Browse

Estimation of stability number of rock armor using artificial neural network combined with principal component analysis

Cited 0 time in Web of Science Cited 0 time in Scopus
Authors
Lee, Anzy; Kim, Sung Eun; Suh, Kyung-Duck
Issue Date
2015
Publisher
Elsevier
Citation
Procedia Engineering, vol.116, pp. 149-154
Keywords
Armor stoneArtificial Neural NetworkPricipal Component AnalysisStability Number
Description
This is an open access article under the CC BY-NC-ND license
(http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract
In this paper, a hybrid artificial neural network (ANN) model is constructed to estimate the stability number of rock armor using the experimental data of Van der Meer (1988). Among the eleven input parameters in the experiment, the six parameters each of which is well distributed in a certain range are transformed into six principal components (PCs) by using a principal component analysis (PCA), which are then used as the input variables of the ANN. The remaining five parameters that vary among several different values (e.g. number of waves of 1000 or 3000) are directly used as the input variables of the ANN. Since the orthogonality of the PCs prevents the duplication of information by separating the variables into several independent components while maintaining the critical information in them, the hybrid ANN model combined with the PCA gives better results compared with the conventional ANN models.
Language
English
URI
https://hdl.handle.net/10371/95433
Files in This Item:
Appears in Collections:
College of Engineering/Engineering Practice School (공과대학/대학원)Dept. of Civil & Environmental Engineering (건설환경공학부)Journal Papers (저널논문_건설환경공학부)
  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse