DocumentCode
1791112
Title
The Comprehensive Evaluation of Architectural Engineering Geology Based on IACO
Author
Lianguang Mo
Author_Institution
Hunan City Univ., Yiyang, China
fYear
2014
fDate
25-26 Oct. 2014
Firstpage
559
Lastpage
564
Abstract
The evaluation of architectural engineering geology and the danger of geologic hazard is one of the important contents to achieve a right place for architectural engineering. During the process of solving nonlinear regression model of the evaluation of architectural engineering geology and the danger of geologic hazard through neural network, we come up with a new type of bionic algorithm, that is using the improved ant colony algorithm to train the weights threshold value of neural network. This method has cut down the process of training, avoiding the problem of BP algorithm that is easy to fall into partial extremum. Applying the improved BP algorithm to the model of the evaluation of architectural engineering geology and the danger of geologic hazard, displays the good evaluation ability of the network model, and validates the effectiveness and feasibility of the improved neural network based on ant colony algorithm in the evaluation of architectural engineering geology and the danger of geologic hazard.
Keywords
geology; geophysical techniques; neural nets; regression analysis; BP algorithm; IACO; architectural engineering geology; architectural engineering geology evaluation; colony algorithm; comprehensive evaluation; geologic hazard danger; improved neural network; network model; nonlinear regression model; partial extremum; Artificial neural networks; Biological neural networks; Geoengineering; Geology; Optimization; Training; Ant Colony Optimization (ACO) algorithm?BP neural network?Architectural Engineering Geology?Comprehensive Evaluation;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Computation Technology and Automation (ICICTA), 2014 7th International Conference on
Conference_Location
Changsha
Print_ISBN
978-1-4799-6635-6
Type
conf
DOI
10.1109/ICICTA.2014.141
Filename
7003604
Link To Document