Comparative study of neural network, fuzzy logic and linear transfer function techniques in daily rainfall-runoff modelling under different input domains

2010 ◽  
Vol 25 (2) ◽  
pp. 175-193 ◽  
Author(s):  
Anil Kumar Lohani ◽  
N. K. Goel ◽  
K. K. S. Bhatia
Keyword(s):  
Neural Network ◽  
Fuzzy Logic ◽  
Transfer Function ◽  
Comparative Study ◽  
Daily Rainfall ◽  
Rainfall Runoff ◽  
Linear Transfer Function

Prediction of Shear Strength for Subgrade Soil under Freezing-Thawing Based on Back Propagation Neural Network

2014 ◽  
Vol 926-930 ◽  
pp. 610-614 ◽  
Author(s):  
Jing Long Chen ◽  
Pei Feng Cheng ◽  
Chuan Jun Yin
Keyword(s):  
Neural Network ◽  
Shear Strength ◽  
Transfer Function ◽  
Sandy Soil ◽  
Bp Neural Network ◽  
Back Propagation ◽  
Friction Angle ◽  
Back Propagation Neural Network ◽  
Linear Transfer Function ◽  
Propagation Network

Soil samples are taken from two experimental roads in Heilongjiang province for the test. Then a prediction of shear strength is carried out, basing on a three-layer BP (back propagation) network in Matlab, the hidden layer, output layer and training function of which adopt non-linear transfer function tansig, linear transfer function purelin, and trainbfg function respectively. It is found workable to predict factors influencing shearing strength using BP neural network with given soil properties. Prediction results of cohesion strength for clay show a better performance than those for sandy soil, while results of friction angle for sandy soil are better than those for clay. It is indicated that BP neural network does a better work in predicting the friction angle than that of cohesion.

scholarly journals Comparison of different forms of the Multi-layer Feed-Forward Neural Network method used for river flow forecasting

2002 ◽  
Vol 6 (4) ◽  
pp. 671-684 ◽  
Author(s):  
A. Y. Shamseldin ◽  
A. E. Nasr ◽  
K. M. O’Connor
Keyword(s):  
Neural Network ◽  
Transfer Function ◽  
River Flow ◽  
Transfer Functions ◽  
Logistic Function ◽  
Forecast Combination ◽  
Rainfall Runoff ◽  
Feed Forward Neural Network ◽  
Feed Forward ◽  
Flow Forecast

Abstract. The Multi-Layer Feed-Forward Neural Network (MLFFNN) is applied in the context of river flow forecast combination, where a number of rainfall-runoff models are used simultaneously to produce an overall combined river flow forecast. The operation of the MLFFNN depends not only on its neuron configuration but also on the choice of neuron transfer function adopted, which is non-linear for the hidden and output layers. These models, each having a different structure to simulate the perceived mechanisms of the runoff process, utilise the information carrying capacity of the model calibration data in different ways. Hence, in a discharge forecast combination procedure, the discharge forecasts of each model provide a source of information different from that of the other models used in the combination. In the present work, the significance of the choice of the transfer function type in the overall performance of the MLFFNN, when used in the river flow forecast combination context, is investigated critically. Five neuron transfer functions are used in this investigation, namely, the logistic function, the bipolar function, the hyperbolic tangent function, the arctan function and the scaled arctan function. The results indicate that the logistic function yields the best model forecast combination performance. Keywords: River flow forecast combination, multi-layer feed-forward neural network, neuron transfer functions, rainfall-runoff models

Sign in / Sign up

Export Citation Format

Share Document