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 1,513 records · Page 84Linked to original sources
PubMed1999

Segmental specification of GABAergic inhibition during development of hindbrain neural networks.

A primordial rhythm-generating neural network emerges during the segmental period of vertebrate hindbrain development, suggesting a common genetic basis to both the structure and network activity of the region. We show here that segmentation influenced a postsegmental developmental step by which a GABAergic rhythm generator was incorporated into the primordial network and increased rhythm frequency to near mature values. This process depended on specifications in r3 and r5 that controlled, on the basis of a two-segment repeat, later maturation of GABAergic inhibition.

Animals↗
PubMed1995

Evaluation of muscle diseases using artificial neural network analysis of 31P MR spectroscopy data.

Dermatomyositis is an autoimmune disease characterized by an erythematous rash and severe muscle weakness. 31P Magnetic resonance spectroscopy (MRS) provides quantitative data for longitudinal monitoring of disease status and responses to immunosuppressive therapy. A disease variant, amyopathic dermatomyositis, presents with a typical rash but no clinical muscle weakness. However, metabolic abnormalities in the oxidative capacity of muscles of amyopathic patients during exercise were detected with 31P MRS. Because MRS provided the best quantitative data for evaluating dermatomyositis, the 31P metabolic parameters derived from the MR spectra were further processed using an artificial neural network (XERION). The neural network analyses provided additional clinical information from the weighted correlations of multiple 31P parameters, namely, inorganic phosphate, phosphocreatine, ATP, phosphodiesters, and selected ratios. This investigation analyzes the relative importance of the various metabolic parameters for accurate patient characterization and provides insights into the pathogenesis of the disease.

Adenosine Triphosphate↗
PubMed1992

Segmenting ultrasound images of the prostate using neural networks.

This paper describes a method for segmenting transrectal ultrasound images of the prostate using feedforward neural networks. Segmenting two-dimensional images of the prostate into prostate and nonprostate regions is required when forming a three-dimensional image of the prostate from a set of parallel two-dimensional images. Three neural network architectures are presented as examples and discussed. Each of these networks was trained using a small portion of a training image segmented by an expert sonographer. The results of applying the trained networks to the entire training image and to adjacent images in the two-dimensional image set are presented and discussed. The final network architecture was also trained with additional data from two other images in the set. The results of applying this retrained network to each of the images in the set are presented and discussed.

Adult↗
PubMed1997

Neural network prediction of translation initiation sites in eukaryotes: perspectives for EST and genome analysis.

Translation in eukaryotes does not always start at the first AUG in an mRNA, implying that context information also plays a role. This makes prediction of translation initiation sites a non-trivial task, especially when analysing EST and genome data where the entire mature mRNA sequence is not known. In this paper, we employ artificial neural networks to predict which AUG triplet in an mRNA sequence is the start codon. The trained networks correctly classified 88% of Arabidopsis and 85% of vertebrate AUG triplets. We find that our trained neural networks use a combination of local start codon context and global sequence information. Furthermore, analysis of false predictions shows that AUGs in frame with the actual start codon are more frequently selected than out-of-frame AUGs, suggesting that our networks use reading frame detection. A number of conflicts between neural network predictions and database annotations are analysed in detail, leading to identification of possible database errors.

Amino Acid Sequence↗
PubMed2006

Analytic solution of neural network with disordered lateral inhibition.

The replica method has played a key role in analyzing systems with disorder, e.g., the Sherrington-Kirkpatrick (SK) model, and associative neural networks. Here we study the influence of disorder in the lateral inhibition type interactions on the cooperative and uncooperative behavior of recurrent neural networks by using the replica method. Although the interaction between neurons has a dependency on distance, our model can be solved analytically. Bifurcation analysis identifies the boundaries between paramagnetic, ferromagnetic, spin-glass, and localized phases. In the localized phase, the network shows a bump like activity, which is often used as a model of spatial working memory or columnar activity in the visual cortex. Simulation results show that disordered interactions can stabilize the drift the of bump position, which is commonly observed in conventional lateral inhibition type neural networks.

Journal Article↗
PubMed1999

Stability of neural networks and solitons of field theory.

The layers of a feed-forward neural network are interpreted as a cascade of field theories. The stability of the neural network is interpreted as the topological stability of kink solutions. An explicit example is shown for a three-class problem with their field theoretical Lagrangian equations.

Journal Article↗
PubMed1997

A neural network model for predicting pancreas transplant graft outcome.

OBJECTIVE: To compare the results of a neural network versus a logistic regression model for predicting early (0-3 months) pancreas transplant graft survival or loss. RESEARCH DESIGN AND METHODS: This study was a cross-sectional, secondary analysis of demographic and clinical data from 117 simultaneous pancreas-kidney (SPK), 35 pancreas-after-kidney (PAK), and 8 pancreas-transplant-alone (PTA) patients (n = 160). The majority of patients were men (57%) and were white (90.1%), with a mean age of 39 +/- 8.09 years. Of the patients, 23 (14.4%) experienced early graft loss, which included any loss owing to technical or immunological causes, and death with a functional graft. Data were analyzed with a logistic regression model for multivariate analysis and a backpropagation neural network (BPNN) model. RESULTS: A total of 12 predictor variables were chosen from literature and transplant surgeon recommendations. A logistic model with all predictor variables included correctly classified 93.53% of cases. Model sensitivity was 35.71%; specificity was 100% (pseudo-R2 0.24). Of the predictors, history of alcohol abuse (odds ratio [OR] 32.39; 95% CI 1.67-626.89), having a PAK or PTA (OR 13.6; 95% CI 2.20-84.01), and use of a nonlocal organ procurement center (OPO) (OR 4.51; 95% CI 0.78-25.96) were most closely associated with early graft loss. The BPNN model with the same 12 predictor variables correctly predicted 92.50% of cases (R2 0.71). Model sensitivity was 68%; specificity was 96%. Of the predictors, the three variables most closely associated with graft outcome in this model were recipient/donor weight difference >50 lb, having a PAK or PTA, and use of a nonlocal OPO. CONCLUSIONS: First, the BPNN model correctly predicted 92.5% of graft outcomes versus the logistic model (93.53%). Second, the BPNN model rendered more accurate predictions (>0.70 = loss; <0.30 = survival) versus the logistic model (>0.50 = loss; <0.50 = survival). Third, the BPNN model was more sensitive (68%) than the logistic model (35.71%) to graft failures and demonstrated an almost threefold increase in explained variance (R2 = 0.71 vs. 0.24). These results suggest that the BPNN model is a more powerful tool for predicting early pancreas graft loss than traditional multivariate statistical models.

Adolescent↗
PubMed1995

Signal transduction in bacteria: phospho-neural network(s) in Escherichia coli?

The molecular basis of many forms of signal transfer in living organisms is provided via the transient phosphorylation of regulatory proteins by transfer of phosphoryl groups between these proteins. The dominant form of signal transduction in prokaryotic microorganisms proceeds via so-called two-component regulatory systems. These systems constitute phosphoryl transfer pathways, consisting of two or more components. Most of these pathways are linear, but some converge and some are divergent. The molecular properties of some of the well-characterised representatives of two-component systems comply with the requirements to be put upon the elements of a neural network: they function as logical operators and show the phenomenon of autoamplification. Because there are many phosphoryl transfer pathways in parallel and because there also appears to be cross-talk between these pathways, the total of all two-component regulatory systems in a single prokaryotic cell may show the typical characteristics of a 'phospho-neural network'. This may well lead to signal amplification, associative responses and memory effects, characteristics which are typical for neural networks. One of the main challenges in molecular microbial physiology is to determine the extent of the connectivity of the constituting elements of this presumed 'phospho-neural network', and to outline the extent of intelligence-like behaviour this network can generate. Escherichia coli is the organism of choice for this characterization.

Escherichia coli↗
PubMed1998

Classification of observational data with artificial neural networks versus discriminant analysis in pharmacoepidemiological studies--can outcome of fluoxetine treatment be predicted?

For several years, there has been an ongoing discussion about appropriate methodological tools to be applied to observational data in pharmacoepidemiological studies. It is now suggested by our research group that artificial neural networks (ANN) might be advantageous in some cases for classification purposes when compared with discriminant analysis. This is due to their inherent capability to detect complex linear and nonlinear functions in multivariate data sets, the possibility of including data on different scales in the same model, as well as their relative resistance to "noisy" input. In this paper, a short introduction is given to the basics of neural networks and possible applications. For demonstration, a comparison between artificial neural networks and discriminant analysis was performed on a multivariate data set, consisting of observational data of 19738 patients treated with fluoxetine. It was tested, which of the two statistical tools outperforms the two other in regard to the therapeutic response prediction from the clinical input data. Essentially, it was found that neither discriminant analysis nor ANN are able to predict the clinical outcome on the basis of the employed clinical variables. Applying ANN, we were able to rule out the possibility of undetected suppressor effects to a greater extent than would have been possible by the exclusive application of discriminant analysis.

Antidepressive Agents, Second-Generation↗
PubMed1995

Side-chain prediction by neural networks and simulated annealing optimization.

The prediction of the side-chain positions of proteins of known tertiary backbone structure was accomplished by a combination of neural networks and a simulated annealing method. Neural networks were used to generate distributions of side-chain dihedral angles. By eliminating network outputs with low activities, we were able to generate a reduced conformational space in which Monte Carlo-simulated annealing was carried out to optimize side-chain positions. In this study of 12 proteins, the average fractions of correct chi 1, chi 2 and combined chi 1 and chi 2 (to within 40 degrees of actual structure) were 82, 72 and 68% respectively.

Amino Acids↗
PubMed2000

Forecasting summertime surface-level ozone concentrations in the Lower Fraser Valley of British Columbia: an ensemble neural network approach.

Empirical models for predicting daily maximum hourly average ozone concentrations were developed for 10 monitoring stations in the Lower Fraser Valley (LFV) of British Columbia. According to data from 1991 to 1996, ensemble neural network models increased explained variance an average of 7% over multiple linear regression models using the same input variables. Without modification, all models performed poorly on days when the observed peak ozone concentration exceeded 82 parts per billion, the National Ambient Air Quality Objective. When numbers of extreme events in training data were increased using a histogram equalization process, models were able to forecast exceedances with improved accuracy. Modified generalized additive model (GAM) plots and associated measures of input variable importance and interaction were generated for a subset of the trained models and used to investigate relationships between input variables and ozone levels. The neural network models displayed a high degree of interaction among inputs, and it is likely the ability of these model types to account for interactions, rather than the nonlinearity of individual input variables, that explains their improved forecast skill. Inspection of GAM-style plots indicated that the relative importance of input variables in the ensemble neural network models varied with geographic location within the LFV. Four distinct groups of stations were identified, and rankings of inputs within the groups were generally consistent with physical intuition and results of prior studies.

Algorithms↗
PubMed1994

Local noise in neural networks models with self-control.

We modify neural networks models of the Hopfield type so that they can recognize the degree of novelty of the input stimuli on a local level. The networks control themselves the quality of recognition and can also recognize locally the bits of information in the input patterns which do not agree with known patterns, i.e. stored memories. This task is achieved by introducing local variations of the noise level beta in the network. Noise level in a given location depends on the flip frequency of the neurons close to that location.

Mathematics↗
PubMed1994

Combining evolutionary information and neural networks to predict protein secondary structure.

Using evolutionary information contained in multiple sequence alignments as input to neural networks, secondary structure can be predicted at significantly increased accuracy. Here, we extend our previous three-level system of neural networks by using additional input information derived from multiple alignments. Using a position-specific conservation weight as part of the input increases performance. Using the number of insertions and deletions reduces the tendency for overprediction and increases overall accuracy. Addition of the global amino acid content yields a further improvement, mainly in predicting structural class. The final network system has sustained overall accuracy of 71.6% in a multiple cross-validation test on 126 unique protein chains. A test on a new set of 124 recently solved protein structures that have no significant sequence similarity to the learning set confirms the high level of accuracy. The average cross-validated accuracy for all 250 sequence-unique chains is above 72%. Using various data sets, the method is compared to alternative prediction methods, some of which also use multiple alignments: the performance advantage of the network system is at least 6 percentage points in three-state accuracy. In addition, the network estimates secondary structure content from multiple sequence alignments about as well as circular dichroism spectroscopy on a single protein and classifies 75% of the 250 proteins correctly into one of four protein structural classes. Of particular practical importance is the definition of a position-specific reliability index. For 40% of all residues the method has a sustained three-state accuracy of 88%, as high as the overall average for homology modelling. A further strength of the method is greatly increased accuracy in predicting the placement of secondary structure segments.

Amino Acid Sequence↗
PubMed2002

[Application of artificial neural network to simultaneous spectro-fluorimetric determination of phenol and resorcinol].

By the means of artificial neural network and Levenberg-Marquardt back-propagation train algorithm, the two components of phenol, resorcinol were determined simultaneously, in which the fluorescence spectra overlapped. In 290-345 nm, the fluorescence intensity at 14 wavelengths were taken as character of artificial neural network, and samples were arranged by method of equality design. The mean recovery of phenol and resorcinol were 100.2%, 99.99% respectively. The RSD of the results were 0.4% and 1.3%.

Algorithms↗
PubMed2005

Modeling of submerged membrane bioreactor treating cheese whey wastewater by artificial neural network.

A submerged membrane bioreactor receiving cheese whey was modeled by artificial neural network and its performance over a period of 100 days at different solids retention times was evaluated with this robust tool. A cascade-forward network was used to model the membrane bioreactor and normalization was used as a preprocessing method. The network was fed with two subsets of operational data, with two-thirds being used for training and one-third for testing the performance of the artificial neural network. The training procedure for effluent chemical oxygen demand (COD), ammonia, nitrate and total phosphate concentrations was very successful and a perfect match was obtained between the measured and the calculated concentrations. The results of the confirmation (or testing) procedure for effluent ammonia and nitrate concentrations were very successful; however, the results of the confirmation procedure for effluent COD and total phosphate concentrations were only satisfactory.

Algorithms↗
PubMed2003

Computer-assisted enhanced volumetric segmentation magnetic resonance imaging data using a mixture of artificial neural networks.

An accurate computer-assisted method able to perform regional segmentation on 3D single modality images and measure its volume is designed using a mixture of unsupervised and supervised artificial neural networks. Firstly, an unsupervised artificial neural network is used to estimate representative textures that appear in the images. The region of interest of the resultant images is selected by means of a multi-layer perceptron after a training using a single sample slice, which contains a central portion of the 3D region of interest. The method was applied to magnetic resonance imaging data collected from an experimental acute inflammatory model (T(2) weighted) and from a clinical study of human Alzheimer's disease (T(1) weighted) to evaluate the proposed method. In the first case, a high correlation and parallelism was registered between the volumetric measurements, of the injured and healthy tissue, by the proposed method with respect to the manual measurements (r = 0.82 and p < 0.05) and to the histopathological studies (r = 0.87 and p < 0.05). The method was also applied to the clinical studies, and similar results were derived of the manual and semi-automatic volumetric measurement of both hippocampus and the corpus callosum (0.95 and 0.88).

Abscess↗
PubMed1993

A neural network representation of electromyography and joint dynamics in human gait.

Optimization theory and other mathematical algorithms have traditionally been used to model the relationship between muscle activity and lower-limb dynamics during human gait. We introduce here an alternative approach, based on artificial neural networks with the back-propagation algorithm, to map two different transformations: (1) EMG-->joint angles; and (2) EMG-->joint moments. Normal data for 16 muscles and three joint moments and angles (hip, knee, and ankle) were adapted from the literature [Winter (1987), The Biomechanics and Motor Control of Human Gait]. Both networks were successfully trained to map the input vector onto the output vector. The models were tested by feeding in an input vector where all 16 muscles were slightly different (20%) from the training data, and the predicted output vectors suggested that the models were valid. The trained networks were then used to perform two separate simulations: 30% reduction in soleus activity; and removal of rectus femoris. Net 2, in which electromyography was mapped onto joint moments, provided the most reasonable results, suggesting that neural networks can provide a successful platform for both biomechanical modeling and simulation. We believe that this paper has demonstrated the potential of artificial neural networks, and that further efforts should be directed towards the development of larger training sets based on normal and pathological data.

Algorithms↗
PubMed2003

Detection of ophthalmic artery stenosis by least-mean squares backpropagation neural network.

Doppler ultrasound is a noninvasive technique that allows the examination of the direction, velocity, and volume of blood flow. In this study, ophthalmic artery Doppler signals were obtained from 105 subjects, 48 of whom had suffered from ophthalmic artery stenosis. A least-mean squares backpropagation neural network was used to detect the presence or absence of ophthalmic artery stenosis. Spectral analysis of ophthalmic artery Doppler signals was done by the Welch method for determining the neural network inputs. The network was trained, cross validated and tested with subject records from the database. Performance indicators and statistical measures were used for evaluating the neural network. Ophthalmic artery Doppler signals were classified with the accuracy varying from 88.9% to 90.6%.

Adolescent↗