PubMed Health⌕ Search

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 91 records · Page 5Linked to original sources
PubMed2000

Training radial basis function neural networks: effects of training set size and imbalanced training sets.

Obtaining training data for constructing artificial neural networks (ANNs) to identify microbiological taxa is not always easy. Often, only small data sets with different numbers of observations per taxon are available. Here, the effect of both size of the training data set and of an imbalanced number of training patterns for different taxa is investigated using radial basis function ANNs to identify up to 60 species of marine microalgae. The best networks trained to discriminate 20, 40 and 60 species respectively gave overall percentage correct identification of 92, 84 and 77%. From 100 to 200 patterns per species was sufficient in networks trained to discriminate 20, 40 or 60 species. For 40 and 60 species data sets an imbalance in the number of training patterns per species always affected training success, the greater the imbalance the greater the effect. However, this could be largely compensated for by adjusting the networks using a posteriori probabilities, estimated as network output values.

Neural Networks, Computer↗
PubMed2001

Modelling cause-specific hazards with radial basis function artificial neural networks: application to 2233 breast cancer patients.

The clinical course of a disease is often characterized by the possible occurrence of different types of events acting in a competing way. From a statistical point of view this translates into the need of modelling the dependence of cause-specific hazards as a function of covariates. Generalized linear models with Poisson error have previously been adopted for the analysis of competing risks as a function of discrete covariates. In the present paper an artificial neural network extension for the flexible joint estimation of cause-specific hazards depending on both discrete and continuous covariates is proposed. This approach is based on radial basis function networks which have the advantage of allowing parameter estimation by the adoption of standard software for generalized linear models. We have applied this method to data from 2233 breast cancer patients to investigate the effects of age, tumour size, number of metastatic axillary nodes, histology and tumour site on cause-specific hazards for intra-breast tumour recurrences and distant metastases. The adoption of a radial basis function network made it possible to highlight effects that were not considered by previous analyses of the same data.

Adult↗
PubMed1994

Neural-network contributions in biotechnology.

In the mid-1980s, widespread interest in research into artificial neural networks re-emerged following a period of reduced research funding. The much wider availability and the increased power of computing systems, together with new areas of research, is expanding the range of potential application. The main reason for this is that the potential to describe the characteristics of extremely complex systems accurately has been attributed to this methodology. This article examines the contribution of various network methodologies to bioprocess modelling, control and pattern recognition. Industrial processes can benefit from the application of feedforward networks with sigmoidal activation functions, radial basis function networks and autoassociative networks. The contribution that neural networks can make to biochemical and microbiological scientific research is also reviewed briefly.

Animals↗
PubMed2005

Identification and quantification of industrial grade glycerol adulteration in red wine with fourier transform infrared spectroscopy using chemometrics and artificial neural networks.

Fourier transform infrared (FT-IR) single bounce micro-attenuated total reflectance (mATR) spectroscopy, combined with multivariate and artificial neural network (ANN) data analysis, was used to determine the adulteration of industrial grade glycerol in selected red wines. Red wine samples were artificially adulterated with industrial grade glycerol over the concentration range from 0.1 to 15% and calibration models were developed and validated. Single bounce infrared spectra of glycerol adulterated wine samples were recorded in the fingerprint mid-infrared region, 900-1500 cm(-1). Partial least squares (PLS) and PLS first derivatives were used for quantitative analysis (r2 = 0.945 to 0.998), while linear discriminant analysis (LDA) and canonical variate analysis (CVA) were used for classification and discrimination. The standard error of prediction (SEP) in the validation set was between 1.44 and 2.25%. Classification of glycerol adulterants in the different brands of red wine using CVA resulted in a classification accuracy in the range between 94 and 98%. Artificial neural network analysis based on the quick back propagation network (BPN) and the radial basis function network (RBFN) algorithms had classification success rates of 93% using BPN and 100% using RBFN. The genetic algorithm network was able to predict the concentrations of glycerol in wine up to an accuracy of r2 = 0.998.

Algorithms↗
PubMedDate not supplied

Using general regression and probabilistic neural networks to predict human intestinal absorption with topological descriptors derived from two-dimensional chemical structures.

The objective of this study was to develop rapid and reliable methods to predict the percent human intestinal absorption (%HIA) of compounds based on their 2D descriptors. The analyzed data set included 86 drug and drug-like molecules and was the same as that studied by Wessel and co-workers. Instead of using three-dimensional descriptors such as polar surface area, which require lengthy computations, we employed only two-dimensional topological descriptors derived from information about the two-dimensional structure of molecules. The %HIA values were modeled using a general regression neural network (GRNN) and a probabilistic neural network (PNN), variants of normalized radial basis function networks. Both networks performed well to model the %HIA values. The root-mean square (rms) error was 22.8 %HIA unit for the external prediction set for a GRNN model, and 80% of the external prediction set was correctly classified for a PNN model, indicating the potential of our approach to estimate the %HIA values for a large set of compounds as virtual libraries.

Humans↗
PubMed2005

Automatic detection of epileptiform events in EEG by a three-stage procedure based on artificial neural networks.

This paper introduces a three-stage procedure based on artificial neural networks for the automatic detection of epileptiform events (EVs) in a multichannel electroencephalogram (EEG) signal. In the first stage, two discrete perceptrons fed by six features are used to classify EEG peaks into three subgroups: 1) definite epileptiform transients (ETs); 2) definite non-ETs; and 3) possible ETs and possible non-ETs. The pre-classification done in the first stage not only reduces the computation time but also increases the overall detection performance of the procedure. In the second stage, the peaks falling into the third group are aimed to be separated from each other by a nonlinear artificial neural network that would function as a postclassifier whose input is a vector of 41 consecutive sample values obtained from each peak. Different networks, i.e., a backpropagation multilayer perceptron and two radial basis function networks trained by a hybrid method and a support vector method, respectively, are constructed as the postclassifier and then compared in terms of their classification performances. In the third stage, multichannel information is integrated into the system for contributing to the process of identifying an EV by the electroencephalographers (EEGers). After the integration of multichannel information, the overall performance of the system is determined with respect to EVs. Visual evaluation, by two EEGers, of 19 channel EEG records of 10 epileptic patients showed that the best performance is obtained with a radial basis support vector machine providing an average sensitivity of 89.1%, an average selectivity of 85.9%, and a false detection rate (per hour) of 7.5.

Adolescent↗
PubMed2001

Application of artificial neural networks to the classification of soils from São Paulo State using near-infrared spectroscopy.

This paper describes how artificial neural networks can be used to classify multivariate data. Two types of neural networks were applied: a counter propagation neural network (CP-ANN) and a radial basis function network (RBFN). These strategies were used to classify soil samples from different geographical regions in Brazil by means of their near-infrared (diffuse reflectance) spectra. The results were better with CP-ANN (classification error 8.6%) than with RBFN (classification error 11.0%).

Journal Article↗
PubMed1999

Combinatorial evolution of regression nodes in feedforward neural networks.

A number of techniques exist with which neural network architectures such as multilayer perceptrons and radial basis function networks can be trained. These include backpropagation, k-means clustering and evolutionary algorithms. The latter method is particularly useful as it is able to avoid local optima in the search space and can optimise parameters for which no gradient information exists. Unfortunately, only moderately sized networks can be trained by this method, owing to the fact that evolutionary optimisation is very computationally intensive. In this paper a novel algorithm (CERN) is therefore proposed which uses a special form of combinatorial search to optimise groups of neural nodes. Oriented, ellipsoidal basis nodes optimised with CERN achieved significantly better accuracy with fewer nodes than spherical basis nodes optimised by k-means clustering. Multilayer perceptrons optimised by CERN were found to be as accurate as those trained by advanced gradient descent techniques. CERN was also found to be significantly more efficient than a conventional evolutionary algorithm that does not use a combinatorial search.

Journal Article↗
PubMed2000

Inductive learning approaches to rainfall-runoff modelling.

Trying to model the rainfall-runoff process is a complex activity as it is influenced by a number of implicit and explicit factors--for example, precipitation distribution, evaporation, transpiration, abstraction, watershed topography, and soil types. However, this kind of forecasting is particularly important as it is used to predict serious flooding, estimate erosion and identify problems associated with low flow. Inductive learning approaches (e.g. decision trees and artificial neural networks) are particularly well suited to problems of this nature as they can often interpret underlying factors (such as seasonal variations) which cannot be modelled by other techniques. In addition, these approaches can easily be trained on the explicit factors (e.g. rainfall) and the inexplicit factors (e.g. abstraction) that affect river flow. Inductive learning approaches can also be extended to account for new factors that emerge over a period of time. This paper evaluates the application of decision trees and two artificial neural network models (the multilayer perceptron and the radial basis function network) to river flow forecasting in two flood prone UK catchments using real hydrometric data. Comparisons are made between the performance of these approaches and conventional flood forecasting systems.

Algorithms↗
PubMed2004

Prediction of visual perceptions with artificial neural networks in a visual prosthesis for the blind.

Within the framework of the OPTIVIP project, an optic nerve based visual prosthesis is developed in order to restore partial vision to the blind. One of the main challenges is to understand, decode and model the physiological process linking the stimulating parameters to the visual sensations produced in the visual field of a blind volunteer. We propose to use adaptive neural techniques. Two prediction models are investigated. The first one is a grey-box model exploiting the neurophysiological knowledge available up to now. It combines a neurophysiological model with artificial neural networks, such as multi-layer perceptrons and radial basis function networks, in order to predict the features of the visual perceptions. The second model is entirely of the black-box type. We show that both models provide satisfactory prediction tools and achieve similar prediction accuracies. Moreover, we demonstrate that significant improvement (25%) was gained with respect to linear statistical methods, suggesting that the biological process is strongly non-linear.

Blindness↗
PubMed1997

What represents a face? A computational approach for the integration of physiological and psychological data.

Empirical studies of face recognition suggest that faces might be stored in memory by means of a few canonical representations. The nature of these canonical representations is, however, unclear. Although psychological data show a three-quarter-view advantage, physiological studies suggest profile and frontal views are stored in memory. A computational approach to reconcile these findings is proposed. The pattern of results obtained when different views, or combinations of views, are used as the internal representation of a two-stage identification network consisting of an autoassociative memory followed by a radial-basis-function network are compared. Results show that (i) a frontal and a profile view are sufficient to reach the optimal network performance; and (ii) all the different representations produce a three-quarter view advantage, similar to that generally described for human subjects. These results indicate that although three-quarter views yield better recognition than other views, they need not be stored in memory to show this advantage.

Computer Simulation↗
PubMed2005

QSAR study on the Ah receptor-binding affinities of polyhalogenated dibenzo-p-dioxins using net atomic-charge descriptors and a radial basis neural network.

A radial basis function neural network (RBFN) has been used to correlate Ah receptor-binding affinities of polychlorinated, polybrominated, and polychlorinated-brominated dibenzo-p-dioxins with molecular weight and eight net atomic charge descriptors. Support vector machine (SVM) and partial least square (PLS) regression models based on the same data set have also been built. Leave-one-out cross-validation was used to train the RBFN, SVM, and PLS models. For predicting Ah receptor-binding affinities, the RBFN model with a squared cross-validation correlation coefficient (q2) of 0.8818 outperforms the SVM and PLS models and also compares favorably with any other reported quantitative structure-activity relationship model based on the same activity data set. The significance of the RBFN model with net atomic charges as descriptors suggests that electrostatic and dispersion-type interactions play important roles in governing the Ah receptor binding of polychlorinated, polybrominated, and polychlorinated-brominated dibenzo-p-dioxins.

Algorithms↗
PubMed2004

Potential assessment of a neural network model with PCA/RBF approach for forecasting pollutant trends in Mong Kok urban air, Hong Kong.

The forecasting of air pollutant trends has received much attention in recent years. It is an important and popular topic in environmental science, as concerns have been raised about the health impacts caused by unacceptable ambient air pollutant levels. Of greatest concern are metropolitan cities like Hong Kong. In Hong Kong, respirable suspended particulates (RSP), nitrogen oxides (NOx), and nitrogen dioxide (NO2) are major air pollutants due to the dominant usage of diesel fuel by commercial vehicles and buses. Hence, the study of the influence and the trends relating to these pollutants is extremely significant to the public health and the image of the city. The use of neural network techniques to predict trends relating to air pollutants is regarded as a reliable and cost-effective method for the task of prediction. The works reported here involve developing an improved neural network model that combines both the principal component analysis technique and the radial basis function network and forecasts pollutant tendencies based on a recorded database. Compared with general neural network models, the proposed model features a more simple network architecture, a faster training speed, and a more satisfactory prediction performance. The improved model was evaluated with hourly time series of RSP, NOx and NO2 concentrations monitored at the Mong Kok Roadside Gaseous Monitory Station in Hong Kong during the year 2000 and proved to be effective. The model developed is a potential tool for forecasting air quality parameters and is superior to traditional neural network methods.

Air Pollutants↗
PubMed2004

Comparison of neural network predictors in the classification of tracheal-bronchial breath sounds by respiratory auscultation.

Despite extensive research in the area of identification and discrimination of tracheal-bronchial breath sounds by computer analysis, the process of identifying auscultated sounds is still subject to high estimation uncertainties. Here we assess the performance of the relatively new constructive probabilistic neural network (CPNN) against the more common classifiers, namely the multilayer perceptron (MLP) and radial basis function network (RBFN), in classifying a broad range of tracheal-bronchial breath sounds. We present our data as signal estimation models of the tracheal-bronchial frequency spectra. We have examined the trained structure of the CPNN with respect to the other architectures and conclude that this architecture offers an attractive means with which to analyse this type of data. This is based partly on the classification accuracies attained by the CPNN, MLP and RBFN which were 97.8, 77.8 and 96.2%, respectively. We concluded that CPNN and RBFN networks are capable of working successfully with this data, with these architectures being acceptable in terms of topological size and computational overhead requirements. We further believe that the CPNN is an attractive classification mechanism for auscultated data analysis due to its optimal data model generation properties and computationally lightweight architecture.

Auscultation↗
PubMed2006

Recurrent RBFN-based fuzzy neural network control for X-Y-theta motion control stage using linear ultrasonic motors.

A recurrent radial basis function network (RBFN) based fuzzy neural network (FNN) control system is proposed to control the position of an X-Y-theta motion control stage using linear ultrasonic motors (LUSMs) to track various contours in this study. The proposed recurrent RBFN-based FNN combines the merits of self-constructing fuzzy neural network (SCFNN), recurrent neural network (RNN), and RBFN. Moreover, the structure and the parameter learning phases of the recurrent RBFN-based FNN are performed concurrently and on line. The structure learning is based on the partition of input space, and the parameter learning is based on the supervised gradient decent method using a delta adaptation law. The experimental results due to various contours show that the dynamic behaviors of the proposed recurrent RBFN-based FNN control system are robust with regard to uncertainties.

Algorithms↗
PubMedDate not supplied

Constructing a query-able radial basis function artificial neural network.

Artificial neural networks will be more widely accepted as standard engineering tools if their reasoning process can be made less opaque. This paper describes NetQuery, an explanation mechanism that extracts meaningful explanations from trained Radial Basis Function (RBF) networks. RBF networks are well suited for explanation generation because they contain a set of locally tuned units. Standard RBF networks are modified to identify dependencies between the inputs, to be sparsely connected, and to have an easily interpretable output layer. Given these modifications, the network architecture can be used to extract "Why?" and "Why not?" explanations from the network in terms of excitatory and inhibitory in-puts and their linear relationships, greatly simplified by a run-time pruning algorithm. These query results are validated by creating an expert system based on the explanations. NetQuery is also able to inform a user about a possible change in category for a given pattern by responding to a "How can I...?" query. This kind of query is extremely useful when analyzing the quality of a pattern set.

Algorithms↗
PubMed2003

Neural networks for process control and optimization: two industrial applications.

The two most widely used neural models, multilayer perceptron (MLP) and radial basis function network (RBFN), are presented in the framework of system identification and control. The main steps for building such nonlinear black box models are regressor choice, selection of internal architecture, and parameter estimation. The advantages of neural network models are summarized: universal approximation capabilities, flexibility, and parsimony. Two applications are described in steel industry and water treatment, respectively, the control of alloying process in a hot dipped galvanizing line and the control of a coagulation process in a drinking water treatment plant. These examples highlight the interest of neural techniques, when complex nonlinear phenomena are involved, but the empirical knowledge of control operators can be learned.

Algorithms↗