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 253 records · Page 14Linked to original sources
PubMed2003

An introduction to bio-inspired artificial neural network architectures.

In this introduction to artificial neural networks we attempt to give an overview of the most important types of neural networks employed in engineering and explain shortly how they operate and also how they relate to biological neural networks. The focus will mainly be on bio-inspired artificial neural network architectures and specifically to neo-perceptions. The latter belong to the family of convolutional neural networks. Their topology is somewhat similar to the one of the human visual cortex and they are based on receptive fields that allow, in combination with sub-sampling layers, for an improved robustness with regard to local spatial distortions. We demonstrate the application of artificial neural networks to face analysis--a domain we human beings are particularly good at, yet which poses great difficulties for digital computers running deterministic software programs.

Animals↗
PubMed1999

Transformation of an acetaminophen toxicity nomogram to an artificial neural network.

A computerized artificial neural network was built based on the Rumack-Matthew nomogram for treatment of acetaminophen toxicity. NeuralWorks Predict 1.0 was used to build the network. The training set consisted of two input parameters, plasma concentration (microg/ml) and time of ingestion, and an output. The output was a binary unit representing the recommended use of N-acetylcysteine for the prevention of acetaminophen hepatotoxicity. The predictions made by the neural network correlated well with the expected values (95%). Since these networks can be modified with additional data, the present network may be useful for optimizing the use of N-acetylcysteine for the prevention of acetaminophen hepatotoxicity.

Acetaminophen↗
PubMed2001

A late-stopping method for optimal aggregation of neural networks.

Ensembles of artificial neural networks have been used in the last years as classification/regression machines, showing improved generalization capabilities that outperform those of single networks. However, it has been recognized that for aggregation to be effective the individual networks must be as accurate and diverse as possible. An important problem is, then, how to tune the aggregate members in order to have an optimal compromise between these two conflicting conditions. We propose here a simple method for constructing regression/classification ensembles of neural networks that leads to overtrained aggregate members with an adequate balance between accuracy and diversity. The algorithm is favorably tested against other methods recently proposed in the literature, producing an improvement in performance on the standard statistical databases used as benchmarks. In addition, and as a concrete application, we apply our method to the sunspot time series and predict the remainder of the current cycle 23 of solar activity.

Data Collection↗
PubMed1995

Ensemble competitive learning neural networks with reduced input dimension.

Conventional neural networks utilize all the dimensions of the original input patterns for training and classification. However, a particular attribute of the input patterns does not necessarily contribute to classification and may even cause misclassification in certain cases. A new ensemble competitive learning method using the reduced input dimension is proposed. In contrast to the previous ensemble neural networks which adjust learning parameters, the proposed method takes advantage of the information in each dimension of the input patterns. Since the degree of contribution of each attribute to classification is not known beforehand, the different input data sets with one dimension reduced are presented to multiple neural networks. The classification information from each competitive learning neural network is then combined to make a final decision for classification. In order to improve classification accuracy, the ambiguous output neurons are eliminated which cannot be assigned to any class after training. We use three consensus schemes to judge the classification using ensemble neural networks. The experimental results with remote sensing and speech data indicate the improved performance of the proposed method.

Algorithms↗
PubMedDate not supplied

Fast determination of 13C NMR chemical shifts using artificial neural networks.

Nine different artificial neural networks were trained with the spherically encoded chemical environments of more than 500000 carbon atoms to predict their 13C NMR chemical shifts. Based on these results the PC-program "C_shift" was developed which allows the calculation of the 13C NMR spectra of any proposed molecular structure consisting of the covalently bonded elements C, H, N, O, P, S and the halogens. Results were obtained with a mean deviation as low as 1.8 ppm; this accuracy is equivalent to a determination on the basis of a large database but, in a time as short as known from increment calculations, was demonstrated exemplary using the natural agent epothilone A. The artificial neural networks allow simultaneously a precise and fast prediction of a large number of 13C NMR spectra, as needed for high throughput NMR and screening of a substance or spectra libraries.

Magnetic Resonance Spectroscopy↗
PubMedDate not supplied

Variable site-occupancy classification of N-linked glycosylation using artificial neural networks.

A novel neural-network-based model has been developed for the prediction of N-linked glycosylation characteristics related to glycosylation site-occupancy. Intracellular oligosaccharide transfer to a polypeptide is known to be either robust or dependent upon culture conditions during pharmaceutical production. This glycan attachment is classified by the model as robust or variable and is based on an input of the polypeptide primary sequence around the site of glycosylation. The glycosylation model utilizes multiple recurrent neural networks followed by a perceptron classifier. The input length of the polypeptide chain around the site of glycosylation (glycosylation window) was optimized through multiple independent training sessions. Incorporation of five residues prior (n - 5) to the site of glycosylation (n) and four residues beyond (n + 4) the glycan attachment site led to optimal network performance. The size of the glycosylation window for site-occupancy determination is much larger than has been previously reported. This model was developed to evaluate the effects of theoretical polypeptide mutations on glycosylation site-occupancy characteristics. Following correct prediction of the model testing data set, 20 independent networks were used to predict site-occupancy characteristics of wild-type and mutants of the rabies virus glycoprotein (rgp). Simulation results strongly correlated with previously published experimental results (Kasturi, L.; Hegang, C.; Shakin-Eshleman, S. H. Regulation of N-linked core glycosylation: use of a site-directed mutagenesis approach to identify Asn-Xaa-Ser/Thr sequons that are poor oligosacchride acceptors. Biochem. J. 1997, 323, 415-419. Mellquist, J. L.; Kasturi, L.; Spitalnik, S. L.; Shakin-Eshleman, S. H. The amino acid following an Asn-X-Ser/Thr sequon is an important determinant of N-linked core glycosylation efficiency. Biochemistry 1998, 37, 6833-6837). Further simulations on purely theoretical sequences suggested that influences of charged residues were a subset of multiple mechanisms in the determination of glycosylation site-occupancy.

Binding Sites↗
PubMed1996

Multispectral magnetic resonance images segmentation using fuzzy Hopfield neural network.

This paper demonstrates a fuzzy Hopfield neural network for segmenting multispectral MR brain images. The proposed approach is a new unsupervised 2-D Hopfield neural network based upon the fuzzy clustering technique. Its implementation consists of the combination of 2-D Hopfield neural network and fuzzy c-means clustering algorithm in order to make parallel implementation for segmenting multispectral MR brain images feasible. For generating feasible results, a fuzzy c-means clustering strategy is included in the Hopfield neural network to eliminate the need for finding weighting factors in the energy function which is formulated and based on a basic concept commonly used in pattern classification, called the 'within-class scatter matrix' principle. The suggested fuzzy c-means clustering strategy has also been proven to be convergent and to allow the network to learn more effectively than the conventional Hopfield neural network. The experimental results show that a near optimal solution can be obtained using the fuzzy Hopfield neural network based on the within-class scatter matrix.

Algorithms↗
PubMed1999

Leap-frog is a robust algorithm for training neural networks.

Optimization of perceptron neural network classifiers requires an optimization algorithm that is robust. In general, the best network is selected after a number of optimization trials. An effective optimization algorithm generates good weight-vector solutions in a few optimization trial runs owing to its inherent ability to escape local minima, where a less effective algorithm requires a larger number of trial runs. Repetitive training and testing is a tedious process, so that an effective algorithm is desirable to reduce training time and increase the quality of the set of available weight-vector solutions. We present leap-frog as a robust optimization algorithm for training neural networks. In this paper the dynamic principles of leap-frog are described together with experiments to show the ability of leap-frog to generate reliable weight-vector solutions. Performance histograms are used to compare leap-frog with a variable-metric method, a conjugate-gradient method with modified restarts, and a constrained-momentum-based algorithm. Results indicate that leap-frog performs better in terms of classification error than the remaining three algorithms on two distinctly different test problems.

Algorithms↗
PubMed2005

Prediction of seizure onset in an in-vitro hippocampal slice model of epilepsy using Gaussian-based and wavelet-based artificial neural networks.

We propose that artificial neural networks (ANNs) can be used to predict seizure onsets in an in-vitro hippocampal slice model capable of generating spontaneous seizure-like events (SLEs) in their extracellular field recordings. This paper assesses the effectiveness of two ANN prediction schemes: Gaussian-based artificial neural network (GANN) and wavelet-based artificial neural network (WANN). The GANN prediction system consists of a recurrent network having Gaussian radial basis function (RBF) nonlinearities capable of extracting the estimated manifold of the system. It is able to classify the underlying dynamics of spontaneous in-vitro activities into interictal, preictal and ictal modes. It is also able to successfully predict the onsets of SLEs as early as 60 s before. Improvements can be made to the overall seizure predictor design by incorporating time-varying frequency information. Consequently, the idea of WANN is considered. The WANN design entails the assumption that frequency variations in the extracellular field recordings can be used to compute the times at which onsets of SLEs are most likely to occur in the future. Progressions of different frequency components can be captured by the ANN using appropriate frequency band adjustments via pruning, after the initial wavelet transforms. In the off-line processing comprised of 102 spontaneous SLEs generated from 14 in-vitro rat hippocampal slices, with half of them used for training and the other half for testing, the WANN is able to predict the forecoming ictal onsets as early as 2 min prior to SLEs with over 75% accuracy within a 30 s precision window.

Animals↗
PubMed1998

Artificial neural networks in outcome prediction.

Artificial neural networks have been successfully used for pattern recognition and outcome prediction in several clinical settings. The advantage of a neural network is the ability of the model to capture nonlinearities and complex interactions between factors related to the outcome of interest. Neural networks also differ from other decision support systems in that the learning occurs by example through training and not by programming or pre-defined rules. Promising surgical applications include preoperative estimation of surgical risk and quality control within a hospital or health care system. An optimal system would estimate the outcome for the individual patient using all the prognostic and risk information inherent in the available patient characteristics.

Humans↗
PubMed2004

Estimation of bullet striation similarity using neural networks.

A new method that searches for similar striation patterns using neural networks is described. Neural networks have been developed based on the human brain, which is good at pattern recognition. Therefore, neural networks would be expected to be effective in identifying striated toolmarks on bullets. The neural networks used in this study deal with binary signals derived from striation images. This signal plays a significant role in identification, because this signal is the key to the individually of the striations. The neural network searches a database for similar striations by means of these binary signals. The neural network used here is a multilayer network consisting of 96 neurons in the input layer, 15 neurons in the middle, and one neuron in the output layer. Two signals are inputted into the network and a score is estimated based on the similarity of these signals. For this purpose, the network is assigned to a previous learning. To initially test the validity of the procedure, the network identifies artificial patterns that are randomly produced on a personal computer. The results were acceptable and showed robustness for the deformation of patterns. Moreover, with ten unidentified bullets and ten database bullets, the network consistently was able to select the correct pair.

Databases as Topic↗
PubMed1996

Artificial neural networks: current status in cardiovascular medicine.

Artificial neural networks are a form of artificial computer intelligence that have been the subject of renewed research interest in the last 10 years. Although they have been used extensively for problems in engineering, they have only recently been applied to medical problems, particularly in the fields of radiology, urology, laboratory medicine and cardiology. An artificial neural network is a distributed network of computing elements that is modeled after a biologic neural system and may be implemented as a computer software program. It is capable of identifying relations in input data that are not easily apparent with current common analytic techniques. The functioning artificial neural network's knowledge is built on learning and experience from previous input data. On the basis of this prior knowledge, the artificial neural network can predict relations found in newly presented data sets. In cardiology, artificial neural networks have been successfully applied to problems in the diagnosis and treatment of coronary artery disease and myocardial infarction, in electrocardiographic interpretation and detection of arrhythmias and in image analysis in cardiac radiography and sonography. This report focuses on the current status of artificial neural network technology in cardiovascular medical research.

Cardiology↗
PubMed1995

Mathematic modelling of the enteric nervous network. 5. Excitation propagation in a planar neural network.

A mathematical model of the enteric nervous system (Auerbach's plexus) as a planar neural network has been developed, based on the actual morphological data of its organization. The network is composed of excitatory (cholinergic) and inhibitory (adrenergic) neurones interconnected by polysynaptic channels, formed of the geometrically non-uniform unmyelinated nerve axons. The synaptic zones are modelled as a three-compartment open pharmacokinetics system, i.e., presynaptic terminal, synaptic cleft and postsynaptic membrane where the pharmacokinetic mechanisms of electrochemical coupling are considered. All the chemical reactions of transformation of acetylcholine and adrenaline within them are described by first order Michaelis-Menten kinetics. The propagation of the electrical impulse along the pathways and in the vicinity of the nerve terminal is described by the modified Hodgkin-Huxley equations. The results of numerical simulation of the propagation of excitation within the neuronal chain, inhibitory feedback circuit, and a planar neuronal network under normal physiological conditions and after treatment with cholinergic/adrenergic agonists and antagonists are presented. The model predicts the dose-dependent influence of pharmacological agents on the neural network function.

Action Potentials↗
PubMed1999

[The concept and use of artificial neural networks in medicine].

The use of neural networks in medicine is concentrated mainly on classification purposes. In particular, neural networks applications in spectroscopy are discussed, where this approach offers powerful algorithmic tools for interpretation of spectral data and elucidation of chemical structure of compounds. Neural networks are effective also for the classification and prediction of chemical reactivity and structure of proteins and also for QSAR and QSRR studies. At present the most successful use of neural networks in clinical medicine is image analysis and analysis of wave forms--ECG or EEG pattern recognition and classification and partly also clinical diagnosis and prognosis. (Tab. 7, Fig. 2, Ref. 170.)

Neural Networks, Computer↗
PubMed1992

Prediction of structural and functional features of protein and nucleic acid sequences by artificial neural networks.

The applications of artificial neural networks to the prediction of structural and functional features of protein and nucleic acid sequences are reviewed. A brief introduction to neural networks is given, including a discussion of learning algorithms and sequence encoding. The protein applications mostly involve the prediction of secondary and tertiary structure from sequence. The problems in nucleic acid analysis tackled by neural networks are the prediction of translation initiation sites in Escherichia coli, the recognition of splice junctions in human mRNA, and the prediction of promoter sites in E. coli. The performance of the approach is compared with other current statistical methods.

Algorithms↗
PubMedDate not supplied

[Use of artificial neural networks in clinical psychology and psychiatry].

Artificial neural networks make a highly specialised tools in data transformation. The human brain has become an inspiration for the makers of artificial neural networks. Although even though artificial neural networks are more frequently used in areas like financial analysis, marketing studies or economical modelling, their application in psychology and medicine has given a lot of promising and fascinating discoveries. It is worth that artificial neurol networks are successfully used in the diagnosis and etiopathogenesis description of various psychiatric disorders such as eating disorders, compulsions, depression or schizophrenia. To sum up, artificial neural networks offer a very promising option of research methodology for modern clinical psychology and psychiatry. The aim of this article is only an illustration of the applications of artificial neural networks in clinical psychology and psychiatry.

Diagnosis, Computer-Assisted↗
PubMed2004

Automatic artifact component removal using a neural network in MCG signal.

An algorithm combining a neural network and a principal component analysis (PCA) is proposed to remove a pulse-type artifact which often occurs in the 61 channel MCG system installed at Samsung Medical Center in Seoul, Korea. In the proposed work, the acquired signal is first decomposed into components by the PCA, and the components corresponding to the artifact are identified and removed by the neural network. The neural network is an essential component in the automation procedure. Unlike existing artifact rejection algorithms, the proposed algorithm is on a component-by-component basis, and the restored signal is used for further processing once the artifact components are successfully removed. Seven parameters are extracted from each time-domain component and are used as the input to the neural network. They are maximum, minimum, peak-to-peak value, variance, mean, skewness, and kurtosis. In the experiments with volunteers, 97% of the decisions made by the neural network are identical to those by the human experts. Using the proposed technique, the artifact was successfully removed from the MCG signal.

Artifacts↗
PubMed2006

Complex dynamics in simple Hopfield neural networks.

A class of simple Hopfield neural networks with a parameter is investigated. Numerical simulations show that the simple Hopfield neural networks can display chaotic attractors and limit cycles for different parameters. The Lyapunov exponents are calculated; the bifurcation plot and several important phase portraits are presented as well. By virtue of a recent result of horseshoe theory in dynamical systems, we present rigorous computer-assisted verifications for chaotic behavior in the simple Hopfield neural networks for certain parameters and give a brief discussion on the robustness of the chaotic behavior. Quantitative descriptions of the complexity of these neural networks are also given in terms of topological entropy.

Algorithms↗