Home  About us  Contact
 

Basis Function Neural Networks (basis + function_neural_network)

Distribution by Scientific Domains
Chemistry75%

Kinds of Basis Function Neural Networks

  • radial basis function neural network
    		•

    Selected Abstracts

    Quantitative Structure,Activity Relationship Study on Fish Toxicity of Substituted Benzenes

    MOLECULAR INFORMATICS, Issue 8 2008
    Zhiguo Gong
    Abstract Many chemicals cause latent harm, such as erratic diseases and change of climate, and therefore it is necessary to evaluate environmentally safe levels of dangerous chemicals. Quantitative Structure,Toxicity Relationship (QSTR) analysis has become an indispensable tool in ecotoxicological risk assessments. Our paper used QSTR to deal with the modeling of the acute toxicity of 92 substituted benzenes. The molecular descriptors representing the structural features of the compounds were calculated by CODESSA program. Heuristic Method (HM) and Radial Basis Function Neural Networks (RBFNNs) were utilized to construct the linear and the nonlinear QSTR models, respectively. The predictive results were in agreement with the experimental values. The optimal QSTR model which was established based on RBFNNs gave a correlation coefficient (R2) of 0.893, 0.876, 0.889 and Root-Mean-Square Error (RMSE) of 0.220, 0.205, 0.218 for the training set, the test set, and the whole set, respectively. RBFNNs proved to be a very good method to assess acute aquatic toxicity of these compounds, and more importantly, the RBFNNs model established in this paper has fewer descriptors and better results than other models reported in previous literatures. The current model allows a more transparent chemical interpretation of the acute toxicity in terms of intermolecular interactions. [source]

    Studies on the quantitative relationship between the olfactory thresholds of pyrazine derivatives and their molecular structures

    FLAVOUR AND FRAGRANCE JOURNAL, Issue 2 2009
    Feng Luan
    Abstract Quantitative structure,property relationship (QSPR) investigation was performed for the study of olfactory thresholds of pyrazine derivatives. Descriptors calculated from the molecular structures alone were used to represent the characteristics of the compounds. The six molecular descriptors selected by the best mutilinear regression (BMLR) in CODESSA were used as inputs for support vector machine (SVM) and radial basis function neural networks (RNFNN). The root mean squared errors (RMS) of logarithm of olfactory thresholds (p.p.m.) for the training, predicted and overall datasets were 0.5674, 0.6601 and 0.5860 for BMLR, 0.4720, 0.6861 and 0.5194 for RBFNN, and 0.5242, 0.6466 and 0.5495 for SVM, respectively. The prediction results were in agreement with the experimental values. The QSPR models provide a rapid, simple and valid way to predict the odour threshold of pyrazine derivatives. Copyright © 2009 John Wiley & Sons, Ltd. [source]

    Reformulated radial basis function neural networks with adjustable weighted norms

    INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, Issue 10 2003
    Mary M. Randolph-Gips
    This article presents a new family of reformulated radial basis function (RBF) neural networks that employ adjustable weighted norms to measure the distance between the training vectors and the centers of the radial basis functions. The reformulated RBF model introduced in this article incorporates norm weights that can be updated during learning to facilitate the implementation of the desired input-output mapping. Experiments involving classification and function approximation tasks verify that the proposed RBF neural networks outperform conventional RBF neural networks and reformulated RBF neural networks employing fixed Euclidean norms. Reformulated RBF neural networks with adjustable weighted norms are also strong competitors to conventional feedforward neural networks in terms of performance, implementation simplicity, and training speed. © 2003 Wiley Periodicals, Inc. [source]

    Quantitative structure property relationship models for the prediction of liquid heat capacity

    MOLECULAR INFORMATICS, Issue 1 2003
    Xiaojun Yao
    Abstract Quantitative Structure-Property Relationship (QSPR) models based on molecular descriptors derived from molecular structures have been developed for the prediction of liquid heat capacity at 25,°C using a diverse set of 871 organic compounds. The molecular descriptors used to represent molecular structures include constitutional and topological indices and quantum chemical parameters. Forward stepwise regression and radial basis function neural networks (RBFNNs) were used to construct the QSPR models. The root mean square errors in liquid heat capacity predictions for the training, test and overall data sets are 16.857, 18.744 and 17.141 heat capacity units, respectively. The prediction results are in agreement with the experimental values, but the RBFNN model seems to be better than stepwise regression method. [source]