SEARCH · PubMed Health

Results for “Neural Networks, Computer”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 703 records · Page 39Linked to original sources

PubMed2006

A hybrid neural-genetic algorithm for reservoir water quality management.

A combined neural network and genetic algorithm (GA) was developed for water quality management of Feitsui Reservoir in Taiwan. First, an artificial neural network (ANN) model was employed to simulate the behavior of nutrient loads into the reservoir. The data from watershed loads, precipitation in the watershed, and outflow were used in the ANN model to forecast the total phosphorus concentration in the reservoir. A 6-year (1992-97) record of water quality data was used for network training, and additional data collected in 1998-2000 were used for model verification. Further, a GA was used with this ANN model to optimize the control of nutrient loads from the watershed. The GA was used as a search strategy to determine the proper reduction rates of nutrient loads from the watershed so that the objective function could be as close to the optimal value as possible. The study results indicate that the ANN model can effectively simulate the dynamics of reservoir water quality. The GA is able to identify control schemes that reduce the in-reservoir total phosphorus concentration by as much as 60%, and water quality in the reservoir can be expected to achieve an oligotrophic (most of the time) or mesotrophic level if the watershed nutrient loads are reduced by 10-80%.

Algorithms↗

PubMed2005

Beyond bistability: biophysics and temporal dynamics of working memory.

Working memory has often been modeled and conceptualized as a kind of binary (bistable) memory switch, where stimuli turn on plateau-like persistent activity in subsets of cells, in line with many in vivo electrophysiological reports. A potentially related form of bistability, termed up- and down-states, has been studied with regard to its synaptic and ionic basis in vivo and in reduced cortical preparations. Also single cell mechanisms for producing bistability have been proposed and investigated in brain slices and computationally. Recently, however, it has been emphasized that clear plateau-like bistable activity is rather rare during working memory tasks, and that neurons exhibit a multitude of different temporally unfolding activity profiles and temporal structure within their spiking dynamics. Hence, working memory seems to be a highly dynamical neural process with yet unknown mappings from dynamical to computational properties. Empirical findings on ramping activity profiles and temporal structure will be reviewed, as well as neural models that attempt to account for it and its computational significance. Furthermore, recent in vivo, neural culture, and in vitro preparations will be discussed that offer new possibilities for studying the biophysical mechanisms underlying computational processes during working memory. These preparations have revealed additional evidence for temporal structure and spatio-temporally organized attractor states in cortical networks, as well as for specific computational properties that may characterize synaptic processing during high-activity states as during working memory. Together such findings may lay the foundations for highly dynamical theories of working memory based on biophysical principles.

Action Potentials↗

PubMed2003

Dimension change, coarse grained coding and pattern recognition in spatio-temporal nonlinear systems.

Several research programs employing spatio-temporal recurrent dynamics and changes in dimensionality have extended the dialog on neural computation and coding beyond classical frameworks such as feed forward and attractor neural networks and feature detectors. Some have emphasized spiking networks, while others emphasize oscillations and synchronization as the locus of computation and coding. In this paper, the formalism of locally connected homogeneous coupled map lattices is described. Its deployment in an extended version of the dynamical recognizer framework is described, and is compared with density coding, computational mechanics, and liquid state machine frameworks for neural computation. A population coding strategy based on coarse graining the continuous valued distribution of all sites in the lattice is developed and examined as a form of dimension reduction. Results on recognition of 3-D objects are reported. In order to better understand the dynamics supporting recognition, measures suggested by these other research programs and computational frameworks were examined. Dynamics trajectories from object recognition trials were examined for correlation with recognition rates and measures of the distance of the representation space statistics between the target objects and noise initial conditions, and the intrinsic separation between different objects in the set to be classified were performed. These results raise questions about the efficacy of density coding as an explanation for the results, and on the validity of recent criticisms that chaotic systems cannot satisfy separation requirements required for real time computation.

Artifacts↗

PubMed2004

Roles of coherent ongoing oscillations among dynamic cell assemblies in object perception.

I constructed a cortical neural network model and investigated possible roles of coherent ongoing oscillations in membrane potentials of neurons in object perception. The model has a hierarchical structure consisting of two lower networks and one higher network that are reciprocally connected via divergent/convergent projections. Information about features and their relationships (or objects) is encoded by the population activities of neurons (or dynamic cell assemblies) of the lower networks and the higher network, respectively. The ongoing state of the network is expressed by 'random itinerancy' among these dynamic cell assemblies. Under the ongoing state, the dynamic cell assemblies belonging to the same object are transiently linked across the networks and coherently oscillate at lower frequencies (approximately 15 Hz). When the model perceives a presented object, the dynamic cell assemblies corresponding to the object are persistently linked together across the networks and coherently oscillate at higher frequencies (approximately 40 Hz). When the feedback pathways are impaired, the dynamic phase transition from the slow- to fast-oscillations is not induced by the object presentation, keeping the lower frequency oscillations (approximately 15 Hz) where the activated dynamic cell assemblies oscillate incoherently. Reaction times to the object presentation are greatly reduced if the ongoing oscillation frequencies fall within a specific range (approximately 20-30 Hz). I suggest that coherent ongoing slow-oscillations in cortical activity may serve as a ready state for sensory input, whereby the brain can respond effectively to sensory stimulation. Top-down processing via feedback pathways may give an essential contribution to the induction of coherent fast-oscillations across multiple cortical areas, by which relevant features are effectively integrated into a unified percept when stimulated with a sensory object.

Action Potentials↗

PubMedDate not supplied

Reliable disparity estimation through selective integration.

A network model of disparity estimation was developed based on disparity-selective neurons, such as those found in the early stages of processing in the visual cortex. The model accurately estimated multiple disparities in regions, which may be caused by transparency or occlusion. The selective integration of reliable local estimates enabled the network to generate accurate disparity estimates on normal and transparent random-dot stereograms. The model was consistent with human psychophysical results on the effects of spatial-frequency filtering on disparity sensitivity. The responses of neurons in macaque area V2 to random-dot stereograms are consistent with the prediction of the model that a subset of neurons responsible for disparity selection should be sensitive to disparity gradients.

Animals↗

PubMed1993

Prediction of protein secondary structure at better than 70% accuracy.

We have trained a two-layered feed-forward neural network on a non-redundant data base of 130 protein chains to predict the secondary structure of water-soluble proteins. A new key aspect is the use of evolutionary information in the form of multiple sequence alignments that are used as input in place of single sequences. The inclusion of protein family information in this form increases the prediction accuracy by six to eight percentage points. A combination of three levels of networks results in an overall three-state accuracy of 70.8% for globular proteins (sustained performance). If four membrane protein chains are included in the evaluation, the overall accuracy drops to 70.2%. The prediction is well balanced between alpha-helix, beta-strand and loop: 65% of the observed strand residues are predicted correctly. The accuracy in predicting the content of three secondary structure types is comparable to that of circular dichroism spectroscopy. The performance accuracy is verified by a sevenfold cross-validation test, and an additional test on 26 recently solved proteins. Of particular practical importance is the definition of a position-specific reliability index. For half of the residues predicted with a high level of reliability the overall accuracy increases to better than 82%. A further strength of the method is the more realistic prediction of segment length. The protein family prediction method is available for testing by academic researchers via an electronic mail server.

Mathematical Computing↗

PubMed2005

Theoretical note: the C/T ratio in artificial neural networks.

This paper describes computer simulations of the effect of the C/T ratio on acquisition rate in artificial neural networks. The networks consisted of neural processing elements that functioned according to a neurocomputational model whose learning rule is consistent with information on dopaminergic mechanisms of reinforcement. In Simulation 1, three comparisons were made: constant C and variable T, variable C and constant T, and a constant C/T with variable C and T. In the last two comparisons, C was manipulated by changing the probability of reinforcement within the intertrial interval (ITI), in the absence of the conditioned stimulus (CS). Acquisition rate tended to increase with C/T, and the invariant ratio had no effect. In Simulation 2, C was manipulated by changing the ITI, with continuous reinforcement in the presence of the CS and no reinforcements in its absence. Results were comparable to those obtained in Simulation 1. Simulation 3 further explored the effect of the invariant ratio, but with larger absolute values of C and T, which slowed acquisition significantly. The results parallel some experimental findings and theoretical implications of the Gibbon-Balsam model, showing that they can emerge from the moment-to-moment dynamics of a neural-network model. In contrast to that model, however, Simulation 3 suggests that the effect of invariant C/T ratios may be bounded.

Computer Simulation↗

PubMed2003

Estimation of pulmonary artery occlusion pressure by an artificial neural network.

OBJECTIVE: We hypothesized that an artificial neural network, interconnected computer elements capable of adaptation and learning, could accurately estimate pulmonary artery occlusion pressure from the pulsatile pulmonary artery waveform. SETTING: University medical center. SUBJECTS: Nineteen closed-chest dogs. INTERVENTIONS: Pulmonary artery waveforms were digitally sampled before conventional measurements of pulmonary artery occlusion pressure under control conditions, during infusions of serotonin or histamine, or during volume loading. Individual beats were parsed or separated out. Pulmonary artery pressure, its first time derivative, and the beat duration were used as neural inputs. The neural network was trained by using 80% of all samples and tested on the remaining 20%. For comparison, the regression between pulmonary artery diastolic pressure and pulmonary artery occlusion pressure was developed and tested using the same data sets. As a final test of generalizability, the neural network was trained on data obtained from 18 dogs and tested on data from the remaining dog in a round-robin fashion. MEASUREMENTS AND MAIN RESULTS: The correlation coefficient between the pulmonary artery diastolic pressure estimate of pulmonary artery occlusion pressure and measured pulmonary artery occlusion pressure was.75, whereas that for the neural network estimate of pulmonary artery occlusion pressure was.97 (p <.01 for difference between pulmonary artery diastolic pressure and pulmonary artery occlusion pressure estimates). The pulmonary artery diastolic pressure estimate of pulmonary artery occlusion pressure showed a bias of 0.097 mm Hg (limits of agreement -7.57 to 7.767 mm Hg), whereas the neural network estimate of pulmonary artery occlusion pressure showed a bias of -0.002 mm Hg (-2.592 to 2.588 mm Hg). There was no significant change in the bias of the neural network estimate over the range of values tested. In contrast, the bias for the pulmonary artery diastolic pressure estimate significantly increased with the increasing magnitude of the pulmonary artery occlusion pressure. During round-robin testing, the neural network estimate of pulmonary artery occlusion pressure showed suboptimal performance (correlation coefficient between estimated and measured pulmonary artery occlusion pressure.59). CONCLUSIONS: A neural network can accurately estimate pulmonary artery occlusion pressure over a wide range of pulmonary artery occlusion pressure under conditions that alter pulmonary hemodynamics. We speculate that artificial neural networks could provide accurate, real-time estimates of pulmonary artery occlusion pressure in critically ill patients.

Animals↗

PubMed1999

Real time image processing with an analog vision chip system.

A linear analog network model is proposed to characterize the function of the outer retinal circuit in terms of the standard regularization theory. Inspired by the function and the architecture of the model, a vision chip has been designed using analog CMOS Very Large Scale Integrated circuit technology. In the chip, sample/hold amplifier circuits are incorporated to compensate for statistic transistor mismatches. Accordingly, extremely low noise outputs were obtained from the chip. Using the chip and a zero-crossing detector, edges of given images were effectively extracted in indoor illumination.

Adaptation, Ocular↗

PubMed1997

Analyses on the temporal patterns of spikes of auditory neurons of the macaque monkey by means of an artificial neural network and tree-based models.

The time scale over which information in the primary auditory cortex is processed was estimated. An artificial neural network was used to learn the temporal patterns of spikes. After learning, test patterns were input to the network. Comparison of the accuracy of the network with that of the maximum likelihood function computed from the spike count reveals that the temporal patterns of spikes are closely related to stimulus discrimination. Next, a tree-based model from a subset of the spike trains with a fixed time resolution was constructed and validated the model with another. By repeating this for different bin widths, it was found that there are no simple models for the time bin width larger than 50 ms. This indicates that the time scale in the auditory cortex is not larger than 50 ms.

Animals↗

PubMed1996

Web interface for the Heart Disease Program.

The task of making a large complex diagnostic program available to a broad audience of physicians has become more feasible with the ubiquitous accessibility of the client-server architecture of the World Wide Web. This paper describes the design and implementation of a Web interface for the Heart Disease Program (HDP). The client-server architecture imposes a number of requirements on the program. The graphical capabilities of the Web enable a number of enhancements to the program but also cause some limitations. Our initial experience with physicians using the HDP through the Web interface has been positive and we are now conducting an evaluation of the HDP using this form of access.

Computer Communication Networks↗

PubMedDate not supplied

A neural network approach to approximating MAP in belief networks.

Bayesian belief networks (BBN) are a widely studied graphical model for representing uncertainty and probabilistic interdependence among variables. One of the factors that restricts the model's wide acceptance in practical applications is that the general inference with BBN is NP-hard. This is also true for the maximum a posteriori probability (MAP) problem, which is to find the most probable joint value assignment to all uninstantiated variables, given instantiation of some variables in a BBN. To circumvent the difficulty caused by MAP's computational complexity, we suggest in this paper a neural network approximation approach. With this approach, a BBN is treated as a neural network without any change or transformation of the network structure, and the node activation functions are derived based on an energy function defined over a given BBN. Three methods are developed. They are the hill-climbing style discrete method, the simulated annealing method, and the continuous method based on the mean field theory. All three methods are for BBN of general structures, with the restriction that nodes of BBN are binary variables. In addition, rules for applying these methods to noisy-or networks are also developed, which may lead to more efficient computation in some cases. These methods' convergence is analyzed, and their validity tested through a series of computer experiments with two BBN of moderate size and complexity. Although additional theoretical and empirical work is needed, the analysis and experiments suggest that this approach may lead to effective and accurate approximation for MAP problems.

Algorithms↗

PubMed1994

Energy minimization method using automata network for sequence and side-chain conformation prediction from given backbone geometry.

Globular proteins have high packing densities as a result of residue side chains in the core achieving a tight, complementary packing. The internal packing is considered the main determinant of native protein structure. From that point of view, we present here a method of energy minimization using an automata network to predict a set of amino acid sequences and their side-chain conformations from a desired backbone geometry for de novo design of proteins. Using discrete side-chain conformations, that is, rotamers, the sequence generation problem from a given backbone geometry becomes one of combinatorial problems. We focused on the residues composing the interior core region and predicted a set of amino acid sequences and their side-chain conformations only from a given backbone geometry. The kinds of residues were restricted to six hydrophobic amino acids (Ala, Ile, Met, Leu, Phe, and Val) because the core regions are almost always composed of hydrophobic residues. The obtained sequences were well packed as was the native sequence. The method can be used for automated sequence generation in the de novo design of proteins.

Bacterial Proteins↗

PubMed2005

Computational intelligence-based optimisation of wastewater treatment plants.

Methods of computational intelligence (CI), especially fuzzy control and neuronal networks, are used for controlling and optimising of wastewater treatment plants. Areas of application are the control of sludge water dosage, of phosphate elimination by optimal precipitant dosage as well as an optimal aeration in the nitrification zone. In two municipal wastewater treatment plants with 60,000 and 12,600 person equivalents the controllers have been installed and optimised and they have been in operation for several years. Results of operation of the plants are presented in comparison to previously used classical control. Performance increased significantly and the outflow values could be kept securely below the government requirements without increase of the energy consumption. Peak loads in the inflow were eliminated in the plant and did not increase outflow concentrations. Results of operation for more than three years clearly show that the CI controller is a cost-efficient method for a sustainable rise of performance in municipal wastewater treatment plants.

Artificial Intelligence↗

PubMed2002

Multi-objective cooperative coevolution of artificial neural networks (multi-objective cooperative networks).

In this paper we present a cooperative coevolutive model for the evolution of neural network topology and weights, called MOBNET. MOBNET evolves subcomponents that must be combined in order to form a network, instead of whole networks. The problem of assigning credit to the subcomponents is approached as a multi-objective optimization task. The subcomponents in a cooperative coevolutive model must fulfill different criteria to be useful, these criteria usually conflict with each other. The problem of evaluating the fitness on an individual based on many criteria that must be optimized together can be approached as a multi-criteria optimization problems, so the methods from multi-objective optimization offer the most natural way to solve the problem. In this work we show how using several objectives for every subcomponent and evaluating its fitness as a multi-objective optimization problem, the performance of the model is highly competitive. MOBNET is compared with several standard methods of classification and with other neural network models in solving four real-world problems, and it shows the best overall performance of all classification methods applied. It also produces smaller networks when compared to other models. The basic idea underlying MOBNET is extensible to a more general model of coevolutionary computation, as none of its features are exclusive of neural networks design. There are many applications of cooperative coevolution that could benefit from the multi-objective optimization approach proposed in this paper.

Biological Evolution↗

PubMed2002

Simplified normal mode analysis of conformational transitions in DNA-dependent polymerases: the elastic network model.

The Elastic Network Model is used to investigate the open/closed transition in all DNA-dependent polymerases whose structure is known in both forms. For each structure the model accounts well for experimental crystallographic B-factors. It is found in all cases that the transition can be well described with just a handful of the normal modes. Usually, only the lowest and/or the second lowest frequency normal modes deduced from the open form give rise to calculated displacement vectors that have a correlation coefficient larger than 0.50 with the observed difference vectors between the two forms. This is true for every structural class of DNA-dependent polymerases where a direct comparison with experimental structural data is available. In cases where only one form has been observed by X-ray crystallography, it is possible to make predictions concerning the possible existence of another form in solution by carefully examining the vector displacements predicted for the lowest frequency normal modes. This simple model, which has the advantage to be computationally inexpensive, could be used to design novel kind of drugs directed against polymerases, namely drugs preventing the open/closed transition from occurring in bacterial or viral DNA-dependent polymerases.

Computer Simulation↗

PubMed2005

Artificial neural network models for prediction of acute coronary syndromes using clinical data from the time of presentation.

STUDY OBJECTIVE: Clinical and ECG data from presentation are highly discriminatory for diagnosis of acute coronary syndromes, whereas definitive diagnosis from serial ECG and cardiac marker protein measurements is usually not available for several hours. Artificial neural networks are computer programs adept at pattern recognition tasks and have been used to analyze data from chest pain patients with a view to developing diagnostic algorithms that might improve triage practices in the emergency department. The aim of this study is to develop and optimize artificial neural network models for diagnosis of acute coronary syndrome, to test these models on data collected prospectively from different centers, and to establish whether the performance of these models was superior to that of models derived using a standard statistical technique, logistic regression. METHODS: The study used data from 3,147 patients presenting to 3 hospitals with acute chest pain. Data from hospital 1 were used to train the models, which were then tested on independent data from the other 2 hospitals. From 40 potential factors, variables were selected according to the logarithm of their likelihood ratios to produce models using 8, 13, 20, and 40 factors. Identical data were used for logistic regression and artificial neural network models. Calibration and performance were assessed, the latter using receiver operating characteristic (ROC) curve analysis. RESULTS: Although the performance of artificial neural network models generally increased with increasing numbers of factors, this was insignificant. The 13-factor model was therefore used for the rest of the study owing to its marginally improved calibration over the smallest model. Area under the ROC curve (with standard error) was 0.97 (0.006). The overall sensitivity and specificity of this model for acute coronary syndrome diagnosis using the training data was 0.93. ROC curves for logistic regression and artificial neural network models applied to data from the 3 hospitals were identical. For the 13-factor artificial neural network model tested on data from hospitals 2 and 3, area under the ROC curves (standard error) were 0.93 (0.006) and 0.95 (0.009), respectively. Investigation of the performance of the artificial neural network models throughout the range of predicted probabilities showed that they were well calibrated. CONCLUSION: This study confirms that artificial neural networks can offer a useful approach for developing diagnostic algorithms for chest pain patients; however, the exceptional performance and simplicity of the logistic model militates in favor of logistic regression for the present task. Our artificial neural network models were well calibrated and performed well on unseen data from different centers. These issues have not been addressed in previous studies. However, and unlike in previous studies, we did not find the performance of artificial neural network models to be significantly different from that of suitably optimized logistic regression models.

Adolescent↗

PubMed2003

Diagnostic and neural analysis of skin cancer (DANAOS). A multicentre study for collection and computer-aided analysis of data from pigmented skin lesions using digital dermoscopy.

BACKGROUND: Early detection of melanomas by means of diverse screening campaigns is an important step towards a reduction in mortality. Computer-aided analysis of digital images obtained by dermoscopy has been reported to be an accurate, practical and time-saving tool for the evaluation of pigmented skin lesions (PSLs). A prototype for the computer-aided diagnosis of PSLs using artificial neural networks (NNs) has recently been developed: diagnostic and neural analysis of skin cancer (DANAOS). OBJECTIVES: To demonstrate the accuracy of PSL diagnosis by the DANAOS expert system, a multicentre study on a diverse multinational population was conducted. METHODS: A calibrated camera system was developed and used to collect images of PSLs in a multicentre study in 13 dermatology centres in nine European countries. The dataset was used to train an NN expert system for the computer-aided diagnosis of melanoma. We analysed different aspects of the data collection and its influence on the performance of the expert system. The NN expert system was trained with a dataset of 2218 dermoscopic images of PSLs. RESULTS: The resulting expert system showed a performance similar to that of dermatologists as published in the literature. The performance depended on the size and quality of the database and its selection. CONCLUSIONS: The need for a large database, the usefulness of multicentre data collection, as well as the benefit of a representative collection of cases from clinical practice, were demonstrated in this trial. Images that were difficult to classify using the NN expert system were not identical to those found difficult to classify by clinicians. We suggest therefore that the combination of clinician and computer may potentially increase the accuracy of PSL diagnosis. This may result in improved detection of melanoma and a reduction in unnecessary excisions.

Adult↗