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 343 records · Page 19Linked to original sources
PubMed1997

An ECG classifier designed using modified decision based neural networks.

In this paper, a neural network based generalized software system is presented for automatic analysis of electrocardiograms (ECGs). The proposed system is capable of intuitively diagnosing the disease from the ECG using the knowledge acquired from the training. A modified decision based neural network which converges in a finite amount of time is employed. The training procedure used automatically varies the size of the network. The system is capable of being trained even without an expert's supervision. The physician can correct the network as and when a misclassification occurs, thus making the system less error-prone as time passes. The proposed system has been tested using an ECG data base representing different cardiological conditions such as bundle branch blocks and infarctions. The system is capable of detecting different types of arrhythmias also.

Algorithms↗
PubMed2006

Implementing Gaussian process inference with neural networks.

Gaussian processes compare favourably with backpropagation neural networks as a tool for regression, and Bayesian neural networks have Gaussian process behaviour when the number of hidden neurons tends to infinity. We describe a simple recurrent neural network with connection weights trained by one-shot Hebbian learning. This network amounts to a dynamical system which relaxes to a stable state in which it generates predictions identical to those of Gaussian process regression. In effect an infinite number of hidden units in a feed-forward architecture can be replaced by a merely finite number, together with recurrent connections.

Algorithms↗
PubMed2003

Enhancement of drilling safety and quality using online sensors and artificial neural networks.

Cutting force sensors and neural networks have been used for the occupational safety of the drilling process. The drill conditions have been online classified into 3 categories: safe, caution, and danger. This approach can change the drill just before its failure. The inputs to neural networks include drill size, feed rate, spindle speed, and features that were extracted from drilling force measurements. The outputs indicate the safety states. This detection system can reach a success rate of over 95%. Furthermore, the one misclassification during online tests was a one-step ahead pre-alarm that is acceptable from the safety and quality viewpoint. The developed online detection system is very robust and can be used in very complex manufacturing environments.

Equipment Safety↗
PubMed2005

Forecasting the prognosis of choroidal melanoma with an artificial neural network.

PURPOSE: To develop an artificial neural network (ANN) that will forecast the 5-year mortality from choroidal melanoma. DESIGN: Retrospective, comparative, observational cohort study. PARTICIPANTS: One hundred fifty-three eyes of 153 consecutive patients with choroidal melanoma (age, 58.4+/-14.6 years) who were treated with ruthenium 106 brachytherapy between 1988 and 1998 at the Department of Ophthalmology, Hadassah University Hospital, Jerusalem, Israel. METHODS: Patients were observed clinically and ultrasonographically (A- and B-mode standardized ultrasonography). Metastatic screening included liver function tests and liver imaging. Backpropagation ANNs composed of 3 or 4 layers of neurons with various types of transfer functions and training protocols were assessed for their ability to predict the 5-year mortality. The ANNs were trained on 77 randomly selected patients and tested on a different set of 76 patients. Artificial neural networks were compared based on their sensitivity, specificity, forecasting accuracy, area under the receiver operating curves, and likelihood ratios (LRs). The best ANN was compared with the results of logistic regression and the performance of an ocular oncologist. MAIN OUTCOME: The ability of the ANNs to forecast the 5-year mortality from choroidal melanoma. RESULTS: Thirty-one patients died during the follow-up period of metastatic choroidal melanoma. The best ANN (one hidden layer of 16 neurons) had 84% forecasting accuracy and an LR of 31.5. The number of hidden neurons significantly influenced the ANNs' performance (P<0.001). The performance of the ANNs was not significantly influenced by the training protocol, the number of hidden layers, or the type of transfer function. In comparison, logistic regression reached 86% forecasting accuracy, with a very low LR (0.8), whereas the human expert forecasting ability was <70% (LR, 1.85). CONCLUSIONS: Artificial neural networks can be used for forecasting the prognosis of choroidal melanoma and may support decision-making in treating this malignancy.

Brachytherapy↗
PubMed2002

Epicenter location by analysis of interictal spikes: a case study for the use of artificial neural networks in biomedical engineering.

Artificial neural network (ANN) technology is finding increasing application in medicine and biomedical engineering. This paper supplies necessary background in ANN technology for researchers unfamiliar with this rapidly emerging discipline. This introduction to ANN application is cast in the context of epileptic seizure epicenter location. This is a very real problem faced by neurosurgeons every day. Precise location of the area of excision is currently determined with a network of surgically implanted subdural electrodes. This means that the cure entails two surgical procedures: one to implant the electrode array that precisely locates the epicenter, and another to remove the epicenter. This paper outlines an experimental diagnostic software system (DSS) that uses artificial neural network (ANN) analysis of magnetoencephalographic (MEG) data to eliminate the first of these surgical procedures. The MEG recording is a quick and painless process that requires no surgery. This approach has the potential to save time, reduce patient discomfort, and eliminate a painful and potentially dangerous surgical step in the treatment procedure.

Biomedical Engineering↗
PubMed1992

Personal computer system for ECG ST-segment recognition based on neural networks.

A personal computer system for electrocardiogram (ECG) ST-segment recognition is developed based on neural networks. The system consists of a preprocessor, neural networks and a recogniser. The adaptive resonance theory (ART) is employed to implement the neural networks in the system, which self-organise in response to the input ECG. Competitive and co-operative interaction among neurons in the neural networks makes the system robust to noise. The preprocessor detects the R points and divides the ECG into cardiac cycles. Each cardiac cycle is fed into the neural networks. The neural networks then address the approximate locations of the J point and the onset of the T-wave (T(on)). The recogniser determines the respective ranges in which the J and T(on) points lie, based on the locations addressed. Within those ranges, the recogniser finds the exact locations of the J and T(on) points either by a change in the sign of the slope of the ECG, a zero slope or a significant change in the slope. The ST-segment is thus recognised as the portion of the ECG between the J and T(on) points. Finally, the appropriateness of the length of the ST-segment is evaluated by an evaluation rule. As the process goes on, the neural networks self-organise and learn the characteristics of the ECG patterns which vary with each patient.(ABSTRACT TRUNCATED AT 250 WORDS)

Computer Systems↗
PubMed2000

Signal decoding and receiver evolution. An analysis using an artificial neural network.

We use a connectionist model, a recurrent artificial neural network, to investigate the evolution of species recognition in sympatric taxa. We addressed three questions: (1) Does the accuracy of artificial neural networks in discriminating between conspecifics and other sympatric heterospecifics depend on whether the networks were trained only to recognize conspecifics, as opposed to being trained to discriminate between conspecifics and sympatric heterospecifics? (2) Do artificial neural networks weight most heavily those signal features that differ most between conspecifics and sympatric heterospecifics, or those features that vary less within conspecifics? (3) Does selection for species recognition generate sexual selection? We find that: (1) Neural networks trained only on self recognition do not classify species as accurately as networks trained to discriminate between conspecifics and heterospecifics. (2) Neural networks weight signal features in a manner suggesting that the total sound environment as opposed to the relative variation of signals within the species is more important in the evolution of recognition mechanisms. (3) Selection for species recognition generates substantial variation in the relative attractiveness of signals within the species and thus can result in sexual selection.

Biological Evolution↗
PubMed2003

Computer simulation of inhibition-dependent binding in a neural network.

Reverberating dynamics of neural network is modeled on PC in order to illustrate possible role of inhibition as binding controller in the network. The network is composed of binding neurons. In the binding neuron model [BioSystems 48 (1998) 263], the degree of temporal coherence between synaptic inputs is decisive for triggering, and slow inhibition is expressed in terms of the degree, which is necessary for triggering. Two learning mechanisms are implemented in the network, namely, adjusting synaptic strength and/or propagation delays. By means of forced playing of external pattern, the network is taught to support dynamics with disconnected and bound patterns of activity. By choosing either high, or low inhibition, one can switch between the disconnected and bound patterns, respectively. This is interpreted as inhibition-controlled binding in the network.

Computer Simulation↗
PubMedDate not supplied

Predictive carcinogenicity: a model for aromatic compounds, with nitrogen-containing substituents, based on molecular descriptors using an artificial neural network.

A back-propagation neural network to predict the carcinogenicity of aromatic nitrogen compounds was developed. The inputs were molecular descriptors of different types: electrostatic, topological, quantum-chemical, physicochemical, etc. For the output the index TD50 as introduced by Gold and colleagues was used, giving a continuous numerical parameter expressing carcinogenicity. From the tens of descriptors calculated, principal component analysis enabled us to restrict the number of parameters to be used for the artificial neural network (ANN). We used 104 molecules for the study. An Rcv2 = 0.69 was obtained. After removal of 12 outliers, a new ANN gave an Rcv2 of 0.82.

Carcinogenicity Tests↗
PubMed2004

Constrained motion control of flexible robot manipulators based on recurrent neural networks.

In this paper, a neural network approach is presented for the motion control of constrained flexible manipulators, where both the contact force everted by the flexible manipulator and the position of the end-effector contacting with a surface are controlled. The dynamic equations for vibration of flexible link and constrained force are derived. The developed control, scheme can adaptively estimate the underlying dynamics of the manipulator using recurrent neural networks (RNNs). Based on the error dynamics of a feedback controller, a learning rule for updating the connection weights of the adaptive RNN model is obtained. Local stability properties of the control system are discussed. Simulation results are elaborated on for both position and force trajectory tracking tasks in the presence of varying parameters and unknown dynamics, which show that the designed controller performs remarkably well.

Algorithms↗
PubMed2006

Prediction of near-surface soil moisture at large scale by digital terrain modeling and neural networks.

The capability of Artificial Neural Network models to forecast near-surface soil moisture at fine spatial scale resolution has been tested for a 99.5 ha watershed located in SW Spain using several easy to achieve digital models of topographic and land cover variables as inputs and a series of soil moisture measurements as training data set. The study methods were designed in order to determining the potentials of the neural network model as a tool to gain insight into soil moisture distribution factors and also in order to optimize the data sampling scheme finding the optimum size of the training data set. Results suggest the efficiency of the methods in forecasting soil moisture, as a tool to assess the optimum number of field samples, and the importance of the variables selected in explaining the final map obtained.

Humidity↗
PubMed2002

Delay-dependent exponential stability analysis of delayed neural networks: an LMI approach.

For neural networks with constant or time-varying delays, the problems of determining the exponential stability and estimating the exponential convergence rate are studied in this paper. An approach combining the Lyapunov-Krasovskii functionals with the linear matrix inequality is taken to investigate the problems, which provide bounds on the interconnection matrix and the activation functions, so as to guarantee the systems' exponential stability. Some criteria for the exponentially stability, which give information on the delay-dependence property, are derived. The results obtained in this paper provide one more set of easily verified guidelines for determining the exponentially stability of delayed neural networks, which are less conservative and less restrictive than the ones reported so far in the literature.

Algorithms↗
PubMed2000

Optimal design of connectivity in neural network training.

Many authors consider neural network (NN) supervised training as an optimization process during which the weights are iteratively adjusted in order to minimise an error (cost) function, which represents the difference between the obtained and the aimed output. The error function surface is usually nonconvex, can be highly convoluted, with many plateaux and long narrow troughs, and can encounter many saddle and local minima (LM) points. Because backpropagation (BP), which is widely used method for supervised learning, uses local methods for optimization, it can get stuck in LM. This can make learning very difficult and sometimes its convergence to optimal solution--not possible. In this paper we propose a stochastic method for global optimization (GO), which make use of a uniformly distributed LP tau sequence of points. The developed technique is tested with common benchmark problems and used for neural network supervised learning. The conducted tests show that the proposed method can be successfully used for an optimal supervised training of small size NN.

Neural Networks, Computer↗
PubMed1992

Application of neural networks to the interpretation of laboratory data in cancer diagnosis.

Neural networks are a relatively new method of multivariate analysis. The purpose of this study was to investigate the ability of neural networks to differentiate benign from malignant breast conditions on the basis of the pattern of nine variables: patient age, total cholesterol, high-density lipoprotein cholesterol, triglycerides, apolipoprotein A-I, apolipoprotein B, albumin, the tumor marker CA15-3, and the Fossel index (measurement of methylene and methyl line-widths in proton NMR spectra). The laboratory analyses were made with blood plasma or serum specimens. The neural network was "trained" with 57 patients: 23 patients with breast malignancies and 34 patients with benign breast conditions. A neural network with nine input neurons, 15 hidden neurons, and two output neurons correctly classified all 57 patients. The ability of the network to predict the diagnoses of patients that it had no encountered in training was tested with a separate group (cross-validation group) of 20 patients. The network correctly predicted the diagnoses for 80% of these patients. For comparison we analyzed the same sets of 57 training patients and 20 cross-validation patients by quadratic discriminant function analysis. The quadratic discriminant function, calculated from the same 57 patients used to train the neural network, correctly classified 84% of the 57 patients, and correctly diagnosed 75% of the 20 cross-validation patients. The results suggest that neural networks are a potentially useful multivariate method for optimizing the diagnostic utility of laboratory data.

Antigens, Tumor-Associated, Carbohydrate↗
PubMed1996

Statistical approach to neural network model building for gentamicin peak predictions.

Feed forward neural networks are flexible, nonlinear modeling tools that are an extension of traditional statistical techniques. The hypothesis that feed forward neural network models can be built in a similar fashion as a statistical model was tested. Feed forward neural network models were built using forward and backward variable selection, and zero to five hidden nodes, and tanh and linear transfer functions were used. Gentamicin serum concentrations were predicted as a model drug for testing these methods. Peak observations from 392 patients were used to train, test, and validate the feed forward neural network. Inputs were demographic and drug dosing information. Model selection was performed using the Akaike information criteria (AIC), Bayesian information criteria (BIC), and a method of stopped training. The models with lowest root mean square (rms) error were those with all 10 inputs and five hidden nodes. Average rms error in the validation set was lowest for stopped training (1.46), then AIC (1.51), and finally BIC (1.56). Larger models tended to result in the best predictions. Overfitting can occur in models that are too large, either by using too many nodes in the hidden layer (rms = 1.49) or by using too many inputs with little information associated with them (rms = 1.70). We conclude that neural networks can be built using a large number of parameters that have good predictive performance. Care must be used during training to avoid overfitting the data. A stopped training method resulted in the network with the lowest rms error.

Adult↗
PubMedDate not supplied

Holographic neural networks as nonlinear discriminants for chemical applications.

A holographic neural network has been investigated for use as a discriminant. Six sets of artificial data and two data sets of infrared spectra, reduced using principal component analysis, of prepared cervical smears were analyzed by four regular discriminant methods as well as by the holographic neural network method. In all cases, it was found that the holographic neural network method gave comparable, and in some cases superior, results to the other discriminant methods. The holographic neural network method is simple to apply and has the advantage that it can be easily refined when new data become available without disturbing the original mapping. It is suggested that the holographic neural network method should be seriously considered when discrimination methods need to be applied.

Cervix Uteri↗
PubMed2006

A novel radial basis function neural network for discriminant analysis.

A novel radial basis function neural network for discriminant analysis is presented in this paper. In contrast to many other researches, this work focuses on the exploitation of the weight structure of radial basis function neural networks using the Bayesian method. It is expected that the performance of a radial basis function neural network with a well-explored weight structure can be improved. As the weight structure of a radial basis function neural network is commonly unknown, the Bayesian method is, therefore, used in this paper to study this a priori structure. Two weight structures are investigated in this study, i.e., a single-Gaussian structure and a two-Gaussian structure. An expectation-maximization learning algorithm is used to estimate the weights. The simulation results showed that the proposed radial basis function neural network with a weight structure of two Gaussians outperformed the other algorithms.

Algorithms↗
PubMed2004

Effects of neural network feedback to physicians on admit/discharge decision for emergency department patients with chest pain.

STUDY OBJECTIVE: Neural networks can risk-stratify emergency department (ED) patients with potential acute coronary syndromes with a high specificity, potentially facilitating ED discharge of patients to home. We hypothesized that the use of "real-time" neural networks would decrease the admission rate for ED chest pain patients. METHODS: We conducted a before-and-after trial. Consecutive ED patients with chest pain were evaluated before and after implementation of a neural network in an urban university ED. Data included 40 variables used in neural networks for acute myocardial infarction and acute coronary syndrome. Data were obtained in real time, and neural network outputs were provided to the treating physician while patients were in the ED. On hospital discharge, attending physicians received feedback, including neural network output, their initial clinical impression, cardiac test results, and final diagnosis. The main outcome was the actual admit/discharge decision made before versus after the implementation of the neural network. RESULTS: Before implementation, 4,492 patients were enrolled; after implementation, 432 patients were enrolled. Implementation of the neural network did not decrease the hospital admission rate (before: 62.7% [95% confidence interval (CI) 61.3% to 64.1%] versus after: 66.6% [95% CI 62.2% to 71.0%]). Additionally, the ICU admission rates were not different (11.4% [95% CI 10.5% to 12.3%] versus 9.3% [95% CI 6.6% to 12.0%]). Physician query found that the neural network changed management in only 2 cases (<1%). CONCLUSION: The use of real-time neural network feedback did not influence the admission decision for ED patients with chest pain, most likely because the neural network output was delayed until the return of cardiac markers, and the disposition decision had already been made by that time.

Adult↗