Optimisation of radial basis and backpropagation neural networks for modelling auto-ignition temperature by quantitative-structure property relationships

Tetteh, John; Metcalfe, E.; Howells, Sían

doi:10.1016/0169-7439(95)00088-7

Cited by 78 publications

(47 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The topology and learning parameters of RBFNs are easy to optimize [4,5]. Although recently, RBFNs have been successfully applied in many multivariate calibration [6], classification [7] and QSPR studies [8,9], the present study is among the limited number of its applications in QSAR studies.…”

Section: Introductionmentioning

confidence: 98%

Correlation weighted successive projections algorithm as a novel method for variable selection in QSAR studies: investigation of anti‐HIV activity of HEPT derivatives

Kompany‐Zareh

Akhlaghi

2007

Journal of Chemometrics

View full text Add to dashboard Cite

Correlation weighted successive projections algorithm (CWSPA), as a modified version of successive projections algorithm (SPA), is proposed for selection of descriptors in the non-linear quantitative structure-activity relationship (QSAR) study of a series of 1-[2-hydroxyethoxy-methyl]-6-(phenylthio)thymine] (HEPT) derivatives, as non-nucloside reverse transcriptase inhibitors (NNRTIs). In the proposed procedure the correlation coefficient of each descriptor with the activities (r g ) was an additional criterion for selection of descriptors. The extent of contribution of r in the selection of variables, m, was also optimized and r 4 g -CWSPA was the selected condition (m ¼ 4). Three layer radial basis function networks (RBFNs) and molecular descriptors derived solely from molecular structure were used to construct the non-linear QSAR models. Utilizing r 4 g -CWSPA a limited number of uncorrelated and informative descriptors were selected. The relative standard error percent in anti-HIV activity predictions for the training set by the application of cross-validation (RSECV%) was 9.77%, and for prediction set (RSEP%) was 8.61% when the selected number of descriptors were 20. The obtained model outperforms those given in the literature in both the fitting and predicting stages. RBFN analysis yielded predicted activities in an acceptable agreement with the experimentally obtained values (cross-validation r ¼ 0.924, prediction r ¼ 0.939). Compared to SPA, r m g -CWSPA resulted in a lower RSECV% and RSEP% values using lower number of selected variables. The results show that considering the correlation of variables to the independent variables increase the performance of selection, as a result, the quality of the set of selected variables. Finally, a simple procedure for selection of variables using r 4 g -CWSPA was proposed in which there was no need to test all possible initial descriptors. The results from the simple procedure were comparable to the procedure in which all of the possible initial descriptors were tested. The proposed method was successfully validated by five different training and test sets.

show abstract

Section: Introductionmentioning

confidence: 98%

Correlation weighted successive projections algorithm as a novel method for variable selection in QSAR studies: investigation of anti‐HIV activity of HEPT derivatives

Kompany‐Zareh

Akhlaghi

2007

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…Suzuki [6] used unconventional physicochemical parameters, such as the critical pressure and parachor, to predict the AIT of organic compounds by means of multiple linear regression (MLR). Tetteh et al [7,8] have used both artificial neural networks (ANNs) and radial basis function neural networks (RBFNNs) for modeling the AIT on a data set of 232 organic compounds with 13 functional descriptors. Mitchell and Jurs [9] have estimated the AIT with an ANN using a data set of 327 compounds including hydrocarbons, halogenated hydrocarbons, and compounds containing oxygen, sulphur, and nitrogen.…”

Section: Introductionmentioning

confidence: 99%

Autoignition Temperature Prediction Using an Artificial Neural Network with Particle Swarm Optimization

Lazzús

2011

Int J Thermophys

View full text Add to dashboard Cite

The autoignition temperatures of organic compounds were estimated using a hybrid method that includes a simple group contribution method (GCM) implemented in an artificial neural network (ANN) replacing a standard back-propagation algorithm with particle swarm optimization (PSO). A data set of 250 compounds was used for training the network. The optimal condition of the network was obtained by adjusting various parameters by trial-and-error. The capabilities of the designed network were tested in the prediction of the autoignition temperature of 93 compounds not considered during the training step. The proposed model is shown to be more accurate than those of other published works. The results show that the proposed GCM + ANN + PSO method represent an excellent alternative for the estimation of this property with acceptable accuracy (AARD = 1.7 %; AAE = 10 K).

show abstract

“…The optimization of its topology and learning parameters are easy to implement [29,30]. Recently, RBFNs have been successfully applied in many multivariate calibration [31,32], classification [33,34] and QSAR/QSPR studies [35][36][37][38].…”

Section: Introductionmentioning

confidence: 99%

Application of radial basis function networks and successive projections algorithm in a QSAR study of anti‐HIV activity for a large group of HEPT derivatives

Akhlaghi¹,

Kompany‐Zareh²

2006

Journal of Chemometrics

View full text Add to dashboard Cite

A series of 1-[2-hydroxyethoxy-methyl]-6-(phenylthio)thymine] (HEPT) derivatives, as nonnucloside reverse transcriptase inhibitors (NNRTIs), was investigated using a nonlinear quantitative structureanti-HIV-1-activity relationship (QSAR) study. Molecular descriptors derived solely from molecular structure were used to represent molecular structure. Utilizing successive projections algorithm (SPA) and a stepwise backward elimination, a subset of 11 descriptors were selected. Application of SPA minimizes the collinearity between the selected descriptors, which are known to be responsible for the anti-HIV-1 activity. Three layer radial basis function networks (RBFNs) were used to construct the nonlinear QSAR models in all stages of study. The relative standard error percent in anti-HIV activity predictions for the training set by the application of cross-validation (RSECV%) was 9.94%, and for prediction set (RSEP%) was 9.99%. The obtained model outperforms those given in the literature in both the fitting and predicting stages. RBFN analysis yielded predicted activities in the excellent agreement with the experimentally obtained values (cross-validation r ¼ 0.927, prediction r ¼ 0.925).

show abstract

Optimisation of radial basis and backpropagation neural networks for modelling auto-ignition temperature by quantitative-structure property relationships

Cited by 78 publications

References 4 publications

Correlation weighted successive projections algorithm as a novel method for variable selection in QSAR studies: investigation of anti‐HIV activity of HEPT derivatives

Correlation weighted successive projections algorithm as a novel method for variable selection in QSAR studies: investigation of anti‐HIV activity of HEPT derivatives

Autoignition Temperature Prediction Using an Artificial Neural Network with Particle Swarm Optimization

Application of radial basis function networks and successive projections algorithm in a QSAR study of anti‐HIV activity for a large group of HEPT derivatives

Contact Info

Product

Resources

About