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 253 records · Page 14Linked to original sources

PubMed2006

Use of artificial neural networks in near-infrared reflectance spectroscopy calibrations for predicting the inclusion percentages of wheat and sunflower meal in compound feedingstuffs.

The use of near-infrared reflectance spectroscopy (NIRS) calibrations to predict the ingredient composition in compound feeds (i.e., inclusion percentage of each ingredient) is a complex task, regarding both the nature of the parameters to be predicted, since they are not well-defined chemical entities, and the heterogeneousness of the matrices/formulas in which each ingredient participates. The present paper evaluates the use of nonlinear regression methods, such as artificial neural networks (ANN), for developing NIRS calibrations to predict these parameters. Two of the most representative ingredients in the Spanish compound feed formulations (wheat and sunflower meal) were selected for evaluating ANN possibilities, using a large spectral library comprising a total of 7523 commercial compound feed samples; 7423 were used as training set and 100 as validation set. Three general models of networks were studied: multilayer perceptron with back-propagation training (BP), multilayer perceptron with Levenberg-Maquartd training (LM), and radial basis function nets (RBF); moreover, in accordance with a factorial design, more complex architectures were evaluated gradually, changing the number of hidden layers and hidden neurons, for the determination of the optimal network topology. For both ingredients, the best results were obtained using ANN with BP training, showing prediction error values (SEP) of 2.72% and 0.66% for wheat and sunflower meal, respectively. These SEP values showed a significant improvement (19%-49% for sunflower meal and wheat, respectively) in comparison with those obtained using calibrations developed with linear methods.

Animal Feed↗

PubMed2004

Indirect adaptive control for synchronous generator: comparison of MLP/RBF neural networks approach with Lyapunov stability analysis.

This paper compares two indirect adaptive neurocontrollers, namely a multilayer perceptron neurocontroller (MLPNC) and a radial basis function neurocontroller (RBFNC) to control a synchronous generator. The different damping and transient performances of two neurocontrollers are compared with those of conventional linear controllers, and analyzed based on the Lyapunov direct method.

Neural Networks, Computer↗

PubMed2006

A novel RBF neural network training methodology to predict toxicity to Vibrio fischeri.

This work introduces a neural network methodology for developing QSTR predictors of toxicity to Vibrio fischeri. The method adopts the Radial Basis Function (RBF) architecture and the fuzzy means training strategy, which is fast and repetitive, in contrast to most traditional training techniques. The data set that was utilized consisted of 39 organic compounds and their corresponding toxicity values to Vibrio fischeri, while lipophilicity, equalized electronegativity and one topological index were used to provide input information to the models. The performance and predictive ability of the RBF model were illustrated through external validation and various statistical tests. The proposed methodology can be used to successfully model toxicity to Vibrio fischeri for a heterogeneous set of compounds.

Aliivibrio fischeri↗

PubMed1996

Possibilities of using neural networks for ECG classification.

Some characteristics of the neural network approach have been tested and validated for the particular problem of diagnostic classification in the field of computerized electrocardiography. Two different databases have been used for the evaluation process: CORDA, developed by the Medical Informatics Department of the University of Leuven, and ECG-UCL, developed by the Cliniques Universitaires Saint-Luc, Université Catholique de Louvain. Electrocardiographic signals classified on the basis of electrocardiographic independent clinical data, with a single diagnosis and no conduction abnormalities, have been considered. Seven diagnostic classes have been taken into account, including the different locations of ventricular hypertrophy and myocardial infarction. Two architectures of neural networks have been analyzed in detail considering three aspects: the normalization process, pruning techniques, and fuzzy preprocessing by the use of radial basis functions. The comparison of the results obtained with the two databases will be discussed in detail.

Algorithms↗

PubMed2000

Approximation of continuous and discontinuous mappings by a growing neural RBF-based algorithm.

In this paper a neural network for approximating continuous and discontinuous mappings is described. The activation functions of the hidden nodes are the Radial Basis Functions (RBF) whose variances are learnt by means of an evolutionary optimization strategy. A new incremental learning strategy is used in order to improve the net performances. The learning strategy is able to save computational time because of the selective growing of the net structure and the capability of the learning algorithm to keep the effects of the activation functions local. Further, it does not require high order derivatives. An analysis of the learning capabilities and a comparison of the net performances with other approaches reported in literature have been performed. It is shown that the resulting network improves the approximation results reported for continuous mappings and for those exhibiting a finite number of discontinuities.

Algorithms↗

PubMed2002

A general framework for neural network models on censored survival data.

Flexible parametric techniques for regression analysis, such as those based on feed forward artificial neural networks (FFANNs), can be useful for the statistical analysis of censored time data. These techniques are of particular interest for the study of the outcome dependence from several variables measured on a continuous scale, since they allow for the detection of complex non-linear and non-additive effects. Few efforts have been made until now to account for censored times in FFANNs. In the attempt to fill this gap, specific error functions and data representation will be introduced for multilayer perceptron and radial basis function extensions of generalized linear models for survival data.

Humans↗

PubMed2005

An artificial neural network for predicting the incidence of radiation pneumonitis.

A method to predict radiation-induced pneumonitis (RP) using an artificial neural network (ANN) was investigated. A retrospective study was applied to the clinical data from 142 patients who have been treated with three-dimensional conformal radiotherapy for tumors in the thoracic region. These data were classified, based on their treatment outcome, into two patient clusters: with RP (Np=26) and without RP (Np= 116). An ANN was designed as a classifier. To perform the classification, a patient-treatment outcome with RP was assigned a value of 1, and a patient treatment outcome without RP was assigned a value of -1. The input of the ANN was limited to the patient lung dose-volume data only. A volume vector (VD) that describes patient lung subvolumes receiving more than a set of threshold doses was used as the network input variable. A zero value was used as the threshold to set the output value into -1 or 1. Three ANNs (ANN_1, ANN_2, and ANN_3), each with three layers, were trained to perform this classification function and to show the effect of training data on the ANN performance. Radial basis function was applied as the hidden layer neuron activation function and a sigmoid function was selected as the output layer neuron function. Backpropagation with a conjugate gradient algorithm was used to train the network. ANN_1 was trained and tested by using the leave-one-out method. ANN_2 was trained by randomly selecting 2/3 of the patient data, and tested by the remaining 1/3 of the data. ANN_3 was trained by a user selecting 2/3 of the patient data, and tested by the remaining 1/3 of the data. The predictive accuracy was verified as the area under a receiver operator characteristic (ROC) curve. The correct classification rates of 73% for RP cases, and 99% for non-RP cases were obtained from ANN_1. The corresponding correct classification rates of 44% for RP cases, and 89% for non-RP cases were obtained from ANN_2. From the ANN_3 test phase, the corresponding correct classification rates of 55% for RP cases, and 95% non-RP cases were achieved. The area under ROC curve was 0.85+/-0.05, 0.68+/-0.10, and 0.81+/-0.09 for ANN_1, ANN _2, and ANN_3, respectively, within its asymmetric 95% confidence interval. The sensitivity was 95%, 57%, and 71%, and the specificity was 94%, 88%, and 90% for ANN_1, ANN_2, and ANN_3, respectively. Preliminary results suggest that the ANN approach provides a useful tool for the prediction of radiation-induced lung pneumonitis, using the patient lung dose-volume information.

Algorithms↗

PubMed1998

Neural predictive controller for insulin delivery using the subcutaneous route.

A neural predictive controller for closed-loop control of glucose using subcutaneous (s.c.) tissue glucose measurement and s.c. infusion of monomeric insulin analogs was developed and evaluated in a simulation study. The proposed control strategy is based on off-line system identification using neural networks (NN's) and nonlinear model predictive controller design. The system identification framework combines the concept of nonlinear autoregressive model with exogenous inputs (NARX) system representation, regularization approach for constructing radial basis function NN's, and validation methods for nonlinear systems. Numerical studies on system identification and closed-loop control of glucose were carried out using a comprehensive model of glucose regulation and a pharmacokinetic model for the absorption of monomeric insulin analogs from the s.c. depot. The system identification procedure enabled construction of a parsimonious network from the simulated data, and consequently, design of a controller using multiple-step-ahead predictions of the previously identified model. According to the simulation results, stable control is achievable in the presence of large noise levels, for unknown or variable time delays as well as for slow time variations of the controlled process. However, the control limitations due to the s.c. insulin administration makes additional action from the patient at meal time necessary.

Algorithms↗

PubMed2006

Lidar detection of underwater objects using a neuro-SVM-based architecture.

This paper presents a neural network architecture using a support vector machine (SVM) as an inference engine (IE) for classification of light detection and ranging (Lidar) data. Lidar data gives a sequence of laser backscatter intensities obtained from laser shots generated from an airborne object at various altitudes above the earth surface. Lidar data is pre-filtered to remove high frequency noise. As the Lidar shots are taken from above the earth surface, it has some air backscatter information, which is of no importance for detecting underwater objects. Because of these, the air backscatter information is eliminated from the data and a segment of this data is subsequently selected to extract features for classification. This is then encoded using linear predictive coding (LPC) and polynomial approximation. The coefficients thus generated are used as inputs to the two branches of a parallel neural architecture. The decisions obtained from the two branches are vector multiplied and the result is fed to an SVM-based IE that presents the final inference. Two parallel neural architectures using multilayer perception (MLP) and hybrid radial basis function (HRBF) are considered in this paper. The proposed structure fits the Lidar data classification task well due to the inherent classification efficiency of neural networks and accurate decision-making capability of SVM. A Bayesian classifier and a quadratic classifier were considered for the Lidar data classification task but they failed to offer high prediction accuracy. Furthermore, a single-layered artificial neural network (ANN) classifier was also considered and it failed to offer good accuracy. The parallel ANN architecture proposed in this paper offers high prediction accuracy (98.9%) and is found to be the most suitable architecture for the proposed task of Lidar data classification.

Algorithms↗

PubMed2000

Information complexity of neural networks.

This paper studies the question of lower bounds on the number of neurons and examples necessary to program a given task into feed forward neural networks. We introduce the notion of information complexity of a network to complement that of neural complexity. Neural complexity deals with lower bounds for neural resources (numbers of neurons) needed by a network to perform a given task within a given tolerance. Information complexity measures lower bounds for the information (i.e. number of examples) needed about the desired input-output function. We study the interaction of the two complexities, and so lower bounds for the complexity of building and then programming feed-forward nets for given tasks. We show something unexpected a priori--the interaction of the two can be simply bounded, so that they can be studied essentially independently. We construct radial basis function (RBF) algorithms of order n3 that are information-optimal, and give example applications.

Electronic Data Processing↗

PubMed2005

Evolutionary optimization of radial basis function classifiers for data mining applications.

In many data mining applications that address classification problems, feature and model selection are considered as key tasks. That is, appropriate input features of the classifier must be selected from a given (and often large) set of possible features and structure parameters of the classifier must be adapted with respect to these features and a given data set. This paper describes an evolutionary algorithm (EA) that performs feature and model selection simultaneously for radial basis function (RBF) classifiers. In order to reduce the optimization effort, various techniques are integrated that accelerate and improve the EA significantly: hybrid training of RBF networks, lazy evaluation, consideration of soft constraints by means of penalty terms, and temperature-based adaptive control of the EA. The feasibility and the benefits of the approach are demonstrated by means of four data mining problems: intrusion detection in computer networks, biometric signature verification, customer acquisition with direct marketing methods, and optimization of chemical production processes. It is shown that, compared to earlier EA-based RBF optimization techniques, the runtime is reduced by up to 99% while error rates are lowered by up to 86%, depending on the application. The algorithm is independent of specific applications so that many ideas and solutions can be transferred to other classifier paradigms.

Algorithms↗

PubMed2002

Minimum description length neural networks for time series prediction.

Artificial neural networks (ANN) are typically composed of a large number of nonlinear functions (neurons) each with several linear and nonlinear parameters that are fitted to data through a computationally intensive training process. Longer training results in a closer fit to the data, but excessive training will lead to overfitting. We propose an alternative scheme that has previously been described for radial basis functions (RBF). We show that fundamental differences between ANN and RBF make application of this scheme to ANN nontrivial. Under this scheme, the training process is replaced by an optimal fitting routine, and overfitting is avoided by controlling the number of neurons in the network. We show that for time series modeling and prediction, this procedure leads to small models (few neurons) that mimic the underlying dynamics of the system well and do not overfit the data. We apply this algorithm to several computational and real systems including chaotic differential equations, the annual sunspot count, and experimental data obtained from a chaotic laser. Our experiments indicate that the structural differences between ANN and RBF make ANN particularly well suited to modeling chaotic time series data.

Journal Article↗

PubMed2006

Qualitative identification of tea categories by near infrared spectroscopy and support vector machine.

Near-infrared (NIR) spectroscopy has been successfully utilized for the rapid identification of green, black and Oolong tea. The spectral features of each tea category are reasonably differentiated in the NIR region, and the spectral differences provided enough qualitative spectral information for the identification of tea. Support vector machine (SVM) as the pattern recognition was applied to identify three tea categories in this study. The top five principal components (PCs) were extracted as the input of SVM classifiers by principal component analysis (PCA). The RBF SVM classifiers and the polynomial SVM classifiers were studied comparatively in this experiment. The best experimental results were obtained using the radial basis function (RBF) SVM classifier with sigma=0.5. The accuracies of identification were all more than 90% for three tea categories. Finally, compared with the back propagation artificial neural network (BP-ANN) approach, SVM algorithm showed its excellent generalization for identification results. The overall results show that NIR spectroscopy combined with SVM can be efficiently utilized for rapid and simple identification of the tea categories.

Pattern Recognition, Automated↗

PubMed2001

The constraint based decomposition (CBD) training architecture.

The Constraint Based Decomposition (CBD) is a constructive neural network technique that builds a three or four layer network, has guaranteed convergence and can deal with binary, n-ary, class labeled and real-value problems. CBD is shown to be able to solve complicated problems in a simple, fast and reliable manner. The technique is further enhanced by two modifications (locking detection and redundancy elimination) which address the training speed and the efficiency of the internal representation built by the network. The redundancy elimination aims at building more compact architectures while the locking detection aims at improving the training speed. The computational cost of the redundancy elimination is negligible and this enhancement can be used for any problem. However, the computational cost of the locking detection is exponential in the number of dimensions and should only be used in low dimensional spaces. The experimental results show the performance of the algorithm presented in a series of classical benchmark problems including the 2-spiral problem and the Iris, Wine, Glass, Lenses, Ionosphere, Lung cancer, Pima Indians, Bupa, TicTacToe, Balance and Zoo data sets from the UCI machine learning repository. CBD's generalization accuracy is compared with that of C4.5, C4.5 with rules, incremental decision trees, oblique classifiers, linear machine decision trees, CN2, learning vector quantization (LVQ), backpropagation, nearest neighbor, Q* and radial basis functions (RBFs). CBD provides the second best average accuracy on the problems tested as well as the best reliability (the lowest standard deviation).

Algorithms↗

PubMed2001

Algebraic geometrical methods for hierarchical learning machines.

Hierarchical learning machines such as layered perceptrons, radial basis functions, Gaussian mixtures are non-identifiable learning machines, whose Fisher information matrices are not positive definite. This fact shows that conventional statistical asymptotic theory cannot be applied to neural network learning theory, for example either the Bayesian a posteriori probability distribution does not converge to the Gaussian distribution, or the generalization error is not in proportion to the number of parameters. The purpose of this paper is to overcome this problem and to clarify the relation between the learning curve of a hierarchical learning machine and the algebraic geometrical structure of the parameter space. We establish an algorithm to calculate the Bayesian stochastic complexity based on blowing-up technology in algebraic geometry and prove that the Bayesian generalization error of a hierarchical learning machine is smaller than that of a regular statistical model, even if the true distribution is not contained in the parametric model.

Algorithms↗

PubMed2004

Adaptive stochastic resonance in noisy neurons based on mutual information.

Noise can improve how memoryless neurons process signals and maximize their throughput information. Such favorable use of noise is the so-called "stochastic resonance" or SR effect at the level of threshold neurons and continuous neurons. This paper presents theoretical and simulation evidence that 1) lone noisy threshold and continuous neurons exhibit the SR effect in terms of the mutual information between random input and output sequences, 2) a new statistically robust learning law can find this entropy-optimal noise level, and 3) the adaptive SR effect is robust against highly impulsive noise with infinite variance. Histograms estimate the relevant probability density functions at each learning iteration. A theorem shows that almost all noise probability density functions produce some SR effect in threshold neurons even if the noise is impulsive and has infinite variance. The optimal noise level in threshold neurons also behaves nonlinearly as the input signal amplitude increases. Simulations further show that the SR effect persists for several sigmoidal neurons and for Gaussian radial-basis-function neurons.

Algorithms↗

PubMed2003

Fault detection and classification in chemical processes based on neural networks with feature extraction.

Feed forward neural networks are investigated here for fault diagnosis in chemical processes, especially batch processes. The use of the neural model prediction error as the residual for fault diagnosis of sensor and component is analyzed. To reduce the training time required for the neural process model, an input feature extraction process for the neural model is implemented. An additional radial basis function neural classifier is developed to isolate faults from the residual generated, and results are presented to demonstrate the satisfactory detection and isolation of faults using this approach.

Algorithms↗

PubMed1998

The diabolo classifier

We present a new classification architecture based on autoassociative neural networks that are used to learn discriminant models of each class. The proposed architecture has several interesting properties with respect to other model-based classifiers like nearest-neighbors or radial basis functions: it has a low computational complexity and uses a compact distributed representation of the models. The classifier is also well suited for the incorporation of a priori knowledge by means of a problem-specific distance measure. In particular, we will show that tangent distance (Simard, Le Cun, & Denker, 1993) can be used to achieve transformation invariance during learning and recognition. We demonstrate the application of this classifier to optical character recognition, where it has achieved state-of-the-art results on several reference databases. Relations to other models, in particular those based on principal component analysis, are also discussed.

Journal Article↗