DocumentCode :
2777823
Title :
Improvement of an Artificial Neural Network Model using Min-Max Preprocessing for the Prediction of Wave-induced Seabed Liquefaction
Author :
Cha, Deaho ; Blumenstein, Michael ; Zhang, Hong ; Jen, Dong-Sheng
Author_Institution :
Griffith Univ., Gold Coast
fYear :
0
fDate :
0-0 0
Firstpage :
4577
Lastpage :
4581
Abstract :
In the past decade, artificial neural networks (ANNs) have been widely applied to the engineering problems with a complicated system. ANNs are becoming an important alternative option for solving problems in comparison to traditional engineering solutions, which are usually involved in complicated mathematical theories. In this study, we apply an ANN model to the wave-induced seabed liquefaction problem, which is a key issue in the area of coastal and ocean engineering. Furthermore, we adopted an ANN model with preprocessing (MIN-MAX) on difficult training data. This paper demonstrates the capacity of the proposed ANN model using MIN-MAX pre-processing to provide coastal engineers with another effective tool to analyse the stability of seabed sediment.
Keywords :
liquefaction; minimax techniques; neural nets; artificial neural network; min-max preprocessing; seabed sediment; wave-induced seabed liquefaction; Artificial neural networks; Australia; Data engineering; Gold; Oceans; Predictive models; Sea measurements; Stability analysis; Stress; Training data;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2006. IJCNN '06. International Joint Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-9490-9
Type :
conf
DOI :
10.1109/IJCNN.2006.247085
Filename :
1716734
Link To Document :
بازگشت