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.

SourceResearch connectionFrom yearThrough year

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

At least 1,351 records · Page 75Linked to original sources

PubMed2005

New conditions for global exponential stability of cellular neural networks with delays.

In this paper, we study further a class of cellular neural networks model with delays. By employing the inequality api(m)(k=1)1 b(q(k))(k) or=0, b(k) >or=0, q(k) > 0 with sigma(m)(k=1) q(k) = r-1, and r > 1), constructing a new Lyapunov functional, and applying the Homeomorphism theory, we derive some new conditions ensuring the existence, uniqueness of the equilibrium point and its global exponential stability for cellular neural networks. These conditions are independent of delays and possess infinitely adjustable real parameters, which are of highly important significance in the designs and applications of networks. In addition, we extend or improve the previously known results.

Algorithms↗

PubMed2004

Phylogenetic, ontogenetic and adult adaptive plasticity of rhythmic neural networks: a common neuromodulatory mechanism?

Neuromodulatory inputs are known to play a major role in the adaptive plasticity of rhythmic neural networks in adult animals. Using the crustacean stomatogastric nervous system, we have investigated the role of modulatory inputs in the development of rhythmic neural networks. We found that the same neuronal population is organised into a single network in the embryo, as opposed to the two networks present in the adult. However, these adult networks pre-exist in the embryo and can be unmasked by specific alterations of the neuromodulatory environment. Similarly, adult networks may switch back to the embryonic phenotype by manipulating neuromodulatory inputs. During development, we found that the early established neuromodulatory population display alteration in expressed neurotransmitter phenotypes, and that although the population of modulatory neurones is established early, with morphology and projection pattern similar to adult ones, their neurotransmitter phenotype may appear gradually. Therefore the abrupt switch from embryonic to adult network expression occurring at metamorphosis may be due to network reconfiguration in response to changes in modulatory input, as found in adult adaptive plasticity. Strikingly, related crustacean species express different motor outputs using the same basic network circuitry, due to species-specific alteration in neuromodulatory substances within homologous projecting neurones. Therefore we propose that alterations within neuromodulatory systems to a given rhythmic neural network displaying the same basic circuitry may account for the generation of different motor outputs throughout development (ontogenetic plasticity), adulthood (adaptive plasticity) and evolution (phylogenetic plasticity).

Animals↗

PubMed2002

[Improving signal-noise relations of evoked potentials by neural networks].

Single trial evoked potentials recorded in a sleep deprivation experiment were analyzed by means of neural networks. For improving the signal-noise-ratio a neural network classifier was trained to distinguish between the S-class which consists of assumed visually evoked single trial potentials and the N-class which should contain no event related components. The members of S-class and the N-class were averaged separately. We compared the averaged potentials of all single trials with the averaged potentials of the S-class members and we were able to show a significant improvement in the amplitudes and the signal-noise-ratio. We got the result that increasing sleep deprivation corresponds to a significantly decreasing number of members in the S-class. We concluded that sleep deprivation led to a significant number of stimuli which could not be preprocessed.

Artifacts↗

PubMed2006

Fuzzy neural network for flow estimation in sewer systems during wet weather.

Estimation of the water flow from rainfall intensity during storm events is important in hydrology, sewer system control, and environmental protection. The runoff-producing behavior of a sewer system changes from one storm event to another because rainfall loss depends not only on rainfall intensities, but also on the state of the soil and vegetation, the general condition of the climate, and so on. As such, it would be difficult to obtain a precise flowrate estimation without sufficient a priori knowledge of these factors. To establish a model for flow estimation, one can also use statistical methods, such as the neural network STORMNET, software developed at Lyonnaise des Eaux, France, analyzing the relation between rainfall intensity and flowrate data of the known storm events registered in the past for a given sewer system. In this study, the authors propose a fuzzy neural network to estimate the flowrate from rainfall intensity. The fuzzy neural network combines four STORMNETs and fuzzy deduction to better estimate the flowrates. This study's system for flow estimation can be calibrated automatically by using known storm events; no data regarding the physical characteristics of the drainage basins are required. Compared with the neural network STORMNET, this method reduces the mean square error of the flow estimates by approximately 20%. Experimental results are reported herein.

Calibration↗

PubMed2003

[An artificial neural network model for lake color inversion using TM imagery].

The technology of artificial neural network was used for inversing water quality parameters from TM imagery data in the paper in order to study water quality and eutrophic status of lake. On the basis of satellite synchronous monitoring experiment, a BP neural network model was constructed, in which concentrations of SS, CODMn, DO, T-N, T-P and chlo-a were inversed from Landsat TM data and the accuracy of which was good, the relative error of which could be controlled below 25%. Moreover, the reasons of simulating error, ways of improving model and applications of the model were also analyzed in detail. The results of this research told that based on a small-scale of satellite synchronous experiment, the model could be applied successfully in investigation, analysis and estimation of lake water quality.

Color↗

PubMed1993

Using a neural network to identify potential HLA-DR1 binding sites within proteins.

The presentation by antigen-presenting cells of immunodominant peptide segments in association with major histocompatibility complex (MHC) encoded proteins is fundamental to the efficacy of a specific immune response. One approach used to identify immunodominant segments within proteins has involved the development of predictive algorithms which utilize amino acid sequence data to identify structural characteristics or motifs associated with in vivo antigenicity. The parallel-computing technique termed 'neural networking' has recently been shown to be remarkably efficient at addressing the problem of pattern recognition and can be applied to predict protein secondary structure attributes directly from amino acid sequence data. In order to examine the potential of a neural network to generalize peptide structural features related to binding within class II MHC-encoded proteins, we have trained a neural network to determine whether or not any given amino acid of a protein is part of a peptide segment capable of binding to HLA-DR1. We report that a neural network trained on a data base consisting of peptide segments known to bind to HLA-DR1 is able to generalize features relating to HLA-DR1-binding capacity (r = 0.17 and p = 0.0001).

Amino Acid Sequence↗

PubMed2003

Exponential stability and periodic solutions of neural networks with continuously distributed delays.

In this paper we study a class of neural networks with continuously distributed delays. By means the of Lyapunov functional method, we obtain some sufficient conditions ensuring the existence, uniqueness, and global exponential stability of the equilibrium and periodic solution. We 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. Moreover, these conclusions are presented in terms of system parameters and can be easily verified. Therefore, our results play an important role in the design of globally exponentially stable neural circuits and periodic oscillatory neural circuits.

Biophysical Phenomena↗

PubMed1998

The prediction of common bile duct stones using a neural network.

BACKGROUND: The role of preoperative ERCP and endoscopic sphincterotomy (ES) in the diagnosis and treatment of suspected common bile duct stones (CBDS) in the laparoscopic age is controversial. The preoperative diagnosis of CBDS by ERCP and the removal of CBDS by ES are advantageous because of technical difficulties in performing laparoscopic exploration of the common bile duct. Approximately 50% of preoperative ERCP examinations are normal, however. The noninvasive diagnosis of CBDS has assumed new importance, but it has proved to be an elusive goal. Neural networks are a form of artificial computer intelligence that have been used successfully to interpret ECGs and to diagnose myocardial infarcts. The purpose of this study was to determine whether a neural network could be trained to predict CBDS accurately in patients at high risk of having duct stones. STUDY DESIGN: We trained a back-propagation neural network to predict the presence of CBDS. Retrospective data from patients who had a cholecystectomy and either a preoperative ERCP or intraoperative cholangiogram were used to build the network, and it was tested using unseen data. RESULTS: One hundred forty patients were used to train the network, and 16 patients were used to test it. The trained network was able to predict CBDS in 100% of the patients in both the training and test sets. CONCLUSIONS: Screening of high-risk patients for CBDS by neural network analysis is highly accurate. This promising new, noninvasive, and inexpensive technique can potentially decrease the need for preoperative ERCP by 50%, but additional prospective evaluation is indicated.

Adult↗

PubMed2003

Binary neural network training algorithms based on linear sequential learning.

A key problem in Binary Neural Network learning is to decide bigger linear separable subsets. In this paper we prove some lemmas about linear separability. Based on these lemmas, we propose Multi-Core Learning (MCL) and Multi-Core Expand-and-Truncate Learning (MCETL) algorithms to construct Binary Neural Networks. We conclude that MCL and MCETL simplify the equations to compute weights and thresholds, and they result in the construction of simpler hidden layer. Examples are given to demonstrate these conclusions.

Algorithms↗

PubMed2006

Modeling and simulation of Streptomyces peucetius var. caesius N47 cultivation and epsilon-rhodomycinone production with kinetic equations and neural networks.

This study focuses on comparing different kinetic growth models and the use of neural networks in the batch cultivation of Streptomyces peucetius var. caesius producing epsilon-rhodomycinone. Contois, Monod and Teissier microbial growth models were used as well as the logistic growth modeling approach, which was found best in the simulations of growth and glucose consumption in the batch growth phase. The lag phase was included in the kinetic model with a CO2 trigger and a delay factor. Substrate consumption and product formation were included as Luedeking-Piret and logistic type equations, respectively. Biomass formation was modeled successfully with a 6-8-2 network, and the network was capable of biomass prediction with an R2-value of 0.983. Epsilon-rhodomycinone production was successfully modeled with a recursive 8-3-1 network capable of epsilon-rhodomycinone prediction with an R2-value of 0.903. The predictive power of the neural networks was superior to the kinetic models, which could not be used in predictive modeling of arbitrary batch cultivations.

Anthracyclines↗

PubMed1995

Patterns of functional damage in neural network models of associative memory.

Current understanding of the effects of damage on neural networks is rudimentary, even though such understanding could lead to important insights concerning neurological and psychiatric disorders. Motivated by this consideration, we present a simple analytical framework for estimating the functional damage resulting from focal structural lesions to a neural network model. The effects of focal lesions of varying area, shape, and number on the retrieval capacities of a spatially organized associative memory are quantified, leading to specific scaling laws that may be further examined experimentally. It is predicted that multiple focal lesions will impair performance more than a single lesion of the same size, that slit like lesions are more damaging than rounder lesions, and that the same fraction of damage (relative to the total network size) will result in significantly less performance decrease in larger networks. Our study is clinically motivated by the observation that in multi-infarct dementia, the size of metabolically impaired tissue correlates with the level of cognitive impairment more than the size of structural damage. Our results account for the detrimental effect of the number of infarcts rather than their overall size or structural damage, and for the "multiplicative" interaction between Alzheimer's disease and multi-infarct dementia.

Algorithms↗

PubMed1995

Classification of brain compartments and head injury lesions by neural networks applied to MRI.

An automatic, neural network-based approach was applied to segment normal brain compartments and lesions on MR images. Two supervised networks, backpropagation (BPN) and counterpropagation, and two unsupervised networks, Kohonen learning vector quantizer and analog adaptive resonance theory, were trained on registered T2-weighted and proton density images. The classes of interest were background, gray matter, white matter, cerebrospinal fluid, macrocystic encephalomalacia, gliosis, and "unknown." A comprehensive feature vector was chosen to discriminate these classes. The BPN combined with feature conditioning, multiple discriminant analysis followed by Hotelling transform, produced the most accurate and consistent classification results. Classification of normal brain compartments were generally in agreement with expert interpretation of the images. Macrocystic encephalomalacia and gliosis were recognized and, except around the periphery, classified in agreement with the clinician's report used to train the neural network.

Artificial Intelligence↗

PubMed2000

On impulsive autoassociative neural networks.

Many systems existing in physics, chemistry, biology, engineering, and information science can be characterized by impulsive dynamics caused by abrupt jumps at certain instants during the process. These complex dynamical behaviors can be modeled by impulsive differential systems or impulsive neural networks. This paper formulates and studies a new model of impulsive autoassociative neural networks. Several fundamental issues, such as global exponential stability and existence and uniqueness of equilibria of such neural networks, are established.

Models, Neurological↗

PubMed2006

Neural network modeling of the kinetics of SO2 removal by fly ash-based sorbent.

The mechanistic modeling of the sulfation reaction between fly ash-based sorbent and SO2 is a challenging task due to a variety reasons including the complexity of the reaction itself and the inability to measure some of the key parameters of the reaction. In this work, the possibility of modeling the sulfation reaction kinetics using a purely data-driven neural network was investigated. Experiments on SO2 removal by a sorbent prepared from coal fly ash/CaO/CaSO4 were conducted using a fixed bed reactor to generate a database to train and validate the neural network model. Extensive SO2 removal data points were obtained by varying three process variables, namely, SO2 inlet concentration (500-2000 mg/L), reaction temperature (60-80 degreesC), and relative humidity (50-70%), as a function of reaction time (0-60 min). Modeling results show that the neural network can provide excellent fits to the SO2 removal data after considerable training and can be successfully used to predict the extent of SO2 removal as a function of time even when the process variables are outside the training domain. From a modeling standpoint, the suitably trained and validated neural network with excellent interpolation and extrapolation properties could have immediate practical benefits in the absence of a theoretical model.

Adsorption↗

PubMed2004

Template learning of cellular neural network using genetic programming.

A new learning algorithm for space invariant Uncoupled Cellular Neural Network is introduced. Learning is formulated as an optimization problem. Genetic Programming has been selected for creating new knowledge because they allow the system to find new rules both near to good ones and far from them, looking for unknown good control actions. According to the lattice Cellular Neural Network architecture, Genetic Programming will be used in deriving the Cloning Template. Exploration of any stable domain is possible by the current approach. Details of the algorithm are discussed and several application results are shown.

Algorithms↗

PubMed2000

Ruptured abdominal aortic aneurysm: a novel method of outcome prediction using neural network technology.

BACKGROUND: reported survival following emergency surgery for ruptured abdominal aortic aneurysm (RAAA) varies widely between institutions. This is largely attributable to differences in case mix. The aim of this study was to identify and evaluate a set of prognostic variables that would accurately predict outcome for individual patients from perioperative indices. METHODS: perioperative factors associated with subsequent mortality at our institution were identified by retrospective review of 102 consecutive operations for RAAA over a 7-year period (January 1990 to January 1997). Logistic regression analysis was used to select the most significant variables associated with subsequent mortality. These were used to construct, train, and validate a neural network designed to predict survival from surgery in individual cases on a prospective basis. RESULTS: the 30-day mortality rate was 53%. Multivariate analysis identified four highly significant independent predictors of mortality; preoperative hypotension, intraperitoneal rupture, preoperative coagulopathy, and preoperative cardiac arrest. Using these inputs, the neural network correctly predicted outcome in 82.5% of individual cases. CONCLUSION: a neural network based on just four perioperative variables can accurately predict outcome of RAAA. Prognostic variables should be reported in studies as a measure of the effect of case mix on survival data. Neural networks have potential to aid decision-making relating to outcome for individual cases.

Aged↗

PubMed1992

Application of neural networks in medical diagnosis: the case of sexually-transmitted diseases.

In this paper neural networks are used to formulate a means of diagnosing sexually-transmitted diseases (STD's). An overview of the theoretical background of neural networks is presented. A summary of the diseases used in the project and their signs and symptoms are given. These signs and symptoms are used to train a network. Upon presentation of a set of signs and symptoms to the trained network, the presence of a disease or diseases with those symptoms may be deduced.

Diagnosis, Computer-Assisted↗

PubMed1994

Overlapping neural networks for multiple motor engrams.

The hypothesis was tested that learned movement trajectories of different shapes can be stored in, and generated by, largely overlapping neural networks. Indeed, it was possible to train a massively interconnected neural network to generate different shapes of internally stored, dynamically evolving movement trajectories using a general-purpose core part, common to all networks, and a special-purpose part, specific for a particular trajectory. The weights of connections between the core units do not carry any information about trajectories. The core network alone could generate externally instructed trajectories but not internally stored ones, for which both the core and the trajectory-specific part were needed. All information about the movements is stored in the weights of connections between the core part and the specialized units and between the specialized units themselves. Due to these connections the core part reveals specific dynamical behavior for a particular trajectory and, as the result, discriminates different tasks. The percentage of trajectory-specific units needed to generate a certain trajectory was small (2-5%), and the total output of the network is almost entirely provided by the core part, whereas the role of the small specialized parts is to drive the dynamical behavior. These results suggest an efficient and effective mechanism for storing learned motor patterns in, and reproducing them by, overlapping neural networks and are in accord with neurophysiological findings of trajectory-specific cells and with neurological observations of loss of specific motor skills in the presence of otherwise intact motor control.

Models, Theoretical↗