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 1,045 records · Page 58Linked to original sources

PubMed1997

[The application of artificial neural network based on ambiguous function to heart sound classification].

In this study the artificial neural network was applied to heart sound classification. The network input data are ambiguous function, hence the crossterm problem of Wigner distribution is avoided. The simulation result shows that this is an effective technique. A suboptimal network model was proposed by many times of training and checking. The main factors related to network property were also discussed.

Aerospace Medicine↗

PubMed2006

Systems analyses characterize integrated functions of biochemical networks.

Metabolic, regulatory and signaling pathways have been characterized in detail over the past century. As the amount of genomic, proteomic and metabolic data has increased, and the mathematical and analytical capabilities of interrogating these data have advanced, the overlapping roles of pathway constituents have been described. These developments reflect the truly integrated nature of subcellular biochemical networks. Systems analyses, including the reconstruction of stoichiometric networks, provide a key set of tools for quantifying overlap among the metabolic, regulatory and signaling functions of network components. Accounting for this integration is crucial for accurately describing the function of biochemical networks.

Biochemistry↗

PubMed1999

Feature selection for optimized skin tumor recognition using genetic algorithms.

In this paper, a new approach to computer supported diagnosis of skin tumors in dermatology is presented. High resolution skin surface profiles are analyzed to recognize malignant melanomas and nevocytic nevi (moles), automatically. In the first step, several types of features are extracted by 2D image analysis methods characterizing the structure of skin surface profiles: texture features based on cooccurrence matrices, Fourier features and fractal features. Then, feature selection algorithms are applied to determine suitable feature subsets for the recognition process. Feature selection is described as an optimization problem and several approaches including heuristic strategies, greedy and genetic algorithms are compared. As quality measure for feature subsets, the classification rate of the nearest neighbor classifier computed with the leaving-one-out method is used. Genetic algorithms show the best results. Finally, neural networks with error back-propagation as learning paradigm are trained using the selected feature sets. Different network topologies, learning parameters and pruning algorithms are investigated to optimize the classification performance of the neural classifiers. With the optimized recognition system a classification performance of 97.7% is achieved.

Algorithms↗

PubMedDate not supplied

Simulation of a viral epidemic by means of a neural network.

The neurons of the network used for the simulation of a viral epidemic correspond to the individuals of the community. The activation state of the neurons reflects the contagious state of the diseased persons. Variable thresholds are introduced for the differentiation of the neuronal non-activation states (susceptible or immune subjects). The thresholds are calculated depending on the cumulated values over time of the neural activation states. The network functions synchronously. In order to follow up the state of the neural network, recurrence relations were introduced. They were applied in two epidemiological situations which differ from each other by the spreading intensity of the virus over time, reflected by the particular values ascribed to the elements of the neural connection matrix.

Child↗

PubMed2002

[Application of resilient backpropagation neural network in predicting hydrophobic parameters of alkylbenzenes].

Artificial neural networks have been applied for predicting the hydrophobic parameters of alkylbenzene. Compared with traditional methods it has the advantages of simple operation and wide applications. Based on error back propagation neural networks the relationship among the molecular connectivity index (chi), van der Waals surface area (Aw) and hydrophobic parameter was studied, meanwhile the mathematical model was established and used to predict the hydrophobic parameters. By comparing the hydrophobic parameters of experimental values with those calculated by neural networks, we found they had good agreement. The average relative deviation was less than 1%. Because traditional back propagation network is generally time consuming, resilient backpropagation (RPROP) algorithm was used to solve this problem. By using RPROP algorithm, the hydrophobic parameters were obtained precisely by fast training and simple parameter's selection. It needed less than 1,000 iterations to reach the goal on the computer operated at 1.4 GHz. The present work shows that the artificial neural network is a new powerful tool to predict the physicochemical parameters.

Algorithms↗

PubMed2004

Neuronal bases of perceptual learning revealed by a synaptic balance scheme.

Our ability to perceive external sensory stimuli improves as we experience the same stimulus repeatedly. This perceptual enhancement, called perceptual learning, has been demonstrated for various sensory systems, such as vision, audition, and somatosensation. I investigated the contribution of lateral excitatory and inhibitory synaptic balance to perceptual learning. I constructed a simple associative neural network model in which sensory features were expressed by the activities of specific cell assemblies. Each neuron is sensitive to a specific sensory feature, and the neurons belonging to the same cell assembly are sensitive to the same feature. During perceptual learning processes, the network was presented repeatedly with a stimulus that was composed of a sensory feature and noise, and the lateral excitatory and inhibitory synaptic connection strengths between neurons were modified according to a pulse-timing-based Hebbian rule. Perceptual learning enhanced the cognitive performance of the network, increasing the signal-to-noise ratio of neuronal activity. I suggest here that the alteration of the synaptic balance may be essential for perceptual learning, especially when the brain tries to adopt the most suitable strategy--signal enhancement, noise reduction, or both--for a given perceptual task.

Action Potentials↗

PubMed1998

Multilayer neural networks and Bayes decision theory.

There are many applications of multilayer neural networks to pattern classification problems in the engineering field. Recently, it has been shown that Bayes a posteriori probability can be estimated by feedforward neural networks through computer simulation. In this paper, Bayes decision theory is combined with the approximation theory on three-layer neural networks, and the two-category n-dimensional Gaussian classification problem is studied. First, we prove theoretically that three-layer neural networks with at least 2n hidden units have the capability of approximating the a posteriori probability in the two-category classification problem with arbitrary accuracy. Second, we prove that the input-output function of neural networks with at least 2n hidden units tends to the a posteriori probability as Back-Propagation learning proceeds ideally. These results provide a theoretical basis for the study of pattern classification by computer simulation.

Journal Article↗

PubMed1995

Artificial neural networks for screening patients needing emergency cranial computed tomography scans in emergency departments.

RATIONALE AND OBJECTIVES: We evaluated the potential for a neural network to screen candidates for emergency cranial computed tomography (CT) scans in an emergency department setting. METHODS: Data were collected from 1625 patients undergoing emergency cranial CT scanning in two different emergency departments (EDs). Singular value decomposition (SVD) was used to remap input data for network training. Data were randomly divided into six subsets, and one was reserved as a test set to analyze network performance. Five networks were then trained on data from the five remaining sets using fivefold cross-validation. Each trained network was allowed an independent vote on need for CT scanning in each case from the test set. The majority vote was used as the final prediction. A similar analysis was done on data from each individual ED. Results are compared with prior statistical studies of the same data. RESULTS: The network performed well when predicting clinical variable patterns that consistently produced negative CT scans and on patterns that were ambiguous in terms of the CT scan results. It performed poorly, however, on patterns that consistently predicted positive scans. This last finding appears to have resulted from inadequate training material. The two populations from which data were taken were shown to be distinct, but a network trained on the combined data performed as well as the networks from the individual EDs in predicting patients requiring CT scanning. Variables with the greatest contribution to the networks' prediction were consistent with those in prior statistical studies. CONCLUSION: Although preliminary in nature, neural networks show promise as a screening device for selecting patients for emergent cranial CT scanning.

Analysis of Variance↗

PubMed2006

Coherent ongoing subthreshold state of a cortical neural network regulated by slow- and fast-spiking interneurons.

Although details of cortical interneurons in anatomy and physiology have been well understood, little is known about how they contribute to ongoing spontaneous neuronal activity that could have a great impact on subsequent neuronal information processing. Simulating a cortical neural network model of an early sensory area, we investigated whether and how two distinct types of inhibitory interneurons, or fast-spiking interneurons with narrow axonal arbors and slow-spiking interneurons with wide axonal arbors, have a spatiotemporal influence on the ongoing activity of principal cells and subsequent cognitive information processing. In the model, dynamic cell assemblies, or population activation of principal cells, expressed information about specific sensory features. Within cell assemblies, fast-spiking interneurons give a feedback inhibitory effect on principal cells. Between cell assemblies, slow-spiking interneurons give a lateral inhibitory effect on principal cells. Here, we show that these interneurons keep the network at a subthreshold level for action potential generation under the ongoing state, by which the reaction time of principal cells to sensory stimulation could be accelerated. We suggest that the best timing of inhibition mediated by fast-spiking interneurons and slow-spiking interneurons allows the network to remain near threshold for rapid responses to input.

Action Potentials↗

PubMed1998

Simulating lipophilicity of organic molecules with a back-propagation neural network.

From a training set of 7200 chemicals, a back-propagation neural network (BNN) model was developed for calculating the 1-octanol/water partition coefficient (log P) of molecules containing nitrogen, oxygen, halogen, phosphorus, and/or sulfur atoms. Chemicals were described by means of autocorrelation vectors encoding hydrophobicity, molar refractivity, H-bonding acceptor ability, and H-bonding donor ability. A 35/32/1 composite network composed of four configurations was selected as the final model (root-mean-square error (RMS) = 0.37, r = 0.97) because it provided the best simulation results (RMS = 0.39, r = 0.98) on an external testing set of 519 molecules. This final model compared favorably with a recently published BNN model using variables (atoms and bonds) derived from connection matrices.

Computer Simulation↗

PubMed2003

Speeding up backpropagation using multiobjective evolutionary algorithms.

The use of backpropagation for training artificial neural networks (ANNs) is usually associated with a long training process. The user needs to experiment with a number of network architectures; with larger networks, more computational cost in terms of training time is required. The objective of this letter is to present an optimization algorithm, comprising a multiobjective evolutionary algorithm and a gradient-based local search. In the rest of the letter, this is referred to as the memetic Pareto artificial neural network algorithm for training ANNs. The evolutionary approach is used to train the network and simultaneously optimize its architecture. The result is a set of networks, with each network in the set attempting to optimize both the training error and the architecture. We also present a self-adaptive version with lower computational cost. We show empirically that the proposed method is capable of reducing the training time compared to gradient-based techniques.

Algorithms↗

PubMed2003

Polynomial harmonic GMDH learning networks for time series modeling.

This paper presents a constructive approach to neural network modeling of polynomial harmonic functions. This is an approach to growing higher-order networks like these build by the multilayer GMDH algorithm using activation polynomials. Two contributions for enhancement of the neural network learning are offered: (1) extending the expressive power of the network representation with another compositional scheme for combining polynomial terms and harmonics obtained analytically from the data; (2) space improving the higher-order network performance with a backpropagation algorithm for further gradient descent learning of the weights, initialized by least squares fitting during the growing phase. Empirical results show that the polynomial harmonic version phGMDH outperforms the previous GMDH, a Neurofuzzy GMDH and traditional MLP neural networks on time series modeling tasks. Applying next backpropagation training helps to achieve superior polynomial network performances.

Algorithms↗

PubMed1999

Telepathology and imaging spectroscopy as a new modality in histopathology.

Telemedicine started in the late 1950's by transmitting data on patients' pulse and heart rates. In the 1980's it expanded to radiology and orthopedics. The technology is now expanding to other specialties that can digitally gather patient data. Telepathology comprises the transmission of microscopic images via telecommunication network. Image compression and multiplexing technologies enabled high-resolution telepathology as well as real-time video consultations over international telephone lines. Organ transplantation has become a viable treatment and offers new life to an increasing number of patients suffering from chronic end stage diseases and from irreversible organ failure. Rejection is still a major problem in kidney, liver, and heart transplantation. To gain further insight into the complex interactions within the components of the immune system, it has become increasingly necessary to develop rapid and simple methods to monitor the status of the immune system in patients. Clinical signs suggest organ rejection and abnormal laboratory test results, but only histological signs on biopsy specimens are adequately specific. The financial cost of organ transplant makes it imperative to develop tools for the early identification and treatment of organ rejection. An increasingly sensitive and accurate way of localizing key structures and abnormalities is through spectroscopy of either H&E stained samples or with a fluorescent tag (fluorophore) or by relying on natural fluorescence. The system is based on a unique Prism and Mirror Imaging Spectroscopy System ("PARISS), spectrometer originally designed and implemented for remote Earth monitoring from space and aircraft and astronomical imaging spectroscopy. Compact and lightweight both the mirror and prism are presently constructed in inexpensive glass but can also be injection molded in plastic. Any number of vendors anywhere in the world can produce all parts of the assembly. This greatly enhances the chances of future commercial viability. The Interactive Histopathology Consultation Network INTERPATH (PL961121) project integrated of remote control imaging microscopy system, imaging spectroscopy, and communication networks called SPECTROMIC. This telepethology unit will be a useful tool in the Regional and International Integrated Telemedicine Network for Medical Assistance in End Stage Diseases and Organ Transplant, RETRANSPLANT HC 4028 (HC) & IN 4028 (HC).

Computer Systems↗

PubMed1999

[Artificial neural network application in spectral recognition].

An artificial neural network was devised and established for spectral matching. It was proved that when training sample spectra and unknown spectra had the same magnitude calibration, the network recognized spectra very well and had some advantages over other conventional spectral matching methods.

Computer Simulation↗

PubMed2000

Synaptic background activity enhances the responsiveness of neocortical pyramidal neurons.

Neocortical pyramidal neurons in vivo are subject to an intense synaptic background activity but little is known of how this activity affects cellular responsiveness and what function it may serve. These issues were examined in morphologically reconstructed neocortical pyramidal neurons in which synaptic background activity was simulated based on recent measurements in cat parietal cortex. We show that background activity can be decomposed into two components: a tonically active conductance and voltage fluctuations. Previous studies have mostly focused on the conductance effect, revealing that background activity is responsible for a decrease in responsiveness, which imposes severe conditions of coincidence of inputs necessary to discharge the cell. It is shown here, in contrast, that responsiveness is enhanced if voltage fluctuations are taken into account; in this case the model can produce responses to inputs that would normally be subthreshold. This effect is analyzed by dissecting and comparing the different components of background activity, as well as by evaluating the contribution of parameters such as the dendritic morphology, the distribution of leak currents, the value of axial resistivity, the densities of voltage-dependent currents, and the release parameters underlying background activity. Interestingly, the model's optimal responsiveness was obtained when voltage fluctuations were of the same order as those measured intracellularly in vivo. Possible consequences were also investigated at the population level, where the presence of background activity allowed networks of pyramidal neurons to instantaneously detect inputs that are small compared with the classical detection threshold. These results suggest, at the single-cell level, that the presence of voltage fluctuations has a determining influence on cellular responsiveness and that these should be taken into account in models of background activity. At the network level, we predict that background activity provides the necessary drive for detecting events that would normally be undetectable. Experiments are suggested to explore this possible functional role for background activity.

Action Potentials↗

PubMed1995

Evolving neural networks for detecting breast cancer.

Artificial neural networks are applied to the problem of detecting breast cancer from histologic data. Evolutionary programming is used to train the networks. This stochastic optimization method reduces the chance of becoming trapped in locally optimal weight sets. Preliminary results indicate that very parsimonious neural nets can outperform other methods reported in the literature on the same data. The results are statistically significant.

Breast Neoplasms↗

PubMed1999

Improved classifications of myocardial bull's-eye scintigrams with computer-based decision support system.

UNLABELLED: In a recent study, artificial neural networks were trained to detect coronary artery disease using scintigraphic data as input. The performance of the networks was better than that of human experts using coronary angiography as a gold standard. In clinical practice, this type of neural networks will not take over the decision-making process from the physician but will assist by proposing an interpretation of the scintigram. The purpose of this study was to assess the influence of such decision support on the interpretations of the physicians. METHODS: A population of 135 patients who had undergone both myocardial 99mTc-sestamibi rest/stress scintigraphy and coronary angiography within a 3-mo period was studied. An image set consisting of the bull's-eye rest, stress, difference and quote images was constructed for each patient. Three experienced physicians independently classified all image sets regarding the presence and/or absence of coronary artery disease in two vascular territories using a four-grade scale. The physicians classified the image sets twice with and twice without the advice of artificial neural networks. RESULTS: The joint evaluation of the three physicians showed significantly improved performance with decision support, measured as increases in the areas under the receiver operating characteristic curves from 0.65 to 0.70 (P = 0.018) and from 0.79 to 0.82 (P = 0.006) for two vascular territories. Furthermore, the joint evaluation showed significantly less intraobserver and interobserver variability with decision support. CONCLUSION: Physicians classifying myocardial bull's-eye images benefit from the advice of artificial neural networks. These results show the high potential for neural networks as clinical decision support systems.

Adult↗

PubMed2006

A new synaptic plasticity rule for networks of spiking neurons.

In this paper, we describe a new Synaptic Plasticity Activity Rule (SAPR) developed for use in networks of spiking neurons. Such networks can be used for simulations of physiological experiments as well as for other computations like image analysis. Most synaptic plasticity rules use artificially defined functions to modify synaptic connection strengths. In contrast, our rule makes use of the existing postsynaptic potential values to compute the value of adjustment. The network of spiking neurons we consider consists of excitatory and inhibitory neurons. Each neuron is implemented as an integrate-and-fire model that accurately mimics the behavior of biological neurons. To test performance of our new plasticity rule we designed a model of a biologically-inspired signal processing system, and used it for object detection in eye images of diabetic retinopathy patients, and lung images of cystic fibrosis patients. The results show that the network detects the edges of objects within an image, essentially segmenting it. Our ultimate goal, however, is not the development of an image segmentation tool that would be more efficient than nonbiological algorithms, but developing a physiologically correct neural network model that could be applied to a wide range of neurological experiments. We decided to validate the SAPR by using it in a network of spiking neurons for image segmentation because it is easy to visually assess the results. An important thing is that image segmentation is done in an entirely unsupervised way.

Algorithms↗