Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Neural network”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

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

At least 1,333 records · Page 74Linked to original sources
PubMed2005

[Algorithms of artificial neural networks--practical application in medical science].

Artificial Neural Networks (ANN) may be a tool alternative and complementary to typical statistical analysis. However, in spite of many computer applications of various ANN algorithms ready for use, artificial intelligence is relatively rarely applied to data processing. This paper presents practical aspects of scientific application of ANN in medicine using widely available algorithms. Several main steps of analysis with ANN were discussed starting from material selection and dividing it into groups, to the quality assessment of obtained results at the end. The most frequent, typical reasons for errors as well as the comparison of ANN method to the modeling by regression analysis were also described.

Algorithms↗
PubMed2004

Robust and adaptive backstepping control for nonlinear systems using RBF neural networks.

In this paper, two different backstepping neural network (NN) control approaches are presented for a class of affine nonlinear systems in the strict-feedback form with unknown nonlinearities. By a special design scheme, the controller singularity problem is avoided perfectly in both approaches. Furthermore, the closed loop signals are guaranteed to be semiglobally uniformly ultimately bounded and the outputs of the system are proved to converge to a small neighborhood of the desired trajectory. The control performances of the closed-loop systems can be shaped as desired by suitably choosing the design parameters. Simulation results obtained demonstrate the effectiveness of the approaches proposed. The differences observed between the inputs of the two controllers are analyzed briefly.

Neural Networks, Computer↗
PubMedDate not supplied

Understanding birthing mode decision making using artificial neural networks.

BACKGROUND: This study examined obstetricians' decisions to perform or not to perform cesarean sections. The aim was to determine whether an artificial neural network could be constructed to accurately and reliably predict the birthing mode decisions of expert clinicians and to elucidate which factors were most important in deciding the birth mode. METHODS: Mothers with singleton, live births who were privately insured, nonclinic, non-Medicaid patients at a major tertiary care private hospital were included in the study (N = 1508). These mothers were patients of 2 physician groups: a 7-obstetrician multispecialtygroup practice and a physician group of 79 independently practicing obstetricians affiliated with the same hospital. A feedforward, multilayer artificial neural network (ANN) was developed and trained. It was then tested and optimized until the most parsimonious network was identified that retained a similar level of predictive power and classification accuracy. The performance of this network was further optimized using the methods of receiver operating characteristic (ROC) analysis and information theory to find the cutoff that maximized the information gain. The performance of the final ANN at this cutoff was measured using sensitivity, specificity, classification accuracy, area under the ROC curve, and maximum information gain. RESULTS: The final neural network had excellent predictive accuracy for the birthing mode (classification accuracy = 83.5%; area under the ROC curve = 0.924; maximum information = 40.4% of a perfect diagnostic test). CONCLUSION: This study demonstrated that a properly optimized ANN is able to accurately predict the birthing mode decisions of expert clinicians. In addition to previously identified clinical factors (cephalopelvic disproportion, maternal medical condition necessitating a cesarean section, arrest of labor, malpresentation of the baby, fetal distress, andfailed induction), nonclinical factors such as the mothers' views on birthing mode were also found to be important in determining the birthing mode.

Decision Making↗
PubMed1996

The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction.

Recurrent neural networks (RNNs) can learn to perform finite state computations. It is shown that an RNN performing a finite state computation must organize its state space to mimic the states in the minimal deterministic finite state machine that can perform that computation, and a precise description of the attractor structure of such systems is given. This knowledge effectively predicts activation space dynamics, which allows one to understand RNN computation dynamics in spite of complexity in activation dynamics. This theory provides a theoretical framework for understanding finite state machine (FSM) extraction techniques and can be used to improve training methods for RNNs performing FSM computations. This provides an example of a successful approach to understanding a general class of complex systems that has not been explicitly designed, e.g., systems that have evolved or learned their internal structure.

Neural Networks, Computer↗
PubMed2004

Probing Norwalk-like virus presence in shellfish, using artificial neural networks.

A database was examined using artificial neural network (ANN) models to investigate the efficacy of predicting PCR-identified Norwalk-like virus presence and absence in shellfish. The relative importance of variables in the model and the predictive power obtained by application of ANN modelling methods were compared with previously developed logistic regression models. In addition, two country-specific datasets were analysed separately with ANN models to determine if the relative importance of the input variables was similar for geographically diverse regions. The results of this analysis found that ANN models predicted Norwalk-like virus presence and absence in shellfish with equivalent, and better, precision than logistic regression models. For overall classification performance, ANN modelling had a rate of 93%, vs 75% for the logistic regression. ANN models were able to illuminate the site-specific relationships between indicators and pathogens.

Databases, Factual↗
PubMed2000

Development of a neural network heating controller for solar buildings.

Artificial neural networks (ANN's) are more and more widely used in energy management processes. ANN's can be very useful in optimizing the energy demand of buildings, especially of those of high thermal inertia. These include the so-called solar buildings. For those buildings, a controller able to forecast not only the energy demand but also the weather conditions can lead to energy savings while maintaining thermal comfort. In this paper, such an ANN controller is proposed. It consists of a meteorological module, forecasting the ambient temperature and solar irradiance, the heating energy switch predictor module and the indoor temperature-defining module. The performance of the controller has been tested both experimentally and in a building thermal simulation environment. The results showed that the use of the proposed controller can lead to 7.5% annual energy savings in the case of a highly insulated passive solar test cell.

Equipment Design↗
PubMedDate not supplied

Neural network modelling of an electrochemical process.

Artificial Neural Network (ANN) methodology has gained popularity in chemistry in recent years as a result of its ability to solve problems for various purposes. In particular, ANN shows a very high performance in the modelling of the experimental measurements. To this aim, the trained ANN is used to predict unknown values of measurement system. For a given trial set of parameters, the experimental response may be predicted by the model. In recent decades, several investigations were based on the electrooxidation of D-glucose owing to its many applications such as detection systems (glucose sensors), fuel cells and synthesis of economically interesting products. In the present work based on the electrochemical process modelling, the estimation of peak current densities of the D-glucose electrooxidation on palladium electrode in alkaline medium was investigated as a function of potential sweep rate and D-glucose concentration by using a three layer feed-forward ANN with error propagation learning algorithm.

Electrochemistry↗
PubMed1998

The neural network classification of false killer whale (Pseudorca crassidens) vocalizations.

This study reports the use of unsupervised, self-organizing neural network to categorize the repertoire of false killer whale vocalizations. Self-organizing networks are capable of detecting patterns in their input and partitioning those patterns into categories without requiring that the number or types of categories be predefined. The inputs for the neural networks were two-dimensional characterization of false killer whale vocalization, where each vocalization was characterized by a sequence of short-time measurements of duty cycle and peak frequency. The first neural network used competitive learning, where units in a competitive layer distributed themselves to recognize frequently presented input vectors. This network resulted in classes representing typical patterns in the vocalizations. The second network was a Kohonen feature map which organized the outputs topologically, providing a graphical organization of pattern relationships. The networks performed well as measured by (1) the average correlation between the input vectors and the weight vectors for each category, and (2) the ability of the networks to classify novel vocalizations. The techniques used in this study could easily be applied to other species and facilitate the development of objective, comprehensive repertoire models.

Animals↗
PubMed2001

Prediction of retention times for anions in linear gradient elution ion chromatography with hydroxide eluents using artificial neural networks.

The feasibility of using an artificial neural network (ANN) to predict the retention times of anions when eluted from a Dionex AS11 column with linear hydroxide gradients of varying slope was investigated. The purpose of this study was to determine whether an ANN could be used as the basis of a computer-assisted optimisation method for the selection of optimal gradient conditions for anion separations. Using an ANN with a (1, 10, 19) architecture and a training set comprising retention data obtained with three gradient slopes (1.67, 2.50 and 4.00 mM/min) between starting and finishing conditions of 0.5 and 40.0 mM hydroxide, respectively, retention times for 19 analyte anions were predicted for four different gradient slopes. Predicted and experimental retention times for 133 data points agreed to within 0.08 min and percentage normalised differences between the predicted and experimental data averaged 0.29% with a standard deviation of 0.29%. ANNs appear to be a rapid and accurate method for predicting retention times in ion chromatography using linear hydroxide gradients.

Anions↗
PubMed2005

Artificial neural networks for document analysis and recognition.

Artificial neural networks have been extensively applied to document analysis and recognition. Most efforts have been devoted to the recognition of isolated handwritten and printed characters with widely recognized successful results. However, many other document processing tasks, like preprocessing, layout analysis, character segmentation, word recognition, and signature verification, have been effectively faced with very promising results. This paper surveys the most significant problems in the area of offline document image processing, where connectionist-based approaches have been applied. Similarities and differences between approaches belonging to different categories are discussed. A particular emphasis is given on the crucial role of prior knowledge for the conception of both appropriate architectures and learning algorithms. Finally, the paper provides a critical analysis on the reviewed approaches and depicts the most promising research guidelines in the field. In particular, a second generation of connectionist-based models are foreseen which are based on appropriate graphical representations of the learning environment.

Algorithms↗
PubMed2004

Classification of MCA stenosis in diabetes by MLP and RBF neural network.

For the classification of Middle Cerebral Artery (MCA) stenosis, Doppler signals have been received from the diabetes and control group by using 2 MHz Transcranial Doppler. After the Fast Fourier Transform (FFT) analyses of the Doppler signals, Power Spectrum Density (PSD) estimations have been made and Multilayer Perceptron (MLP) and Radial Basis Function (RBF) have been dealt to apply to the neural networks. PSD estimations of Doppler signals received from MCA of 104 subjects have been successfully classified by MLP (correct classification = 94.2%) and RBF (correct classification = 88.4%) neural network. As we have seen in the area under ROC curve (AUC), MLP neural network (AUC = 0.934) has classified more successfully when compared with RBF neural network (AUC = 0.873).

Brain↗
PubMed1996

Visual evoked potential enhancement by an artificial neural network filter.

The application of an artificial neural network filter (ANNF) to estimate the visual evoked potential (VEP) is presented. VEP is the gross electrical response of the brain to visual stimuli. Due to the low SNR, it is difficult to extract response from individual stimulus trials. The ANNF we used estimates the deterministic component of the signal and removes the noise uncorrelated with the stimulus, even when the noise is colored. The ANNF is trained through back-error propagation with a data set consisting of a training signal and a target signal. The training signal is the raw VEP from a single trial having a SNR of about -5 dB, while the target signal has a higher SNR which is achieved by ensemble averaging 100 stimulus trials. Simulated signals were generated to test the performance of the ANNF. Results show that the ANNF could greatly enhance the SNR of the VEP to single visual stimulus. Thus the total number of ensembles is reduced. In clinical applications, the traditional ensemble averaging method requires a hundred ensembles to determine the VEP. When ANNF is used, about 20 ensembles are sufficient for the same purpose.

Adolescent↗
PubMed2003

Uncertainty in the output of artificial neural networks.

Analysis of the performance of artificial neural networks (ANNs) is usually based on aggregate results on a population of cases. In this paper, we analyze ANN output corresponding to the individual case. We show variability in the outputs of multiple ANNs that are trained and "optimized" from a common set of training cases. We predict this variability from a theoretical standpoint on the basis that multiple ANNs can be optimized to achieve similar overall performance on a population of cases, but produce different outputs for the same individual case because the ANNs use different weights. We use simulations to show that the average standard deviation in the ANN output can be two orders of magnitude higher than the standard deviation in the ANN overall performance measured by the Az value. We further show this variability using an example in mammography where the ANNs are used to classify clustered microcalcifications as malignant or benign based on image features extracted from mammograms. This variability in the ANN output is generally not recognized because a trained individual ANN becomes a deterministic model. Recognition of this variability and the deterministic view of the ANN present a fundamental contradiction. The implication of this variability to the classification task warrants additional study.

Algorithms↗
PubMed2000

Artificial neural networks: fundamentals, computing, design, and application.

Artificial neural networks (ANNs) are relatively new computational tools that have found extensive utilization in solving many complex real-world problems. The attractiveness of ANNs comes from their remarkable information processing characteristics pertinent mainly to nonlinearity, high parallelism, fault and noise tolerance, and learning and generalization capabilities. This paper aims to familiarize the reader with ANN-based computing (neurocomputing) and to serve as a useful companion practical guide and toolkit for the ANNs modeler along the course of ANN project development. The history of the evolution of neurocomputing and its relation to the field of neurobiology is briefly discussed. ANNs are compared to both expert systems and statistical regression and their advantages and limitations are outlined. A bird's eye review of the various types of ANNs and the related learning rules is presented, with special emphasis on backpropagation (BP) ANNs theory and design. A generalized methodology for developing successful ANNs projects from conceptualization, to design, to implementation, is described. The most common problems that BPANNs developers face during training are summarized in conjunction with possible causes and remedies. Finally, as a practical application, BPANNs were used to model the microbial growth curves of S. flexneri. The developed model was reasonably accurate in simulating both training and test time-dependent growth curves as affected by temperature and pH.

Humans↗
PubMed1995

Artificial neural networks for multicomponent kinetic determinations.

An artificial neural network (ANN) procedure that uses the scores of a principal component model as input data was tested for calibration in the resolution of binary mixtures from kinetic measurements. The results thus obtained are compared with those provided by partial least-squares (PLS) regression and principal component regression (PCR). The ANN was first applied to simulated single wavelength kinetic curves. The effect of experimental variability was considered by assuming rate constants to fit a normal distribution curve. An amount of instrumental noise was also added to the simulated curves. Both linear and nonlinear systems were tested. Non-linearity was assumed to result from interactions between analytes and modeled by introducing a multiplicative term in the rate equation. The results provided by the three methods on linear systems were comparable; in the presence of interactions between analytes, however, the ANN method clearly outperformed the other two. The ANN method was also used to resolve mixtures of Fe(III), Co(II), and Zn(II) by displacement from their EGTA complexes with 4-(2-pyridylazo)resorcinol (PAR) using a stopped-flow injection assembly including a diode array detector. Preliminary experiments revealed the Co(II) and Zn(II) displacement reactions to be pseudo-first-order and that of Fe(III) to be a multistep process that departed from the linear behavior of the other two. Again, the results obtained with ANN were better than those provided by PCR and PLS.

Calibration↗
PubMed1996

Identification of coherent structures in turbulent shear flows with a fuzzy artmap neural network.

An implementation of a Fuzzy Artmap neural network is used to detect and to identify (recognise) structures (patterns) embedded in the velocity field of a turbulent wake behind a circular cylinder. The net is trained to recognise both clockwise and anticlockwise eddies present in the u and v velocity fields at 420 diameters downstream of the cylinder that generates the wake, using a pre-processed part of the recorded velocity data. The phase relationship that exists between the angles of the velocity vectors of an eddy pattern is used to reduce the number of classes contained in the data, before the start of the training procedure. The net was made stricter by increasing the vigilance parameter within the interval [0.90, 0.95] and a set of net-weights were obtained for each value. Full data files were scanned with the net classifying patterns according to their phase characteristics. The net classifies about 27% of the recorded signals as eddy motions, with the strictest vigilance parameter and without the need to impose external initial templates. Spanwise distances (homogeneous direction of the flow) within the centres of the eddies identified suggest that they form pairs of counter-rotating vortices (double rollers). The number of patterns selected with Fuzzy Artmap is lower than that reported for template matching because the net classifies eddies according to the recirculating pattern present at the core or central region, while template matching extends the region over which correlation between data and template is performed. In both cases, the topology of educed patterns is in agreement.

Air Movements↗
PubMed1995

Prediction of receptor properties and binding affinity of ligands to benzodiazepine/GABAA receptors using artificial neural networks.

To date the use of artificial neural networks (ANNs) in quantitative structure-activity relationship (QSAR) studies has been primarily concerned in comparing the predictive accuracy of the technique using known data sets where the data set parameters had been preselected and optimized for use with other statistical methods. Little effort has been directed at optimizing the input parameters for use with ANNs or exploring other potential strengths of ANNs. In this study, back-propagation ANNs and multilinear regression (MLR) were used to examine the QSAR between substituent constants and random noise at six positions on 57 1,4-benzodiazepin-2-ones (1,4-BZs) and their binding affinities (log IC50) for benzodiazepine GABAA receptor preparations. By using selective pruning and cross-validation techniques, it was found possible to use ANNs to indicate an optimum set of 10 input parameters from a choice of 48 which were then used to train back-propagation ANNs that best predicted the receptor binding affinity with a high correlation between known and predicted data sets. Using the optimum set of input parameters, three-layer ANNs performed no better than the two-layer ANNs which gave marginally better results than MLR. Using the trained ANNs to examine the individual parameters showed that increases in the lipophilicity and F polar value at position 7, F polar value at position 2', and dipole at position 1 on the molecule all enhanced receptor binding affinity of 1,4-BZ ligands. Increases in molar refractivity and resonance parameters at position 1, molar refractivity at positions 6' and 2', Hammet meta constant at position 3', and Hammet para constant at position 8 on the molecule all caused decreases in receptor binding affinity. By considering the optimal ANNs as pharmacophore models representing the internal physicochemical structure of the receptor site, it was found that they could be used to critically examine the properties of the receptor site.

Binding Sites↗
PubMed2004

High-Order Neural Network structure selection for function approximation applications using Genetic Algorithms.

Neural network literature for function approximation is by now sufficiently rich. In its complete form, the problem entails both parametric (i.e., weights determination) and structural learning (i.e., structure selection). The majority of works deal with parametric uncertainty assuming knowledge of the appropriate neural structure. In this paper we present an algorithmic approach to determine the structure of High Order Neural Networks (HONNs), to solve function approximation problems. The method is based on a Genetic Algorithm (GA) and is equipped with a stable update law to guarantee parametric learning. Simulation results on an illustrative example highlight the performance and give some insight of the proposed approach.

Journal Article↗