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 1,585 records · Page 88Linked to original sources
PubMed1994

An artificial neural network analogue of learning in autism.

An artificial neural network is simulated that shares formal qualitative similarities with the selective attention and generalization deficits seen in people with autism. The model is based on neuropathological studies which suggest that affected individuals have either too few or too many neuronal connections in various regions of the brain. In simulations where the model was taught to discriminate children with autism from children with mental retardation, having too few simulated neuronal connections led to relatively inferior discrimination of the two groups in a training set and, consequently, relatively inferior generalization of the discrimination to a novel test set. Too many connections produced excellent discrimination but inferior generalization because of overemphasis on details unique to the training set. It is concluded that, within the context of the current model, the neuropathological observations that have been described in the literature are sufficient to explain some of the unique pattern recognition and discrimination learning abilities seen in some people with autism as well as their problems with generalization and concept acquisition. The model generates testable hypotheses that have implications for understanding the pathogenesis, treatment, and phenomenology of autism.

Analysis of Variance↗
PubMed2006

Neural network technology to predict intracellular water volume.

Artificial neural network (ANN) is increasingly applied in clinical medicine. We therefore constructed an ANN to predict intracellular water (ICW) volume in 44 healthy Taiwaners. Demographic and anthropometric data were recorded as predictors, and ICW volume measured by bioelectrical impedance analysis (ICW-BIA) was the reference. ICW volume predicted by ANN (ICW-ANN) was compared with ICW-BIA. ICW-BIA (21.26 +/- 0.58 l) and ICW-ANN (21.25 +/- 0.57 l) was insignificantly different (p = 0.76). ICW-BIA and ICW-ANN were strongly correlated (r = 0.94, p < 0.0001) with a significant agreement (mean difference, 0.01; lower and upper limits of agreement, -2.31 and 2.33) in Bland-Altman plot. Passing-Bablok regression was described as ICW-BIA = 1.04 x ICW-ANN - 0.49, with 95% confidence interval for slope 0.94-1.14 and for intercept -2.76-1.49, indicating that both methods were interchangeable. ANN provided an excellent alternative of BIA to predict ICW volume in healthy subjects.

Adult↗
PubMed1998

Discrimination between methicillin-resistant and methicillin-susceptible Staphylococcus aureus using pyrolysis mass spectrometry and artificial neural networks.

Curie-point pyrolysis mass spectra were obtained from 15 methicillin-resistant and 22 methicillin-susceptible Staphylococcus aureus strains. Cluster analysis showed that the major source of variation between the pyrolysis mass spectra resulted from the phage group of the bacteria, not their resistance or susceptibility to methicillin. By contrast, artificial neural networks could be trained to recognize those aspects of the pyrolysis mass spectra that differentiated methicillin-resistant from methicillin-sensitive strains. The trained neural network could then use pyrolysis mass spectral data to assess whether an unknown strain was resistant to methicillin. These results give the first demonstration that the combination of pyrolysis mass spectrometry with neural networks can provide a very rapid and accurate antibiotic susceptibility testing technique.

Cluster Analysis↗
PubMedDate not supplied

Neural network based temporal video segmentation.

The organization of video information in video databases requires automatic temporal segmentation with minimal user interaction. As neural networks are capable of learning the characteristics of various video segments and clustering them accordingly, in this paper, a neural network based technique is developed to segment the video sequence into shots automatically and with a minimum number of user-defined parameters. We propose to employ growing neural gas (GNG) networks and integrate multiple frame difference features to efficiently detect shot boundaries in the video. Experimental results are presented to illustrate the good performance of the proposed scheme on real video sequences.

Algorithms↗
PubMed2000

Learning chaotic attractors by neural networks.

An algorithm is introduced that trains a neural network to identify chaotic dynamics from a single measured time series. During training, the algorithm learns to short-term predict the time series. At the same time a criterion, developed by Diks, van Zwet, Takens, and de Goede (1996) is monitored that tests the hypothesis that the reconstructed attractors of model-generated and measured data are the same. Training is stopped when the prediction error is low and the model passes this test. Two other features of the algorithm are (1) the way the state of the system, consisting of delays from the time series, has its dimension reduced by weighted principal component analysis data reduction, and (2) the user-adjustable prediction horizon obtained by "error propagation"-partially propagating prediction errors to the next time step. The algorithm is first applied to data from an experimental-driven chaotic pendulum, of which two of the three state variables are known. This is a comprehensive example that shows how well the Diks test can distinguish between slightly different attractors. Second, the algorithm is applied to the same problem, but now one of the two known state variables is ignored. Finally, we present a model for the laser data from the Santa Fe time-series competition (set A). It is the first model for these data that is not only useful for short-term predictions but also generates time series with similar chaotic characteristics as the measured data.

Algorithms↗
PubMed2003

Discrimination of poly(vinyl chloride) samples with different plasticizers and prediction of plasticizer contents in poly(vinyl chloride) using near-infrared spectroscopy and neural-network analysis.

In the recycling of poly(vinyl chloride) (PVC), it is required to discriminate every plasticizer for quality control. For this purpose, the near-infrared spectra were measured for 41 kinds of PVC samples with different plasticizers (DINP, DOP, DOA, TOTM and Polyester) and different plasticizer contents (0-49%). A neural-network analysis was applied to the near-infrared spectra pretreated by second-derivative processing. They were discriminated from one another. The neural-network analysis also allowed us to propose a calibration model which predicts the contents of plasticizers in PVC. The correlation coefficient (R) and the root-mean-square error of prediction (RMSEP) for the DINP calibration model were found to be 0.999 and 0.41 wt%, respectively. In comparison, a partial least-squares regression analysis was carried out. The R and RMSEP of the DINP calibration model were calculated to be 0.993 and 1.27 wt%, respectively. It is found that a near-infrared spectra measurement combined with a neural-network analysis is useful for plastic recycling.

Conservation of Natural Resources↗
PubMed2003

Identification of land use with water quality data in stormwater using a neural network.

To control stormwater pollution effectively, development of innovative, land-use-related control strategies will be required. An approach that could differentiate land-use types from stormwater quality would be the first step to solving this problem. We propose a neural network approach to examine the relationship between stormwater water quality and various types of land use. The neural network model can be used to identify land-use types for future known and unknown cases. The neural model uses a Bayesian network and has 10 water quality input variables, four neurons in the hidden layer, and five land-use target variables (commercial, industrial, residential, transportation, and vacant). We obtained 92.3 percent of correct classification and 0.157 root-mean-squared error on test files. Based on the neural model, simulations were performed to predict the land-use type of a known data set, which was not used when developing the model. The simulation accurately described the behavior of the new data set. This study demonstrates that a neural network can be effectively used to produce land-use type classification with water quality data.

Agriculture↗
PubMed1999

Using artificial neural network analysis of global ventilation-perfusion scan morphometry as a diagnostic tool.

OBJECTIVE: The purpose of this study was to determine whether global statistical data from radionuclide ventilation-perfusion scans could predict the likelihood of pulmonary embolism. MATERIALS AND METHODS: Digital data were obtained from 161 patients undergoing both radionuclide ventilation-perfusion scanning and subsequent pulmonary angiography. Morphometric data characterizing whole-lung perfusion and ventilation parameters were input into artificial neural networks in an attempt to predict the likelihood of pulmonary embolism. RESULTS: The performance of artificial neural networks using only automated global region of interest-based data was superior to that of clinicians in predicting the likelihood of acute pulmonary embolism in patients with normal findings on chest radiographs with segmental or larger emboli (p < .005) and in patients with normal findings on chest radiographs and emboli of any size (p < .01). Network performance did not significantly differ from clinician performance in patients with abnormal findings on chest radiographs. CONCLUSION: The adjunctive use of artificial neural networks using only user-independent, standard image statistics can significantly improve accuracy in the diagnosis of pulmonary embolism in patients with normal findings on chest radiographs.

Humans↗
PubMed2006

Intelligent adaptive nonlinear flight control for a high performance aircraft with neural networks.

This paper describes the development of a neural network (NN) based adaptive flight control system for a high performance aircraft. The main contribution of this work is that the proposed control system is able to compensate the system uncertainties, adapt to the changes in flight conditions, and accommodate the system failures. The underlying study can be considered in two phases. The objective of the first phase is to model the dynamic behavior of a nonlinear F-16 model using NNs. Therefore a NN-based adaptive identification model is developed for three angular rates of the aircraft. An on-line training procedure is developed to adapt the changes in the system dynamics and improve the identification accuracy. In this procedure, a first-in first-out stack is used to store a certain history of the input-output data. The training is performed over the whole data in the stack at every stage. To speed up the convergence rate and enhance the accuracy for achieving the on-line learning, the Levenberg-Marquardt optimization method with a trust region approach is adapted to train the NNs. The objective of the second phase is to develop intelligent flight controllers. A NN-based adaptive PID control scheme that is composed of an emulator NN, an estimator NN, and a discrete time PID controller is developed. The emulator NN is used to calculate the system Jacobian required to train the estimator NN. The estimator NN, which is trained on-line by propagating the output error through the emulator, is used to adjust the PID gains. The NN-based adaptive PID control system is applied to control three angular rates of the nonlinear F-16 model. The body-axis pitch, roll, and yaw rates are fed back via the PID controllers to the elevator, aileron, and rudder actuators, respectively. The resulting control system has learning, adaptation, and fault-tolerant abilities. It avoids the storage and interpolation requirements for the too many controller parameters of a typical flight control system. Performance of the control system is successfully tested by performing several six-degrees-of-freedom nonlinear simulations.

Aircraft↗
PubMed2005

Efficient training algorithms for a class of shunting inhibitory convolutional neural networks.

This article presents some efficient training algorithms, based on first-order, second-order, and conjugate gradient optimization methods, for a class of convolutional neural networks (CoNNs), known as shunting inhibitory convolution neural networks. Furthermore, a new hybrid method is proposed, which is derived from the principles of Quickprop, Rprop, SuperSAB, and least squares (LS). Experimental results show that the new hybrid method can perform as well as the Levenberg-Marquardt (LM) algorithm, but at a much lower computational cost and less memory storage. For comparison sake, the visual pattern recognition task of face/nonface discrimination is chosen as a classification problem to evaluate the performance of the training algorithms. Sixteen training algorithms are implemented for the three different variants of the proposed CoNN architecture: binary-, Toeplitz- and fully connected architectures. All implemented algorithms can train the three network architectures successfully, but their convergence speed vary markedly. In particular, the combination of LS with the new hybrid method and LS with the LM method achieve the best convergence rates in terms of number of training epochs. In addition, the classification accuracies of all three architectures are assessed using ten-fold cross validation. The results show that the binary- and Toeplitz-connected architectures outperform slightly the fully connected architecture: the lowest error rates across all training algorithms are 1.95% for Toeplitz-connected, 2.10% for the binary-connected, and 2.20% for the fully connected network. In general, the modified Broyden-Fletcher-Goldfarb-Shanno (BFGS) methods, the three variants of LM algorithm, and the new hybrid/LS method perform consistently well, achieving error rates of less than 3% averaged across all three architectures.

Algorithms↗
PubMed2003

Using a neural network and spatial clustering to predict the location of active sites in enzymes.

Structural genomics projects aim to provide a sharp increase in the number of structures of functionally unannotated, and largely unstudied, proteins. Algorithms and tools capable of deriving information about the nature, and location, of functional sites within a structure are increasingly useful therefore. Here, a neural network is trained to identify the catalytic residues found in enzymes, based on an analysis of the structure and sequence. The neural network output, and spatial clustering of the highly scoring residues are then used to predict the location of the active site.A comparison of the performance of differently trained neural networks is presented that shows how information from sequence and structure come together to improve the prediction accuracy of the network. Spatial clustering of the network results provides a reliable way of finding likely active sites. In over 69% of the test cases the active site is correctly predicted, and a further 25% are partially correctly predicted. The failures are generally due to the poor quality of the automatically generated sequence alignments. We also present predictions identifying the active site, and potential functional residues in five recently solved enzyme structures, not used in developing the method. The method correctly identifies the putative active site in each case. In most cases the likely functional residues are identified correctly, as well as some potentially novel functional groups.

Algorithms↗
PubMed1999

The backpropagation algorithm in J, a fast prototyping tool for researching neural networks.

This paper illustrates the use of a powerful language, called J, that is ideal for simulating neural networks. The use of J is demonstrated by its application to a gradient descent method for training a multilayer perceptron. It is also shown how the back-propagation algorithm can be easily generalized to multilayer networks without any increase in complexity and that the algorithm can be completely expressed in an array notation which is directly executable through J. J is a general purpose language, which means that its user is given a flexibility not available in neural network simulators or in software packages such as MATLAB. Yet, because of its numerous operators, J allows a very succinct code to be used, leading to a tremendous decrease in development time.

Algorithms↗
PubMed2001

Simultaneous quantitative UV spectrophotometric determination of multicomponents of amino acids using linear neural network.

Simultaneous determination of multicomponents of six amino acids with a novel chemometric technique-a linear neural network (LNN) algorithm is reported in this study. Based on the data correlation coefficient and standard deviation method, 17 representative wavelength points are selected from the original UV spectral data (343 points) as the original input patterns for LNN to build a neural network model. The results obtained only by iterating 15 times is satisfying, with a correlation coefficient of 0.999 and a relative small standard deviation.

Algorithms↗
PubMed2006

Collision detection in complex dynamic scenes using an LGMD-based visual neural network with feature enhancement.

The lobula giant movement detector (LGMD) is an identified neuron in the locust brain that responds most strongly to the images of an approaching object such as a predator. Its computational model can cope with unpredictable environments without using specific object recognition algorithms. In this paper, an LGMD-based neural network is proposed with a new feature enhancement mechanism to enhance the expanded edges of colliding objects via grouped excitation for collision detection with complex backgrounds. The isolated excitation caused by background detail will be filtered out by the new mechanism. Offline tests demonstrated the advantages of the presented LGMD-based neural network in complex backgrounds. Real time robotics experiments using the LGMD-based neural network as the only sensory system showed that the system worked reliably in a wide range of conditions; in particular, the robot was able to navigate in arenas with structured surrounds and complex backgrounds.

Algorithms↗
PubMed2006

Techniques for biased data distributions and variable classification with neural networks applied to otoneurological data.

It is frequently useful and advantageous to investigate not only the classification efficacy of neural networks, but also the reasons for misclassification and relations between input variables and output classes. We have developed novel techniques to disentangle these dilemmas: a network structure and learning strategy for biased output class distributions, a method to measure the classification information incorporated in variables and variable groups, and methods to express properties learned by a network from its structure. We tested these techniques with otoneurological data from the conjunction with vertiginous diseases that we have explored in our previous neural network studies.

Bias↗
PubMed1989

Noise in neural networks: thresholds, hysteresis, and neuromodulation of signal-to-noise.

We study a neural-network model including Gaussian noise, higher-order neuronal interactions, and neuromodulation. For a first-order network, there is a threshold in the noise level (phase transition) above which the network displays only disorganized behavior and critical slowing down near the noise threshold. The network can tolerate more noise if it has higher-order feedback interactions, which also lead to hysteresis and multistability in the network dynamics. The signal-to-noise ratio can be adjusted in a biological neural network by neuromodulators such as norepinephrine. Comparisons are made to experimental results and further investigations are suggested to test the effects of hysteresis and neuromodulation in pattern recognition and learning. We propose that norepinephrine may "quench" the neural patterns of activity to enhance the ability to learn details.

Animals↗
PubMed1994

Neural network for control of rearrangeable Clos networks.

Rapid evolution in the field of communication networks requires high speed switching technologies. This involves a high degree of parallelism in switching control and routing performed at the hardware level. The multistage crossbar networks have always been attractive to switch designers. In this paper a neural network approach to controlling a three-stage Clos network in real time is proposed. This controller provides optimal routing of communication traffic requests on a call-by-call basis by rearranging existing connections, with a minimum length of rearrangement sequence so that a new blocked call request can be accommodated. The proposed neural network controller uses Paull's rearrangement algorithm, along with the special (least used) switch selection rule in order to minimize the length of rearrangement sequences. The functional behavior of our model is verified by simulations and it is shown that the convergence time required for finding an optimal solution is constant, regardless of the switching network size. The performance is evaluated for random traffic with various traffic loads. Simulation results show that applying the least used switch selection rule increases the efficiency in switch rearrangements, reducing the network convergence time. The implementation aspects are also discussed to show the feasibility of the proposed approach.

Algorithms↗
PubMedDate not supplied

[Neural network modeling of triiodothyronine concentrations by the levels of lymphocytic NADP-dependent dehydrogenases in patients with thyroid hypo- and hyperfunction].

Whether a computer model which calculates serum triiodothyronine concentrations (T3) can be constructed by the levels of metabolic enzymes in the immunocompetent cells by means of a neural network predictor of real numbers. For this, the concentration of serum T3 and the activity lymphocytic NADP-dependent dehydrogenases were determined by radioimmune assay and bioluminescence technique, respectively. It was found that the neural network prediction might be only in each examined group alone. Conceivably, this is associated with the presence of compensatory processes of intracellular metabolism at high and low concentrations of thyroid hormones. The involvement of the examined enzymes in the metabolic mechanisms of immuno-endocrine interaction both in health and in disease, as well as in the thyroid hypo- and hyperfunction can be judged from the value of the input parameters of the neural network model.

Adult↗