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 325 records · Page 18Linked to original sources
PubMed2006

Exponential synchronization of a class of neural networks with time-varying delays.

This paper aims to present a synchronization scheme for a class of delayed neural networks, which covers the Hopfield neural networks and cellular neural networks with time-varying delays. A feedback control gain matrix is derived to achieve the exponential synchronization of the drive-response structure of neural networks by using the Lyapunov stability theory, and its exponential synchronization condition can be verified if a certain Hamiltonian matrix with no eigenvalues on the imaginary axis. This condition can avoid solving an algebraic Riccati equation. Both the cellular neural networks and Hopfield neural networks with time-varying delays are given as examples for illustration.

Animals↗
PubMed2003

Prediction of cyclosporine dosage in patients after kidney transplantation using neural networks.

This paper proposes the use of neural networks for individualizing the dosage of cyclosporine A (CyA) in patients who have undergone kidney transplantation. Since the dosing of CyA usually requires intensive therapeutic drug monitoring, the accurate prediction of CyA blood concentrations would decrease the monitoring frequency and, thus, improve clinical outcomes. Thirty-two patients and different factors were studied to obtain the models. Three kinds of networks (multilayer perceptron, finite impulse response (FIR) network, and Elman recurrent network) and the formation of neural-network ensembles are used in a scheme of two chained models where the blood concentration predicted by the first model constitutes an input to the dosage prediction model. This approach is designed to aid in the process of clinical decision making. The FIR network, yielding root-mean-square errors (RMSEs) of 52.80 ng/mL and mean errors (MEs) of 0.18 ng/mL in validation (10 patients) showed the best blood concentration predictions and a committee of trained networks improved the results (RMSE = 46.97 ng/mL, ME = 0.091 ng/mL). The Elman network was the selected model for dosage prediction (RMSE = 0.27 mg/Kg/d, ME = 0.07 mg/Kg/d). However, in both cases, no statistical differences on the accuracy of neural methods were found. The models' robustness is also analyzed by evaluating their performance when noise is introduced at input nodes, and it results in a helpful test for models' selection. We conclude that neural networks can be used to predict both dose and blood concentrations of cyclosporine in steady-state. This novel approach has produced accurate and validated models to be used as decision-aid tools.

Administration, Oral↗
PubMed2001

The simultaneous recurrent neural network for addressing the scaling problem in static optimization.

A trainable recurrent neural network, Simultaneous Recurrent Neural network, is proposed to address the scaling problem faced by neural network algorithms in static optimization. The proposed algorithm derives its computational power to address the scaling problem through its ability to "learn" compared to existing recurrent neural algorithms, which are not trainable. Recurrent backpropagation algorithm is employed to train the recurrent, relaxation-based neural network in order to associate fixed points of the network dynamics with locally optimal solutions of the static optimization problems. Performance of the algorithm is tested on the NP-hard Traveling Salesman Problem in the range of 100 to 600 cities. Simulation results indicate that the proposed algorithm is able to consistently locate high-quality solutions for all problem sizes tested. In other words, the proposed algorithm scales demonstrably well with the problem size with respect to quality of solutions and at the expense of increased computational cost for large problem sizes.

Algorithms↗
PubMed1994

A neural network classifier for cerebral perfusion imaging.

UNLABELLED: Artificial neural networks have been applied to a variety of pattern recognition tasks in medical imaging and have been shown to be a powerful classification tool. The potential usefulness to discriminate normal from abnormal cerebral perfusion patterns was investigated. METHODS: Cerebral perfusion imaging with 99mTc-labeled hexamethylpropyleneimine oxime was performed on 52 normal control subjects, 29 patients with clinically diagnosed Alzheimer's disease (AD) and 25 patients with chronic cocaine polydrug abuse. Each study was registered and scaled to a common anatomic coordinate system, yielding 120 standardized cortical regions. A back-propagation neural network classifier based on regional perfusion was used to classify normal and abnormal perfusion patterns. The neural network was trained to discriminate patients with AD from age-matched normal controls and cocaine polydrug abuse patients from normal controls. The performance of the neural network in these two tasks was evaluated quantitatively by receiver operating characteristic (ROC) analysis using cross-validation. RESULTS: For patients with AD, the area under the ROC curve was 0.93 +/- 0.04. When testing with the cocaine polydrug abuser data, the area under the ROC curve was 0.89 +/- 0.04. CONCLUSION: Neural networks provide a potentially useful tool in the decision-making task to discriminate patients with AD and cocaine abuse from normal controls.

Adult↗
PubMed2004

A solution for two-dimensional mazes with use of chaotic dynamics in a recurrent neural network model.

Chaotic dynamics introduced into a neural network model is applied to solving two-dimensional mazes, which are ill-posed problems. A moving object moves from the position at t to t + 1 by simply defined motion function calculated from firing patterns of the neural network model at each time step t. We have embedded several prototype attractors that correspond to the simple motion of the object orienting toward several directions in two-dimensional space in our neural network model. Introducing chaotic dynamics into the network gives outputs sampled from intermediate state points between embedded attractors in a state space, and these dynamics enable the object to move in various directions. System parameter switching between a chaotic and an attractor regime in the state space of the neural network enables the object to move to a set target in a two-dimensional maze. Results of computer simulations show that the success rate for this method over 300 trials is higher than that of random walk. To investigate why the proposed method gives better performance, we calculate and discuss statistical data with respect to dynamical structure.

Artificial Intelligence↗
PubMed1998

Neural networks as models of psychopathology.

Neural network modeling is situated between neurobiology, cognitive science, and neuropsychology. The structural and functional resemblance with biological computation has made artificial neural networks (ANN) useful for exploring the relationship between neurobiology and computational performance, i.e., cognition and behavior. This review provides an introduction to the theory of ANN and how they have linked theories from neurobiology and psychopathology in schizophrenia, affective disorders, and dementia.

Humans↗
PubMed2004

Dynamics of periodic delayed neural networks.

This paper formulates and studies a model of periodic delayed neural networks. This model can well describe many practical architectures of delayed neural networks, which is generalization of some additive delayed neural networks such as delayed Hopfield neural networks and delayed cellular neural networks, under a time-varying environment, particularly when the network parameters and input stimuli are varied periodically with time. Without assuming the smoothness, monotonicity and boundedness of the activation functions, the two functional issues on neuronal dynamics of this periodic networks, i.e. the existence and global exponential stability of its periodic solutions, are investigated. Some explicit and conclusive results are established, which are natural extension and generalization of the corresponding results existing in the literature. Furthermore, some examples and simulations are presented to illustrate the practical nature of the new results.

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↗
PubMedDate not supplied

Neural network assessment of perioperative cardiac risk in vascular surgery patients.

Neural networks were developed to predict perioperative cardiac complications with data from 567 vascular surgery patients. Neural network scores were based on cardiac risk factors and dipyridamole thallium results. These scores were converted into likelihood ratios that predicted cardiac risk. The prognostic accuracy of the neural networks was similar to that of logistic regression models (ROC areas 76.0% vs 75.8%), but their calibration was better. Logistic regression overestimated event rates in a group of high-risk patients (predicted event rate, 64%; observed rate 30%; n=50, p<0.001). On a validation set of 514 patients, the neural networks still had ROC similar areas to those of logistic regression (68.3% vs 67.5%), but logistic regression again overestimated event rates for a group of high-risk patients. The calibration difference was reflected in the Hosmer-Lemeshow chi-square statistic (18.6 for the neural networks, 45.0 for logistic regression). The neural networks successfully estimated perioperative cardiac risk with better calibration than comparable logistic regression models.

Bayes Theorem↗
PubMed2003

Stability analysis of a delayed Hopfield neural network.

In this paper, we study a class of neural networks, which includes bidirectional associative memory networks and cellular neural networks as its special cases. By Brouwer's fixed point theorem, a continuation theorem based on Gains and Mawhin's coincidence degree, matrix theory, and inequality analysis, we not only obtain some different sufficient conditions ensuring the existence, uniqueness, and global exponential stability of the equilibrium but also estimate the exponentially convergent rate. Our results are less restrictive than previously known criteria and can be applied to neural networks with a broad range of activation functions assuming neither differentiability nor strict monotonicity.

Algorithms↗
PubMed2003

[Simultaneous spectrophotometric determination of mixed colorants by artificial neural network].

The back propagation artificial neural network was applied to process spectrophotometric data of mixed colorants. By optimizing the network structure and parameters, the predication accuracy was enhanced. The method was used for simultaneous determination of mixed colorants in synthetic samples and drinks on sale with satisfactory results. Therefore, the artificial neural network may provide a new approach to determine the mixed colorants is drinks by spectrophotometry without any preliminary chemical separation.

Beverages↗
PubMed1995

Interpretation of nonstress tests by an artificial neural network.

OBJECTIVE: Our purpose was to evaluate an artificial neural network in the interpretation of nonstress tests. STUDY DESIGN: A nonlinear artificial neural network trained by backpropagation was taught to interpret records of nonstress tests by two learning sets. The first set contained nonstress tests that were similarly interpreted by three human experts; the second set contained a subset of nonstress tests that led to interobserver disagreement. Both "raw" fetal heart rate and uterine contraction data and 17 quantified variables obtained by automated computer analysis were introduced to the input layer. After training, the network was tested by presenting it with input patterns to which it had not been exposed. The performance of the system was examined in relation to the human expert. RESULTS: After training the neural network with the first set, a sensitivity of 88.9% and a false-positive rate of 4.3% were obtained at testing. When the learning and test set contained records that led to interobserver disagreement, a sensitivity of 86.7% and a false-positive rate of 19.7% were obtained. Sixty percent of fetal heart rate records interpreted as abnormal by the neural network were interpreted likewise by the human experts. CONCLUSIONS: The results obtained are encouraging in that the neural network could discriminate between normal and abnormal nonstress tests. Further evaluation of this new technique is mandatory to evaluate its efficacy and reliability in interpreting fetal heart rate records.

Algorithms↗
PubMed2002

Classification and prediction of the progression of thyroid-associated ophthalmopathy by an artificial neural network.

OBJECTIVE: We have used an artificial neural network in an attempt to classify and predict the progression of thyroid-associated ophthalmopathy (TAO) at the first clinical examination. DESIGN: This retrospective comparative case series included a group of patients examined by the ophthalmologist only once because of the absence of signs of progressive disease (GR1), as subsequently monitored by an endocrinologist, and a group of patients on follow-up because of progressive disease (GR2). PARTICIPANTS AND METHODS: We examined 242 patients, of whom 207 were women and 35 were men. GR1 included 129 patients (257 eyes) who, on ophthalmologic assessment, were further classified as having no TAO (n = 53; GR1a) and only lid signs or inactive, stable TAO (n = 76; GR1b). GR2 included 113 patients (219 eyes). One hundred three normal subjects (205 eyes), 50 women and 53 men, were tested to provide normal ranges for proptosis values. We applied a model of back propagation neural network with 17 input variables, a training matrix of 414 observations, a randomly selected test group of 115 observations, and, as output, the progression of disease. The ophthalmologic assessment included (1) lid fissure measurement, (2) Hertel, (3) color vision, (4) cover test and Hess screen, (5) visual acuity, (6) tonometry, (7) fundus examination, (8) visual field, and (9) orbital computed tomography scan or ultrasonography. Other parameters included in the neural analysis were gender and age of the patients, their cigarette smoking, and the interval between follow-up visits. RESULTS: The prevalence of smokers among patients without TAO was significantly lower than that among those with TAO (P < 0.03). Mean proptosis values (Hertel) were significantly different in GR1, in GR2, and in a group of normal eyes (P < 0.0001), and the changes of values in consecutive measurements were associated with progression of the disease (P < 0.01). Differences of the proptosis values in the two groups of patients were not related to smoking. The neural network correctly classified 78.3% of 115 eyes (87 patients) and predicted TAO progression in 69.2% of 39 eyes (28 patients). CONCLUSIONS: In our opinion, neural network analysis can be successfully applied for classifying TAO and predicting progression at the first clinical examination.

Adolescent↗
PubMed2000

Preformulation studies and characterization of the physicochemical properties of amorphous polymers using artificial neural networks.

The utility of artificial neural networks (ANNs) as a preformulation tool to determine the physicochemical properties of amorphous polymers such as the hydration characteristics, glass transition temperatures and rheological properties was investigated. The neural network simulator, CAD/Chem, based on the delta back-propagation paradigm was used for this study. The ANNs software was trained with sets of experimental data consisting of different polymer blends with known water-uptake profiles, glass transition temperatures and viscosity values. A set of similar data, not initially exposed to the ANNs was used to validate the ability of the ANNs to recognize patterns. The results of this investigation indicate that the ANNs accurately predicted the water-uptake, glass transition temperatures and viscosities of different amorphous polymers and their physical blends with a low % error (0-8%) of prediction. The ANNs also showed good correlation between the water-uptake and changes in the glass transition temperatures of the polymers. This study demonstrated the potential of the ANNs as a preformulation tool to evaluate the characteristics of amorphous polymers. This is particularly relevant when designing sustained release formulations that require the use of a fast hydrating polymer matrix.

Alginates↗
PubMed2004

An artificial neural network ensemble to predict disposition and length of stay in children presenting with bronchiolitis.

BACKGROUND: Artificial neural networks apply complex non-linear functions to pattern recognition problems. An ensemble is a 'committee' of neural networks that usually outperforms single neural networks. Bronchiolitis is a common manifestation of viral lower respiratory tract infection in infants and toddlers. OBJECTIVE: To train artificial neural network ensembles to predict the disposition and length of stay in children presenting to the Emergency Department with bronchiolitis. METHODS: A specifically constructed database of 119 episodes of bronchiolitis was used to train, validate, and test a neural network ensemble. We used EasyNN 7.0 on a 200 Mhz pentium PC with a maths co-processor. The ensemble of neural networks constructed was subjected to fivefold validation. Comparison with actual and predicted dispositions was measured using the kappa statistic for disposition and the Kaplan-Meier estimations and log rank test for predictions of length of stay. RESULTS: The neural network ensembles correctly predicted disposition in 81% (range 75-90%) of test cases. When compared with actual disposition the neural network performed similarly to a logistic regression model and significantly better than various 'dumb machine' strategies with which we compared it. The prediction of length of stay was poorer, 65% (range 60-80%), but the difference between observed and predicted lengths of stay were not significantly different. CONCLUSION: Artificial neural network ensembles can predict disposition for infants and toddlers with bronchiolitis; however, the prediction of length of hospital stay is not as good.

Bronchiolitis↗
PubMed2003

Prediction of physicochemical properties based on neural network modelling.

The literature describing neural network modelling to predict physicochemical properties of organic compounds from the molecular structure is reviewed from the perspective of pharmaceutical research. The standard three-layer, feed-forward neural network is the technique most frequently used, although the use of other techniques is increasing. Various approaches to describe the molecular structure have been successfully used, including molecular fragments, topological indices, and descriptors calculated by semi-empirical quantum chemical methods. Some physicochemical properties, such as octanol-water partition coefficient, water solubility, boiling point and vapour pressure, have been modelled by several research groups over the years using different approaches and structurally diverse large training sets. The prediction accuracy of most models seems to be rather close to the performance of the experimental measurements, when the accuracy is assessed with a test set from the working database. Results with independent test sets have been less satisfactory. Implications of this problem are discussed.

Chemical Phenomena↗
PubMed2004

Dynamical optimal training for interval type-2 fuzzy neural network (T2FNN).

Type-2 fuzzy logic system (FLS) cascaded with neural network, type-2 fuzzy neural network (T2FNN), is presented in this paper to handle uncertainty with dynamical optimal learning. A T2FNN consists of a type-2 fuzzy linguistic process as the antecedent part, and the two-layer interval neural network as the consequent part. A general T2FNN is computational-intensive due to the complexity of type 2 to type 1 reduction. Therefore, the interval T2FNN is adopted in this paper to simplify the computational process. The dynamical optimal training algorithm for the two-layer consequent part of interval T2FNN is first developed. The stable and optimal left and right learning rates for the interval neural network, in the sense of maximum error reduction, can be derived for each iteration in the training process (back propagation). It can also be shown both learning rates cannot be both negative. Further, due to variation of the initial MF parameters, i.e., the spread level of uncertain means or deviations of interval Gaussian MFs, the performance of back propagation training process may be affected. To achieve better total performance, a genetic algorithm (GA) is designed to search optimal spread rate for uncertain means and optimal learning for the antecedent part. Several examples are fully illustrated. Excellent results are obtained for the truck backing-up control and the identification of nonlinear system, which yield more improved performance than those using type-1 FNN.

Algorithms↗
PubMed1998

Recognition of daily life motor activity classes using an artificial neural network.

OBJECTIVE: To investigate a possible role of artificial neural networks for the automated recognition and classification of daily life activities (eg, sitting, lying, standing, walking, etc) in an attempt to reduce the cost of manual recognition and classification. METHODS: Data from sessions of about 10 hours of continuous recording of eight ambulatory patients were used to train and evaluate eight probabilistic neural networks, each of which is configured for one subject. To provide the reference data for building the training set, the instrumented subject follows a 15- to 30-minute protocol consisting of several daily life activities. To properly evaluate the networks, the remaining manually labeled data of each subject were compared with the output of each trained network. RESULTS: The average recognition rate of the trained neural networks was equal to 95% good classification of all presented cases of the daily life activity. Automatic misclassification of 5% resulted from certain activities being too short or the occurrence of activities that were not included in the training set. CONCLUSION: The preliminary results of the trained neural networks have indicated that the probabilistic neural network is a potentially useful tool for the recognition of daily life motor activities.

Activities of Daily Living↗