Comparison of ANN and principal component analysis-multivariate linear regression models for predicting the river flow based on developed discrepancy ratio statistic

Noori, Roohollah; Khakpour, Amir; Omidvar, Babak; Farokhnia, Ashkan

doi:10.1016/j.eswa.2010.02.020

Cited by 142 publications

(57 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A multi-linear regression analysis (MLRA) attempts to model the relationship between two or more variables and a response by fitting a linear equation to observed data (Noori, Khakpour, Omidvar, & Farokhnia, 2010;Placca, Kouta, Candusso, Blachot, & Charon, 2010). The general purpose of MLRA is to learn about the relationship between several independent variables and a dependent variable.…”

Section: Multiple Linear Regression Analysismentioning

confidence: 99%

Fingerprint–efficacy study of artificial Calculus bovis in quality control of Chinese materia medica

et al. 2011

View full text Add to dashboard Cite

Section: Multiple Linear Regression Analysismentioning

confidence: 99%

Fingerprint–efficacy study of artificial Calculus bovis in quality control of Chinese materia medica

et al. 2011

View full text Add to dashboard Cite

“…The optimal network for this study is a feed forward multilayer perceptron (Cybenko 1989;Hornik et al 1989;Haykin 1994;Noori et al 2009Noori et al , 2010, having one input layer with three inputs (pH, SO 4 , Mg), one hidden layer with six neurons that each neuron has a bias and is fully connected to all inputs and utilises sigmoid hyperbolic tangent (tansig) activation function (Fig. 4).…”

Section: Heavy Metals Prediction Using Bpnnmentioning

confidence: 99%

Prediction of heavy metals in acid mine drainage using artificial neural network from the Shur River of the Sarcheshmeh porphyry copper mine, Southeast Iran

et al. 2011

View full text Add to dashboard Cite

Water is one of the basic and fundamental requirements for the survival of human beings. Mining of the sulphide mines usually produce a significant amount of acid mine drainage (AMD) contributing to huge amounts of chemical components and heavy metals in the receiving waters. Prediction of the heavy metals in the AMD is important in developing any appropriate remediation strategy. This paper attempts to predict heavy metals (Cu, Fe, Mn, Zn) from the AMD using backpropagation neural network (BPNN), general regression neural network (GRNN) and multiple linear regression (MLR), by taking pH, sulphate (SO 4 ) and magnesium (Mg) concentrations in the AMD into account in Shur River, Sarcheshmeh porphyry copper deposit, southeast Iran. The comparison between the predicted concentrations and the measured data resulted in the correlation coefficients, R, 0.92, 0.22, 0.92 and 0.92 for Cu, Fe, Mn and Zn ions using BPNN method. Moreover, the R values were 0.89, 0.37, 0.9 and 0.91 for Cu, Fe, Mn, and Zn taking the GRNN method into consideration. However, the correlation coefficients were low for the results predicted by MLR method (0.83, 0.14, 0.9 and 0.85 for Cu, Fe, Mn and Zn ions, respectively). The results further indicate that the ANN can be used as a viable method to rapidly and cost-effectively predict heavy metals in the AMD. The results obtained from this paper can be considered as an easy and cost-effective method to monitor groundwater and surface water affected by AMD.

show abstract

“…(4). Some studies use PC s directly (Noori et al 2010). However, in this study dimensionless parameters were loaded in PC s as input vectors.…”

Section: Component Rotationmentioning

confidence: 99%

“…Actually, these two matrices are different versions of the same thing. There are myriad applications of PCA in water resource engineering, hydrology and environmental sciences (Winter et al 2000;Loska and Wiechula 2003;Ouyang 2005;Noori et al 2010). Before the PCA application, one has to control 'sample size quality,' and 'data screening,' as presented below.…”

Section: Principal Component Analysis (Pca)mentioning

confidence: 99%

Principle Component Analysis in Conjuction with Data Driven Methods for Sediment Load Prediction

Tayfur

Karimi

Singh

2013

Water Resour Manage

View full text Add to dashboard Cite

This study investigates sediment load prediction and generalization from laboratory scale to field scale using principle component analysis (PCA) in conjunction with data driven methods of artificial neural networks (ANNs) and genetic algorithms (GAs). Five main dimensionless parameters for total load are identified by using PCA. These parameters are used in the input vector of ANN for predicting total sediment loads. In addition, nonlinear equations are constructed, based upon the same identified dimensionless parameters. The optimal values of exponents and constants of the equations are obtained by the GA method. The performance of the so-developed ANN and GA based methods is evaluated using laboratory and field data. Results show that the expert methods (ANN and GA), calibrated with laboratory data, are capable of predicting total sediment load in field, thus showing their transferability. In addition, this study shows that the expert methods are not transferable for suspended load, perhaps due to insufficient laboratory data. Yet, these methods are able to predict suspended load in field, when trained with respective field data.

show abstract

Comparison of ANN and principal component analysis-multivariate linear regression models for predicting the river flow based on developed discrepancy ratio statistic

Cited by 142 publications

References 43 publications

Fingerprint–efficacy study of artificial Calculus bovis in quality control of Chinese materia medica

Fingerprint–efficacy study of artificial Calculus bovis in quality control of Chinese materia medica

Prediction of heavy metals in acid mine drainage using artificial neural network from the Shur River of the Sarcheshmeh porphyry copper mine, Southeast Iran

Principle Component Analysis in Conjuction with Data Driven Methods for Sediment Load Prediction

Contact Info

Product

Resources

About