ORDINATION ANALYSIS OF TAXUS CHINENSIS VAR. MAIREI FORESTS BASED ON ARTIFICIAL NEURAL NETWORK THEORY

2010 ◽  
Vol 03 (01) ◽  
pp. 69-78 ◽  
Author(s):  
JIN-TUN ZHANG ◽  
WENMING RU
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Data Matrix ◽  
Shanxi Province ◽  
Taxus Chinensis ◽  
Forest Types ◽  
Soil Variables ◽  
Topographical Factors ◽  
Artificial Neural ◽  
Neural Network Theory

The artificial neural network is attractive for ecological studies for its power in analyzing and solving complicated and nonlinear matters. The Self-Organizing Feature Map (SOFM) ordination were described and applied to the analysis of Taxus chinensis var. mairei forests in Shanxi province of China in this paper. The data matrix is the important values of 128 species in 95 quadrats. The results showed that SOFM ordination displayed forest communities in species space which reflected ecological gradients successfully. Its first axis is comprehensive gradient of topographical factors and its second axis is a comprehensive gradient of soil variables. SOFM ordination also distinguished 95 quadrats into eight forest types. SOFM ordination made the interpretation of relationships between communities, species, and environments easier.

Applying artificial neural network theory to exploring diatom abundance at tropical Putrajaya Lake, Malaysia

2012 ◽  
Vol 27 (2) ◽  
pp. 211-227 ◽  
Author(s):  
Sorayya Malek ◽  
Aishah Salleh ◽  
Pozi Milow ◽  
Mohd Sapiyan Baba ◽  
S.A. Sharifah
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Network Theory ◽  
Diatom Abundance ◽  
Artificial Neural ◽  
Neural Network Theory

scholarly journals Estimation of the volume of distribution of some pharmacologically important compounds from their structural descriptors

2011 ◽  
Vol 76 (7) ◽  
pp. 1003-1014 ◽  
Author(s):  
Mohammad Fatemi ◽  
Zahra Ghorbannezhad
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Van Der Waals ◽  
Volume Of Distribution ◽  
Data Matrix ◽  
Ann Model ◽  
Data Set ◽  
Atomic Masses ◽  
Artificial Neural ◽  
Mlr Model

Quantitative structure-activity relationship (QSAR) approaches were used to estimate the volume of distribution (Vd) using an artificial neural network (ANN). The data set consisted of the volume of distribution of 129 pharmacologically important compounds, i.e., benzodiazepines, barbiturates, NSAIDs, tricyclic anti-depressants and some antibiotics, such as betalactams, tetracyclines and quinolones. The descriptors, which were selected by stepwise variable selection methods, were: the Moriguchi octanol-water partition coefficient; the 3D-MoRSEsignal 30, weighted by atomic van der Waals volumes; the fragmentbased polar surface area; the d COMMA2 value, weighted by atomic masses; the Geary autocorrelation, weighted by the atomic Sanderson electronegativities; the 3D-MoRSE - signal 02, weighted by atomic masses, and the Geary autocorrelation - lag 5, weighted by the atomic van der Waals volumes. These descriptors were used as inputs for developing multiple linear regressions (MLR) and artificial neural network models as linear and non-linear feature mapping techniques, respectively. The standard errors in the estimation of Vd by the MLR model were: 0.104, 0.103 and 0.076 and for the ANN model: 0.029, 0.087 and 0.082 for the training, internal and external validation test, respectively. The robustness of these models were also evaluated by the leave-5-out cross validation procedure, that gives the statistics Q2 = 0.72 for the MLR model and Q2 = 0.82 for the ANN model. Moreover, the results of the Y-randomization test revealed that there were no chance correlations among the data matrix. In conclusion, the results of this study indicate the applicability of the estimation of the Vd value of drugs from their structural molecular descriptors. Furthermore, the statistics of the developed models indicate the superiority of the ANN over the MLR model.

The Application of BP Artificial Neural Network in Geotechnical Engineering

2014 ◽  
Vol 580-583 ◽  
pp. 823-826
Author(s):  
Na Zhao
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Network Theory ◽  
Geotechnical Engineering ◽  
Time Sequence ◽  
Problem Of Time ◽  
Bp Artificial Neural Network ◽  
Artificial Neural ◽  
Neural Network Theory

Based on MATLAB, the article apply BP artificial neural network theory on the forecasting problem of time sequence in geotechnical engineering, and find it is an effecting way to solve the forecasting problem of time sequence in geotechnical engineering.

Sign in / Sign up

Export Citation Format

Share Document