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 109 records · Page 6Linked to original sources

PubMed1995

More about the difference between men and women: evidence from linear neural networks and the principal-component approach.

The ability of a statistical/neural network to classify faces by sex by means of a pixel-based representation has not been fully investigated. Simulations with pixel-based codes have provided sex-classification results that are less impressive than those reported for measurement-based codes. In no case, however, have the reported pixel-based simulations been optimized for the task of classifying faces by sex. A series of simulations is described in which four network models were applied to the same pixel-based face code. These simulations involved either a radial basis function network or a perceptron as a classifier, preceded or not by a preprocessing step of eigendecomposition. It is shown that performance comparable to that of the measurement-based models can be achieved with pixel-based input (90%) when the data are preprocessed. The effect of the eigendecomposition preprocessing of the faces is then compared with spatial-frequency analysis of face images and analyzed in terms of the perceptual information it captures. It is shown that such an examination may offer insight into the facial aspects important to the sex-classification process. Finally, the contribution of hair information to the performance of the model is evaluated. It is shown that, although the hair contributes to the sex-classification process, it is not the only important contributor.

Algorithms↗

PubMed2001

Upper bound of the expected training error of neural network regression for a Gaussian noise sequence.

In neural network regression problems, often referred to as additive noise models, NIC (Network Information Criterion) has been proposed as a general model selection criterion to determine the optimal network size with high generalization performance. Although NIC has been derived using asymptotic expansion, it has been pointed out that this technique cannot be applied under the assumption that a target function is in a family of assumed networks and the family is not minimal for representing the target true function, i.e. the overrealizable case, in which NIC reduces to the well-known AIC (Akaike Information Criterion) and others depending on a loss function. Because NIC is the unbiased estimator of generalization error based on training error, it is required to derive the expectations of errors for neural networks for such cases. This paper gives upper bounds of the expectations of training errors with respect to the distribution of training data, which we call the expected training error, for some types of networks under the squared error loss. In the overrealizable case, because the errors are determined by fitting properties of networks to noise components, including in data, the target set of data is taken to be a Gaussian noise sequence. For radial basis function networks and 3-layered neural networks with bell shaped activation function in the hidden layer, the expected training error is bounded above by sigma2* - 2nsigma2*logT/T, where sigma2* is the variance of noise, n is the number of basis functions or the number of hidden units and T is the number of data. Furthermore, for 3-layered neural networks with sigmoidal activation function in the hidden layer, we obtained the upper bound of sigma2* - O(log T/T) when n > 2. If the number of data is large enough, these bounds of the expected training error are smaller than sigma2* - N(n)sigma2*/T as evaluated in NIC, where N(n) is the number of all network parameters.

Analysis of Variance↗

PubMed2001

[Application of FAM networks in recommendation of mobile phase for RP-HPLC].

AIM: To establish expert system to recommend solvent strength in RP-HPLC by using FAM (fuzzy associate memorizer) networks. METHODS: Symbolic rules reflecting the quantitative relationship among molecular structure, capacity factors and solvent strength in RP-HPLC were extracted from trained radial basis function networks. Then FAM networks consisting of these rules were built to recommend mobile phase strength for RP-HPLC. RESULTS: The validation results of the system by monocomponent and mutilcomponent drug samples were satisfied. CONCLUSION: The mobile phase recommendation system for RP-HPLC analysis of drugs showed reliable performance.

Chromatography, High Pressure Liquid↗

PubMed2005

Modeling and output tracking of transverse flux permanent magnet machines using high gain observer and RBF neural network.

This paper deals with modeling and adaptive output tracking of a transverse flux permanent magnet machine as a nonlinear system with unknown nonlinearities by utilizing high gain observer and radial basis function networks. The proposed model is developed based on computing the permeance between rotor and stator using quasiflux tubes. Based on this model, the techniques of feedback linearization and Hinfinity control are used to design an adaptive control law for compensating the unknown nonlinear parts, such as the effect of cogging torque, as a disturbance is decreased onto the rotor angle and angular velocity tracking performances. Finally, the capability of the proposed method in tracking both the angle and the angular velocity is shown in the simulation results.

Algorithms↗

PubMed2000

RBF networks for source localization in quantitative electrophysiology.

The backpropagation neural network methods have been proposed recently to solve the inverse problem in quantitative electrophysiology. A major advantage of the technique is that once a neural network is trained, it no longer requires iterations or access to sophisticated computations. We propose to use RBF networks for source localization in the brain, and systematically compare their performance to those of Levenberg-Marquardt (LM) algorithms. We show the use of two types of Radial Basis Function Networks (RBF) network: a classic network with fixed number of hidden layer neurons and an improved network, Minimal Resource Allocation Network (MRAN), recently proposed by one of the authors, capable for dynamically configuring its structure so as to obtain a compact topology to match the data presented to it.

Algorithms↗

PubMed2002

Neural networks for estimating intrinsic dimension.

We consider the problem of feature extraction and determination of intrinsic dimensionality of observation data. One of the common approaches to this problem is to use autoassociative neural networks with a "bottleneck" projecting layer. We propose a different approach in which a neural network performs a topological mapping that creates a nonlinear lower-dimensional projection of the data. The mapping preserves relative distances of neighbors. This technique can be efficiently implemented with the help of radial basis function networks, and it is significantly faster than training an autoassotiative network. We show that the proposed technique can be used for estimating the dimension of minimal mathematical model from time series data.

Journal Article↗

PubMed1994

On using feedforward neural networks for clinical diagnostic tasks.

In this paper we present an extensive comparison between several feedforward neural network types in the context of a clinical diagnostic task, namely the detection of coronary artery disease (CAD) using planar thallium-201 dipyridamole stress-redistribution scintigrams. We introduce results from well-known (e.g. multilayer perceptrons or MLPs, and radial basis function networks or RBFNs) as well as novel neural network techniques (e.g. conic section function networks) which demonstrate promising new routes for future applications of neural networks in medicine, and elsewhere. In particular we show that initializations of MLPs and conic section function networks--which can learn to behave more like an MLP or more like an RBFN--can lead to much improved results in rather difficult diagnostic tasks.

Coronary Disease↗

PubMedDate not supplied

ECG pattern recognition and classification using non-linear transformations and neural networks: a review.

The most widely used signal in clinical practice is the ECG. ECG conveys information regarding the electrical function of the heart, by altering the shape of its constituent waves, namely the P, QRS, and T waves. Thus, the required tasks of ECG processing are the reliable recognition of these waves, and the accurate measurement of clinically important parameters measured from the temporal distribution of the ECG constituent waves. In this paper, we shall review some current trends on ECG pattern recognition. In particular, we shall review non-linear transformations of the ECG, the use of principal component analysis (linear and non-linear), ways to map the transformed data into n-dimensional spaces, and the use of neural networks (NN) based techniques for ECG pattern recognition and classification. The problems we shall deal with are the QRS/PVC recognition and classification, the recognition of ischemic beats and episodes, and the detection of atrial fibrillation. Finally, a generalised approach to the classification problems in n-dimensional spaces will be presented using among others NN, radial basis function networks (RBFN) and non-linear principal component analysis (NLPCA) techniques. The performance measures of the sensitivity and specificity of these algorithms will also be presented using as training and testing data sets from the MIT-BIH and the European ST-T databases.

Algorithms↗

PubMed1995

A perspective and critique of adaptive neurofuzzy systems used for modelling and control applications.

This paper outlines some of the theoretical and practical developments being made in neurofuzzy systems. As the name suggests, neurofuzzy networks were developed by fusing the ideas that originated in the fields of neural and fuzzy systems. A neurofuzzy network attempts to combine the transparent, linguistic, symbolic representation associated with fuzzy logic with the architecture and learning rules commonly used in neural networks. These hybrid structures have both a qualitative and a quantitative interpretation and can overcome some of the difficulties associated with solely neural algorithms which can usually be regarded as black box mappings, and with fuzzy systems where few modelling and learning theories existed. Both B-spline and Gaussian Radial Basis Function networks can be regarded as neurofuzzy systems and soft inductive learning algorithms can be used to extract unknown, qualitative information about the relationships contained in the training data. In a similar manner, qualitative rules or information about the network's structure can be used to initialise the system. These areas, coupled with the extensive work being carried out on theoretically analysing their modelling, convergence and stability properties means that this research topic is highly applicable in "intelligent" modelling and control problems. Apart from outlining this work, the paper also discusses a wide variety of open research questions and suggests areas where new efforts may be fruitfully applied.

Algorithms↗

PubMed2000

Progressive cross-section display of 3D medical images.

The paper presents a hierarchical coding algorithm for 3D medical images based upon hierarchical interpolation with radial basis function networks. By using the properties of the Kronecker product, the computation of the network parameters and the 3D image reconstruction are efficiently done in (L4) computation time and O(L3) storage space, when applied to 3D images of size (L x L x L). A further reduction in processing time is accomplished by using sparse matrix techniques. The salient features of the proposed coding method are that arbitrary cross-section images can be progressively displayed without reconstruction of the whole 3D image; the first image reconstruction starts as soon as the first data transmission has been completed; no expanding procedure is required in 3D image reconstruction, and the blocking effects are not apparent even in the lowest-resolution image. Experimental results using two 3D MRI images, of size (128 x 18 x 64) and with 8-bit grey levels, show that the coding performance is better than that of the 3D DCT coding by about 0.25 bits pixel-1 at higher bit rates, and that the new cross-section display method synthesises the coarsest (finest) section image about six (three) times faster than the standard method that requires the whole 3D image reconstruction.

Algorithms↗

PubMed2005

Multi-space classification for predicting GPCR-ligands.

A classification of molecules depends on the descriptor set which is used to represent the compounds, and each descriptor could be regarded as one perception of a molecule. In this study we show that a combination of several classifiers that are grounded on separate descriptor sets can be superior to a single classifier that was built using all available descriptors. The task of predicting ligands of G-protein coupled receptors (GPCR) served as an example application. The perceptron, multilayer neural networks, and radial basis function (RBF) networks were employed for prediction. We developed classifiers with and without descriptor selection. Prediction accuracy was assessed by the area under the receiver operating characteristic (ROC) curve. In the case with descriptor selection both the selection and the rank order of the descriptors depended on the type and topology of the neural networks. We demonstrate that the overall prediction accuracy of the system can be improved by joining neural network classifiers of different type and topology using a "jury network" that is trained to evaluate the predictions from the individual classifiers. Seventy-one percent correct prediction of GPCR ligands was obtained.

Ligands↗

PubMed2001

Optimal control by least squares support vector machines.

Support vector machines have been very successful in pattern recognition and function estimation problems. In this paper we introduce the use of least squares support vector machines (LS-SVM's) for the optimal control of nonlinear systems. Linear and neural full static state feedback controllers are considered. The problem is formulated in such a way that it incorporates the N-stage optimal control problem as well as a least squares support vector machine approach for mapping the state space into the action space. The solution is characterized by a set of nonlinear equations. An alternative formulation as a constrained nonlinear optimization problem in less unknowns is given, together with a method for imposing local stability in the LS-SVM control scheme. The results are discussed for support vector machines with radial basis function kernel. Advantages of LS-SVM control are that no number of hidden units has to be determined for the controller and that no centers have to be specified for the Gaussian kernels when applying Mercer's condition. The curse of dimensionality is avoided in comparison with defining a regular grid for the centers in classical radial basis function networks. This is at the expense of taking the trajectory of state variables as additional unknowns in the optimization problem, while classical neural network approaches typically lead to parametric optimization problems. In the SVM methodology the number of unknowns equals the number of training data, while in the primal space the number of unknowns can be infinite dimensional. The method is illustrated both on stabilization and tracking problems including examples on swinging up an inverted pendulum with local stabilization at the endpoint and a tracking problem for a ball and beam system.

Feedback↗

PubMedDate not supplied

Electronic nose based tea quality standardization.

In this paper we have used a metal oxide sensor (MOS) based electronic nose (EN) to analyze five tea samples with different qualities, namely, drier month, drier month again over-fired, well fermented normal fired in oven, well fermented overfired in oven, and under fermented normal fired in oven. The flavour of tea is determined mainly by its taste and smell, which is generated by hundreds of Volatile Organic Compounds (VOCs) and Non-Volatile Organic Compounds present in tea. These VOCs are present in different ratios and determine the quality of the tea. For example Assamica (Sri Lanka and Assam Tea) and Assamica Sinesis (Darjeeling and Japanese Tea) are two different species of tea giving different flavour notes. Tea flavour is traditionally measured through the use of a combination of conventional analytical instrumentation and human or ganoleptic profiling panels. These methods are expensive in terms of time and labour and also inaccurate because of a lack of either sensitivity or quantitative information. In this paper an investigation has been made to determine the flavours of different tea samples using an EN and to explore the possibility of replacing existing analytical and profiling panel methods. The technique uses an array of 4 MOSs, each of, which has an electrical resistance that has partial sensitivity to the headspace of tea. The signals from the sensor array are then conditioned by suitable interface circuitry. The data were processed using Principal Components Analysis (PCA), Fuzzy C Means algorithm (FCM). We also explored the use of a Self-Organizing Map (SOM) method along with a Radial Basis Function network (RBF) and a Probabilistic Neural Network classifier. Using FCM and SOM feature extraction techniques along with RBF neural network we achieved 100% correct classification for the five different tea samples with different qualities. These results prove that our EN is capable of discriminating between the flavours of teas manufactured under different processing conditions, viz. over-fermented, over-fired, under fermented, etc.

Chemoreceptor Cells↗

PubMedDate not supplied

Myocardium extraction in positron emission tomography based on soft computing.

This paper presents an efficient and accurate approach to myocardium extraction in Positron Emission Tomography (PET) images based on a careful application of soft computing techniques. PET images present a noisy background, making the automatic myocardium extraction and uptake quantification a difficult task. In this work a Self Organized Radial Basis Function Network (SRBFN) is designed to focus on the myocardium in an iterative process until the total extraction of the myocardium from the noisy background is achieved. Fuzzy sets and fuzziness measures are used to compute the error of the network. The method was tested on a set of nine images of different patients and its effectiveness is illustrated in two patients showing tracer uptake defects.

Fluorodeoxyglucose F18↗

PubMedDate not supplied

Support vector machines-based quantitative structure-property relationship for the prediction of heat capacity.

The support vector machine (SVM), as a novel type of learning machine, for the first time, was used to develop a Quantitative Structure-Property Relationship (QSPR) model of the heat capacity of a diverse set of 182 compounds based on the molecular descriptors calculated from the structure alone. Multiple linear regression (MLR) and radial basis function networks (RBFNNs) were also utilized to construct quantitative linear and nonlinear models to compare with the results obtained by SVM. The root-mean-square (rms) errors in heat capacity predictions for the whole data set given by MLR, RBFNNs, and SVM were 4.648, 4.337, and 2.931 heat capacity units, respectively. The prediction results are in good agreement with the experimental value of heat capacity; also, the results reveal the superiority of the SVM over MLR and RBFNNs models.

Journal Article↗

PubMed2006

Error criteria for cross validation in the context of chaotic time series prediction.

The prediction of a chaotic time series over a long horizon is commonly done by iterating one-step-ahead prediction. Prediction can be implemented using machine learning methods, such as radial basis function networks. Typically, cross validation is used to select prediction models based on mean squared error. The bias-variance dilemma dictates that there is an inevitable tradeoff between bias and variance. However, invariants of chaotic systems are unchanged by linear transformations; thus, the bias component may be irrelevant to model selection in the context of chaotic time series prediction. Hence, the use of error variance for model selection, instead of mean squared error, is examined. Clipping is introduced, as a simple way to stabilize iterated predictions. It is shown that using the error variance for model selection, in combination with clipping, may result in better models.

Journal Article↗

PubMed2002

Fetal lung maturity analysis using ultrasound image features.

This pilot study was carried out to find the feasibility of analyzing the maturity of the fetal lung using ultrasound images. Data were collected from normal pregnant women at intervals of two weeks from the gestation age of 24 to 38 weeks. Images were acquired at two centers located at different geographical locations. The total data acquired consisted of 750 images of immature and 250 images of mature class. A region of interest of 64 x 64 pixels was used for extracting the features. Various textural features were computed from the fetal lung and liver images. The ratios of fetal lung to liver feature values were investigated as possible indexes for classifying the images into those from mature (reduced pulmonary risk) and immature (possible pulmonary risk) lung. The features used are fractal dimension, lacunarity, and features derived from the histogram of the images. The following classifiers were used to classify the fetal lung images as belonging to mature or immature lung: nearest neighbor, k-nearest neighbor, modified k-nearest neighbor, multilayer perceptron, radial basis function network, and support vector machines. The classification accuracy obtained for the testing set ranges from 73% to 96%.

Female↗

PubMed2006

Kernel classifier construction using orthogonal forward selection and boosting with Fisher ratio class separability measure.

A greedy technique is proposed to construct parsimonious kernel classifiers using the orthogonal forward selection method and boosting based on Fisher ratio for class separability measure. Unlike most kernel classification methods, which restrict kernel means to the training input data and use a fixed common variance for all the kernel terms, the proposed technique can tune both the mean vector and diagonal covariance matrix of individual kernel by incrementally maximizing Fisher ratio for class separability measure. An efficient weighted optimization method is developed based on boosting to append kernels one by one in an orthogonal forward selection procedure. Experimental results obtained using this construction technique demonstrate that it offers a viable alternative to the existing state-of-the-art kernel modeling methods for constructing sparse Gaussian radial basis function network classifiers that generalize well.

Algorithms↗