ASCE will be sunsetting the Civil Engineering Database (CEDB) in the coming months. We encourage you to start using the ASCE Library to perform content searches. In the ASCE Library, you can save your search results as well as receive email content alerts when new content relevant to your area of interest is published. Try it out today at https://ascelibrary.org.

 

Trip Generation Analysis by Artificial Neural Networks

by Ardeshir Faghri, Univ of Delaware, Newark, United States,
Jiuyi Hua, Univ of Delaware, Newark, United States,



Document Type: Proceeding Paper

Part of: Microcomputers in Transportation

Abstract:

A new approach for conducting trip generation analysis based on the concepts of artificial neural networks is presented in this paper. First, a brief introduction to the concepts of artificial neural networks is given. Subsequently, two neural network paradigms, ADALINE and Backpropagation, were built and were applied to a real-world database of 150 different sites in the Washington-Baltimore region. A conventional multiple linear regression analysis was also applied to the same database. Prediction results obtained by the regression analysis and the two neural networks, respectively, are compared. The performances of the two neural network paradigms are discussed. Finally, this paper concludes that as an alternative to the regression analysis approach, the neural networks are suitable for trip generation prediction problems.

Subject Headings: Neural networks | Regression analysis | Network analysis | Forecasting | Data analysis | Travel demand | Transportation studies

Services: Buy this book/Buy this article

 

Return to search