Applications of Artificial Neural Networks to Pavement Prediction Modeling: A Case Study

淡江大學機構典藏 > 工學院 > 土木工程學系暨研究所 > 會議論文 > Item 987654321/98194

請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/98194

題名:	Applications of Artificial Neural Networks to Pavement Prediction Modeling: A Case Study
作者:	Lee, Ying-Haur;Ker, Hsiang-Wei;Liu, Yao-Bin
貢獻者:	淡江大學土木工程學系
關鍵詞:	Pavement deflection, prediction modeling, artificial neural networks, dimensional analysis, convergence
日期:	2014-05
上傳時間:	2014-06-12 13:49:02 (UTC+8)
出版者:	Virginia：American Society of Civil Engineers
摘要:	Artificial neural networks (ANN) have been used in many pavement prediction modeling analyses. However, the convergence characteristics and model selection guidelines are rarely studied duc to the requirement of extensive network training time. Thus, the techniques and applications of back propagation neural networks were briefly reviewed. Three ANN models were developed using deflection databases generated by factorial BISAR runs. A study of the convergence characteristics indicated that the resulting ANN model using all dominating dimensionless parameters was proved to have higher accuracy and require less network training time and data than the other counterpart using purely input parameters. Increasing the complexity of ANN models does not necessarily improve the modeling statistics. With the incorporation of subject-related engineering and statistical knowledge into the modeling process, reasonably good predictions may be achieved with more convincing generalization and explanation yet requiring minimal amount oftime and effort.
關聯:	PROCEEDINGS OF THE 10TH ASIA PACIFIC TRANSPORTATION DEVELOPMENT CONFERENCE, pp.289-295
顯示於類別:	[土木工程學系暨研究所] 會議論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
icpt27-2014-ann.pdf	應用類神經網路於鋪面預測模式構建之個案研究	4481Kb	Adobe PDF	217	檢視/開啟

在機構典藏中所有的資料項目都受到原著作權保護.

TAIR相關文章

資料載入中.....