Click for new scientific resources and news about Corona[COVID-19]

Paper Information

Journal:   SHARIF: CIVIL ENINEERING   JUNE-JULY 2008 , Volume 24 , Number 42; Page(s) 95 To 100.
 
Paper: 

A COMPARISON BETWEEN DIFFERENT METHODS OF ASSESSING THE IMPACT OF INPUT FEATURES IN FEEDFORWARD NEURAL NETWORKS USING GEOTECHNICAL DATABASE

 
 
Author(s):  SHAFIEI ALI, GHATE R.
 
* 
 
Abstract: 

The back-propagation neural network (BPNN) has been researched and applied as a convenient tool in a variety of application areas in civil engineering. In particular, BPNN has been applied to many geotechnical engineering problems and has demonstrated some degree of success. A review of the literature reveals that BPNN has been used successfully in pile capacity prediction, modeling soil behavior and liquefaction, etc. However, learning algorithms, such as the BPNN, do not give information on the effect of each input parameter or influencing variable upon the predicted output variable. In other words, it is not possible to find out immediately how the weights of the network or the activation values of the hidden neurons are related to the set of data being handled. Instead, ANNs have been presented to the user as a kind of 'black box', who’s extremely complex work transforms inputs into predetermined outputs. To deal with this problem, during the last 10 years, different interpretative methods for analyzing the effect or importance of input variables on the output of a feed forward neural network have been proposed. In this paper, six methods that give the relative contribution of the input factors were compared. The data used for training the networks is based on the laboratory tests for determining the dynamic properties of aggregate-clay mixtures. Finally, the method which best interprets the networks is introduced.

 
Keyword(s): SENSITIVITY ANALYSIS, WEIGHT PRODUCT METHOD, COMPOSITE CLAY, SHEAR MODULUS, DAMPING RATIO
 
References: 
  • ندارد
 
  Persian Abstract Yearly Visit 66
 
Latest on Blog
Enter SID Blog