzzy output; general system problem; input-output relationship; matrix identification; origin-destination matrix; trip attraction counts; trip estimation; trip generation; Backpropagation; Bismuth; Civil engineering; Economics; Neural networks; Traffic control; Transportation; Upper bound;
Conference_Titel :
Uncertainty Modeling and Analysis, 1993. Proceedings., Second International Symposium on
Conference_Location :
College Park, MD
Print_ISBN :
0-8186-3850-8
DOI :
10.1109/ISUMA.1993.366783
