SEARCH · PubMed Health

Results for “radial basis function network”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 181 records · Page 10Linked to original sources

PubMed2003

Prediction of a stable microemulsion formulation for the oral delivery of a combination of antitubercular drugs using ANN methodology.

PURPOSE: The aim of this project was to develop a colloidal dosage form for the oral delivery of rifampicin and isoniazid in combination with the aid of artificial neural network (ANN) data modeling. METHODS: Data from the 20 pseudoternary phase triangles containing miglyol 812 as the oil component and a mixture of surfactants or a surfactant/cosurfactant blend were used to train, test, and validate the ANN model. The weight ratios of individual components were correlated with the observed phase behavior using radial basis function (RBF) network architecture. The criterion for judging the best model was the percentage success of the model prediction. RESULTS: The best model successfully predicted the microemulsion region as well as the coarse emulsion region but failed to predict the multiphase liquid crystalline phase for cosurfactant-free systems indicating the difference in microemulsion behavior on dilution with water. CONCLUSIONS: A novel microemulsion formulation capable of delivering rifampicin and isoniazid in combination was created to allow for their differences in solubility and potential for chemical reaction. The developed model allowed better understanding of the process of microemulsion formation and stability within pseudoternary colloidal systems.

Administration, Oral↗

PubMed1999

Combined wavelet transformation and radial basis neural networks for classifying life-threatening cardiac arrhythmias.

Automatic detection and classification of arrhythmias based on ECG signals are important to cardiac-disease diagnostics. The ability of the ECG classifier to identify arrhythmias accurately is based on the development of robust techniques for both feature extraction and classification. A classifier is developed based on using wavelet transforms for extracting features and then using a radial basis function neural network (RBFNN) to classify the arrhythmia. Six energy descriptors are derived from the wavelet coefficients over a single-beat interval from the ECG signal. Nine different continuous and discrete wavelet transforms are considered for obtaining the feature vector. An RBFNN adapted to detect and classify life-threatening arrhythmias is then used to classify the feature vector. Classification results are based on 159 arrhythmia files obtained from three different sources. Classification results indicate the potential for wavelet based energy descriptors to distinguish the main features of the signal and thereby enhance the classification scheme. The RBFNN classifier appears to be well suited to classifying the arrhythmia, owing to the feature vectors' linear inseparability and tendency to cluster. Utilising the Daubechies wavelet transform, an overall correct classification of 97.5% is obtained, with 100% correct classification for both ventricular fibrillation and ventricular tachycardia.

Algorithms↗

PubMed2006

Non-invasive temperature prediction of in vitro therapeutic ultrasound signals using neural networks.

In this paper, a novel black-box modelling scheme applied to non-invasive temperature prediction in a homogeneous medium subjected to therapeutic ultrasound is presented. It is assumed that the temperature in a point of the medium is non-linearly related to some spectral features and one temporal feature, extracted from the collected RF-lines. The black-box models used are radial basis functions neural networks (RBFNNs), where the best-fitted models were selected from the space of model structures using a genetic multi-objective strategy. The best-fitted predictive model presents a maximum absolute error less than 0.4 degrees C in a prediction horizon of approximately 2 h, in an unseen data sequence. This work demonstrates that this type of black-box model is well-suited for punctual and non-invasive temperature estimation, achieving, for a single point estimation, better results than the ones presented in the literature, encouraging research on multi-point non-invasive temperature estimation.

Body Temperature↗

PubMedDate not supplied

A practical sub-space adaptive filter.

A Sub-Space Adaptive Filter (SSAF) model is developed using, as a basis, the Modified Probabilistic Neural Network (MPNN) and its extension the Tuneable Approximate Piecewise Linear Regression (TAPLR) model. The TAPLR model can be adjusted by a single smoothing parameter continuously from the best piecewise linear model in each sub-space to the best approximately piecewise linear model over the whole data space. A suitable value in between ensures that all neighbouring piecewise linear models merge together smoothly at their boundaries. This model was developed by altering the form of the MPNN, a network used for general nonlinear regression. The MPNNs special structure allows it to be easily used to model a process by appropriately weighting piecewise linear models associated with each of the network's radial basis functions. The model has now been further extended to allow each piecewise linear model section to be adapted separately as new data flows through it. By doing this, the proposed SSAF model represents a learning/filtering method for nonlinear processes that provides one solution to the stability/plasticity dilemma associated with standard adaptive filters.

Linear Models↗

PubMed1999

Feedforward neural network with adaptive reference pattern layer.

A hybrid neural network architecture is investigated for modeling purposes. The proposed hybrid is based on the multilayer perceptron (MLP) network. In addition to the usual hidden layers, the first hidden layer is selected to be an adaptive reference pattern layer. Each unit in this new layer incorporates a reference pattern that is located somewhere in the space spanned by the input variables. The outputs of these units are the component wise-squared differences between the elements of a reference pattern and the inputs. The reference pattern layer has some resemblance to the hidden layer of the radial basis function (RBF) networks. Therefore the proposed design can be regarded as a sort of hybrid of MLP and RBF networks. The presented benchmark experiments show that the proposed hybrid can provide significant advantages over standard MLPs and RBFs in terms of fast and efficient learning, and compact network structure.

Feedback↗

PubMed2004

Potential assessment of the "support vector machine" method in forecasting ambient air pollutant trends.

Monitoring and forecasting of air quality parameters are popular and important topics of atmospheric and environmental research today due to the health impact caused by exposing to air pollutants existing in urban air. The accurate models for air pollutant prediction are needed because such models would allow forecasting and diagnosing potential compliance or non-compliance in both short- and long-term aspects. Artificial neural networks (ANN) are regarded as reliable and cost-effective method to achieve such tasks and have produced some promising results to date. Although ANN has addressed more attentions to environmental researchers, its inherent drawbacks, e.g., local minima, over-fitting training, poor generalization performance, determination of the appropriate network architecture, etc., impede the practical application of ANN. Support vector machine (SVM), a novel type of learning machine based on statistical learning theory, can be used for regression and time series prediction and have been reported to perform well by some promising results. The work presented in this paper aims to examine the feasibility of applying SVM to predict air pollutant levels in advancing time series based on the monitored air pollutant database in Hong Kong downtown area. At the same time, the functional characteristics of SVM are investigated in the study. The experimental comparisons between the SVM model and the classical radial basis function (RBF) network demonstrate that the SVM is superior to the conventional RBF network in predicting air quality parameters with different time series and of better generalization performance than the RBF model.

Air Pollutants↗

PubMed1999

A tracing evoked potential estimator.

The paper presents an adaptive Gaussian radial basis function neural network (RBFNN) for rapid estimation of evoked potential (EP). Usually, a recorded EP is severely contaminated by background ongoing activities of the brain. Many approaches have been reported to enhance the signal-to-noise ratio (SNR) of the recorded signal. However, non-linear methods are seldom explored due to their complexity and the fact that the non-linear characteristics of the signal are generally hard to determine. An RBFNN possesses built-in non-linear activation functions that enable the neural network to learn any function mapping. An RBFNN was carefully designed to model the EP signal. It has the advantage of being linear-in-parameter, thus a conventional adaptive method can efficiently estimate its parameters. The proposed algorithm is simple so that its convergence behaviour and performance in signal-to-noise ratio (SNR) improvement can be mathematically derived. A series of experiments carried out on simulated and human test responses confirmed the superior performance of the method. In a simulation experiment, an RBFNN having 15 hidden nodes was trained to approximate human visual EP (VEP). For detecting human brain stem auditory EP (BAEP), the approach (40 hidden nodes and convergence rate = 0.005) speeded up the estimation remarkably by using only 80 ensembles to achieve a result comparable to that obtained by averaging 1000 ensembles.

Electroencephalography↗

PubMed2003

In vitro cell growth pharmacodynamic studies: a new nonparametric approach to determining the relative importance of drug concentration and treatment time.

PURPOSE: The effect of an anticancer treatment on tumor cell proliferation in vitro can be described as a three-dimensional surface where the inhibitory effect is related to drug concentration and treatment time. The analysis of this kind of response surface could provide critical information: for example, it could indicate whether a prolonged exposure to a low concentration of an anticancer agent will produce a different effect from exposure to higher concentrations for a shorter period of time. The parametric approach available in the literature was not flexible enough to accommodate the behavior of the response surface in some of the data sets collected as part of our research programs. Therefore, a new, general, nonparametric approach was developed. METHODS: The response surface of the inhibition of cell-based tumor growth was described using a radial basis function neural network (RBF-NN). The RBF-NN was trained using regularization theory, which provided the initialization of a constrained quadratic optimization algorithm that imposes monotonicity of the surface with respect to both concentration and exposure time. RESULTS: In the two analyzed cases (doxorubicin and flavopiridol), the proposed method was accurate and reliable in describing the inhibition surface of tumor cell growth as a function of drug concentration and exposure time. Residuals were small and unbiased. The new method improved on the parametric approach when the relative importance of drug concentration and exposure time in determining the overall effect was not constant across the experimental data. CONCLUSIONS: The proposed RBF-NN can be reliably applied for the analysis in cell-based tumor growth inhibition studies. This approach can be used for optimizing the administration regimens to be adopted in vivo. The use of this methodology can be easily extended to any cell-based experiment, in which the outcome can be seen as a function of two experimental variables.

Antineoplastic Agents↗

PubMed2006

Prediction of standard Gibbs energies of the transfer of peptide anions from aqueous solution to nitrobenzene based on support vector machine and the heuristic method.

Quantitative structure-property relationship (QSPR) method was performed for the prediction of the standard Gibbs energies (DeltaGtheta) of the transfer of peptide anions from aqueous solution to nitrobenzene. Descriptors calculated from the molecular structures alone were used to represent the characteristics of the peptides. The four molecular descriptors selected by the heuristic method (HM) in COmprehensive DEscriptors for Structural and Statistical Analysis (CODESSA) were used as inputs for support vector machine (SVM) and radial basis function neural networks (RNFNN). The results obtained by the novel machine learning technique, SVM, were compared with those obtained by HM and RBFNN. The root mean squared errors (RMS) of the training, predicted and overall data sets are 2.192, 2.541 and 2.267 unit (kJ/mol) for HM, 1.604, 2.478 and 1.817 unit (kJ/mol) for RBFNN and 1.5621, 2.364 and 1.756 unit (kJ/mol) for SVM, respectively. The prediction results were in agreement with the experimental values. This paper provided a potential method for predicting the physiochemical property (DeltaGtheta) of various small peptides.

Anions↗

PubMed2005

Quantitative structure-activity relationship models for prediction of sensory irritants (logRD50) of volatile organic chemicals.

Quantitative classification and regression models for prediction of sensory irritants (logRD50) of volatile organic chemicals (VOCs) have been developed. Each compound was represented by the calculated structural descriptors to encode constitutional, topological, geometrical, electrostatic, and quantum-chemical features. The heuristic method (HM) was then used to search the descriptor space and select the descriptors responsible for activity. The best classification results were found using support vector machine (SVM): the accuracy for training, test and overall data set is 96.5%, 85.7% and 94.4%, respectively. The nonlinear regression models were built by radial basis function neural networks (RNFNN) and SVM, respectively. The root mean squared errors (RMS) in prediction for the training, test and overall data set are 0.4755, 0.6322 and 0.5009 for reactive group, 0.2430, 0.4798 and 0.3064 for nonreactive group by RBFNN. The comparative results obtained by SVM are 0.4415, 0.7430 and 0.5140 for reactive group, 0.3920, 0.4520 and 0.4050 for nonreactive group, respectively. This paper proposes an effective method for poisonous chemicals screening and considering.

Irritants↗

PubMed2004

Study on the quantitative relationship between the structures and electrophoretic mobilities of flavonoids in micellar electrokinetic capillary chromatography.

Quantitative structure-mobility relationship (QSMR) models were developed between the structures of flavonoids and their eletrophoretic mobilities in micellar electrokinetic capillary chromatography. Molecular descriptors calculated from structure alone are used to represent molecular structures, moreover, Nt was defined by ourselves. Multiple linear regression and radial basis function neural networks (RBFNNs) are utilized to construct the linear and nonlinear prediction model, respectively. The optimal QSMR model developed was based on a 3-10-1 RBFNNs architecture. The root mean square errors in mobilities predictions for the data set was 0.1083 mobility unit (10(-4) cm2 V(-1) s(-1)). The prediction results were in good agreement with the experimental values.

Chromatography, Micellar Electrokinetic Capillary↗

PubMed2005

Data reduction in headspace analysis of blood and urine samples for robust bacterial identification.

This paper demonstrates the application of chemical headspace analysis to the problem of classifying the presence of bacteria in biomedical samples by using computational tools. Blood and urine samples of disparate forms were analysed using a Cyrano Sciences C320 electronic nose together with an Agilent 4440 Chemosensor. The high dimensional data sets resulting from these devices present computational problems for parameter estimation of discriminant models. A variety of data reduction and pattern recognition techniques were employed in an attempt to optimise the classification process. A 100% successful classification rate for the blood data from the Agilent 4440 was achieved by combining a Sammon mapping with a radial basis function neural network. In comparison a successful classification rate of 80% was achieved for the urine data from the C320 which were analysed using a novel nonlinear time series model.

Bacteremia↗

PubMedDate not supplied

Classification of inhibitors of protein tyrosine phosphatase 1B using molecular structure based descriptors.

Loss of Protein Tyrosine Phosphatase 1B (PTP 1B) activity is known to enhance insulin sensitivity and resistance to weight gain. So potent and orally active PTP1B inhibitors could be potential pharmacological agents for the treatment of Type 2 diabetes and obesity. Classification models of PTP1B inhibitors are developed using a data set containing 128 compounds. Their inhibitory concentrations ranged from -1.59 to 1.68 log units. Initially a two-class (active, inactive) problem is tackled using a number of different methods. The data set was divided into active and inactive classes on the basis of inhibitory activity of the compounds. Molecular structure-based descriptors were calculated and used in the model development. Descriptors encoding the flexibility of the molecules were investigated. Classification models were generated using k-nearest neighbors (k-NN), linear discriminant analysis (LDA), and radial basis function neural network (RBFNN). All models are tested using an external prediction set, compounds not used anywhere during the model development procedure. A five-descriptor model is developed that produces a classification rate of 85.7% for an external prediction set. Then a three-class (active, moderately active, inactive) problem was explored. This time the data set was divided into highly active, moderate, and inactive classes on the basis of inhibitory activity of the compounds. The best classification rate achieved for an external prediction set was 85%. The classification rates achieved indicate that these models could serve as a screening mechanism, to identify potentially useful PTP 1B inhibitors. In addition multiple linear regression and computational neural network models are also developed for prediction of log IC(50) values. All QSAR models are tested using the same external prediction set.

Benzofurans↗

PubMedDate not supplied

An accurate QSPR study of O-H bond dissociation energy in substituted phenols based on support vector machines.

The support vector machine (SVM), as a novel type of learning machine, was used to develop a Quantitative Structure-Property Relationship (QSPR) model of the O-H bond dissociation energy (BDE) of 78 substituted phenols. The six descriptors calculated solely from the molecular structures of compounds selected by forward stepwise regression were used as inputs for the SVM model. The root-mean-square (rms) errors in BDE predictions for the training, test, and overall data sets were 3.808, 3.320, and 3.713 BDE units (kJ mol(-1)), respectively. The results obtained by Gaussian-kernel SVM were much better than those obtained by multiple linear regression, radial basis function neural networks, linear-kernel SVM, and other QSPR approaches.

Journal Article↗

PubMedDate not supplied

Study of the quantitative structure-mobility relationship of carboxylic acids in capillary electrophoresis based on support vector machines.

The support vector machines (SVM), as a novel type of learning machine, were used to develop a quantitative structure-mobility relationship (QSMR) model of 58 aliphatic and aromatic carboxylic acids based on molecular descriptors calculated from the structure alone. Multiple linear regression (MLR) and radial basis function neural networks (RBFNNs) were also utilized to construct the linear and the nonlinear model to compare with the results obtained by SVM. The root-mean-square errors in absolute mobility predictions for the whole data set given by MLR, RBFNNs, and SVM were 1.530, 1.373, and 0.888 mobility units (10(-5) cm(2) S(-1) V(-1)), respectively, which indicated that the prediction result agrees well with the experimental values of these compounds and also revealed the superiority of SVM over MLR and RBFNNs models for the prediction of the absolute mobility of carboxylic acids. Moreover, the models we proposed could also provide some insight into what structural features are related to the absolute mobility of aliphatic and aromatic carboxylic acids.

Journal Article↗

PubMed2004

Prediction of biological targets using probabilistic neural networks and atom-type descriptors.

Prediction of biological targets for molecules from their chemical structures is beneficial for generating focused libraries, selecting compounds for screening, and annotating biological activities for those compounds whose activities are unknown. We studied the ability of a probabilistic neural network (PNN), a variant of normalized radial basis function (RBF) neural networks, to predict biological activities for a set of 799 compounds having activities against seven biological targets. The compounds were taken from the MDDR database, and they were carefully selected to comprise distinct biological activities and diverse structures. The structural characteristics of compounds were represented by a set of 24 atom-type descriptors defined by 2D topological chemical structures. The modeling was done in two ways: (1). compounds having one certain activity were discriminated from those not having that activity and (2). all compounds were classified into seven biological classes. In both cases, around 90% of the compounds were correctly classified. Further validation of the modeled PNNs was done with 26 317 compounds having biological activities against various targets except for the seven targets used for modeling, and 67-98% compounds were correctly classified depending upon the targets. A PNN trains much more quickly than widely used neural networks such as a feed-forward neural network with error back-propagation. Calculation of atom-type descriptors is easy even for a large-size chemical library. Combination of PNN and atom-type descriptors thus provides a powerful way to predict biological activities from structural information.

Angiotensin-Converting Enzyme Inhibitors↗

PubMed2002

Quantitative analysis of NO2 in the presence of CO using a single tungsten oxide semiconductor sensor and dynamic signal processing.

We demonstrate that NO2 can be quantitatively analysed in the presence of CO using a single tungsten oxide based resistive gas sensor. The working temperature of the sensor was modulated between 190 and 380 degrees C and its dynamic response to different concentrations of CO, NO2, and CO + NO2 mixtures was monitored. Either the fast Fourier transform (FFT) or the discrete wavelet transform (DWT) was used to extract important features from the sensor response. These features were then input to different (statistical and neural) pattern recognition methods. The species considered can be discriminated with a success rate higher than 90% using a Fuzzy ARTMAP or a radial basis function neural network. The concentrations of the gases studied can be accurately predicted, by using the DWT coupled to partial least squares (PLS) models. The correlation coefficients of the predicted versus real concentrations were 0.923, 0.870 and 0.866 for CO, NO2, and NO2 in CO + NO2 mixtures, respectively.

Journal Article↗

PubMed2006

Accurate quantitative structure-property relationship model of mobilities of peptides in capillary zone electrophoresis.

The aim of this work was to predict electrophoretic mobilities of peptides in capillary zone electrophoresis (CZE) using the linear heuristic method (HM) and a nonlinear radial basis function neural network (RBFNN). Two data sets, consisting of 125 peptides ranging in size between 2 and 14 amino acids and 58 peptides ranging in size between 2 and 39 amino acids, are researched to test applicability of the QSPR methods. In this study, the root mean squared (RMS) errors of the training set, the test set and the whole set of data set 1 are 1.3766, 1.5608 and 1.4157 and the correlation coefficients (R2) are 0.9740, 0.9671 and 0.9724 predicted by RBFNN, respectively. While the RMS errors of the training set, the test set and the whole set of data set 2 are 0.6279, 0.8145 and 0.6673 and the correlation coefficients (R2) are 0.9773, 0.9489 and 0.9732, respectively. So the Offord charge-over-mass term (Q/M(2/3)) combined with descriptors calculated by CODESSA represents the structural features of the peptides appropriately. The electrophoretic mobilities of peptides can be accurately predicted by the linear and nonlinear model. Furthermore, the results of nonlinear model are closer to the experimental data than those of linear model.

Electrophoresis, Capillary↗