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 1,279 records · Page 71Linked to original sources
PubMed1996

Manipulator adaptive control by neural networks in an orange picking robot.

The paper focuses on the use of neural networks for process identification in an orange-picking robot adaptive control system. The results that will be shown in the paper refer to a study carried out under the European Community ESPRIT project "CONNY", dealing with the application of neural networks to robotics. The aim of the research is to verify the possibility of integrating a neural identification module in a traditional system to control the movement of the manipulators of the robot. The paper illustrates integration of neural identification in the existing orange-picking robot control system, highlighting the improvement of performance obtainable. Although the proposal refers to a specific robot, it can be applied to any system with the same dynamic features.

Adaptation, Psychological↗
PubMed2004

A neural network learning for adaptively extracting cross-correlation features between two high-dimensional data streams.

This paper proposes a novel cross-correlation neural network (CNN) model for finding the principal singular subspace of a cross-correlation matrix between two high-dimensional data streams. We introduce a novel nonquadratic criterion (NQC) for searching the optimum weights of two linear neural networks (LNN). The NQC exhibits a single global minimum attained if and only if the weight matrices of the left and right neural networks span the left and right principal singular subspace of a cross-correlation matrix, respectively. The other stationary points of the NQC are (unstable) saddle points. We develop an adaptive algorithm based on the NQC for tracking the principal singular subspace of a cross-correlation matrix between two high-dimensional vector sequences. The NQC algorithm provides a fast online learning of the optimum weights for two LNN. The global asymptotic stability of the NQC algorithm is analyzed. The NQC algorithm has several key advantages such as faster convergence, which is illustrated through simulations.

Algorithms↗
PubMed1997

Performance of a neural-network-based determination of amino acid class and secondary structure from 1H-15N NMR data.

A neural network which can determine both amino acid class and secondary structure using NMR data from 15N-labeled proteins is described. We have included nitrogen chemical shifts, 3JHNH alpha coupling constants, alpha-proton chemical shifts, and side-chain proton chemical shifts as input to a three-layer feed-forward network. The network was trained with 456 spin systems from several proteins containing various types of secondary structure, and tested on human ubiquitin, which has no sequence homology with any of the proteins in the training set. A very limited set of data, representative of those from a TOCSY-HSQC and HNHA experiment, was used. Nevertheless, in 60% of the spin systems the correct amino acid class was among the top two choices given by the network, while in 96% of the spin systems the secondary structure was correctly identified. The performance of this network clearly shows the potential of the neural network algorithm in the automation of NMR spectral analysis.

Amino Acids↗
PubMed2005

A novel neural network for the synthesis of antennas and microwave devices.

A novel artificial neural network (SYNTHESIS-ANN) is presented, which has been designed for computationally intensive problems and applied to the optimization of antennas and microwave devices. The antenna example presented is optimized with respect to voltage standing-wave ratio, bandwidth, and frequency of operation. A simple microstrip transmission line problem is used to further describe the ANN effectiveness, in which microstrip line width is optimized with respect to line impedance. The ANNs exploit a unique number representation of input and output data in conjunction with a more standard neural network architecture. An ANN consisting of a heteroassociative memory provided a very efficient method of computing necessary geometrical values for the antenna when used in conjunction with a new randomization process. The number representation used provides significant insight into this new method of fault-tolerant computing. Further work is needed to evaluate the potential of this new paradigm.

Algorithms↗
PubMed2000

Quantification of plasma lipids and apolipoproteins by use of proton NMR spectroscopy, multivariate and neural network analysis.

New approaches for quantification of human blood plasma lipids and apolipoproteins are presented. One method is based on multivariate analysis of proton nuclear magnetic resonance spectra of human blood plasma. Although similar approaches have been developed previously, this is the first time principal component analysis (PCA) and partial least squares regression (PLS) have been applied to this particular task. Further, a large proportion of the subjects in this study were cancer patients undergoing treatment, which introduced a new dimension to the quantification of lipoprotein distributions. Calibration models for prediction of lipids and apolipoproteins were constructed by use of PLS, and blind samples were used to test the predictive ability. Comparison of the predicted vs observed data obtained by standard clinical chemical procedures gave good agreement; the correlation coefficient for total plasma triglyceride was 0.99, for total plasma cholesterol 0.98, for LDL cholesterol 0. 97, and for HDL cholesterol 0.88. These results are comparable with those obtained with other methods. The quantitative analysis of 14 components (including total cholesterol and total triglyceride) of human blood plasma was also undertaken using various neural network (NN) analyses of selected portions of the spectra. Conventional fully connected backpropagation neural network topologies were capable of providing excellent predictions for the majority of the variables, confirming and reinforcing literature related to this approach. However HDL triglycerides were poorly predicted, while intermediate-quality results were obtained for the LDL cholesterol, plasma apoA1 and LDL apoB variables. In these instances, applying significantly different neural network algorithms involving either general regression or polynomial neural networks in combination with genetic adaptive components for parameter optimisation made improved predictions.

Adult↗
PubMed1999

Diagnostic assessment of brain tumours and non-neoplastic brain disorders in vivo using proton nuclear magnetic resonance spectroscopy and artificial neural networks.

PURPOSE: Experiments were carried out to assess the potential of artificial neural network (ANN) analysis in the differential diagnosis of brain tumours (low- and high-grade gliomas) from non-neoplastic focal brain lesions (tuberculomas and abscesses), using proton magnetic resonance spectroscopy (1H MRS) as input data. METHODS: Single-voxel stimulated echo acquisition mode (STEAM) (echo time of 20 ms) spectra were acquired from 138 subjects including 15 with low-grade gliomas, 47 with high-grade gliomas, 18 with tuberculomas, 18 with abscesses and 40 healthy controls. Two neural networks were constructed using the spectral points from 0.6 to 3.4 parts per million. In the first network construction, the ANN had to differentiate between tumours from infections, while the second network had to differentiate between all five histological classes. RESULTS: ANN analysis gave a histologically correct diagnosis for low- and high-grade gliomas with an accuracy of 73% and 98% respectively. None of the 62 tumours was diagnosed as an infectious lesion. Among the non-neoplastic lesions, ANN classification was correct in 89% of tuberculomas and in 83% of brain abscesses. The specificity of ANN diagnosis was 98%, 92%, 99%, and 100% for low-grade gliomas, high-grade gliomas, tuberculomas and abscesses respectively. CONCLUSION: The present data show the clinical utility of non-invasive 1H MRS by automated ANN analysis in the diagnosis of tumour and non-tumour cerebral disorders.

Adolescent↗
PubMed1999

Categorization in fully connected multistate neural network models.

The categorization ability of fully connected neural network models, with either discrete or continuous Q-state units, is studied in this work in replica symmetric mean-field theory. Hierarchically correlated multistate patterns in a two level structure of ancestors and descendents (examples) are embedded in the network and the categorization task consists in recognizing the ancestors when the network is trained exclusively with their descendents. Explicit results for the dependence of the equilibrium properties of a Q=3-state model and a Q=infinity-state model are obtained in the form of phase diagrams and categorization curves. A strong improvement of the categorization ability is found when the network is trained with examples of low activity. The categorization ability is found to be robust to finite threshold and synaptic noise. The Almeida-Thouless lines that limit the validity of the replica-symmetric results, are also obtained.

Learning↗
PubMed1996

Parallel processing of chemical information in a local area network--II. A parallel cross-validation procedure for artificial neural networks.

This paper describes a parallel cross-validation (PCV) procedure, for testing the predictive ability of multi-layer feed-forward (MLF) neural networks models, trained by the generalized delta learning rule. The PCV program has been parallelized to operate in a local area computer network. Development and execution of the parallel application was aided by the HYDRA programming environment, which is extensively described in Part I of this paper. A brief theoretical introduction on MLF networks is given and the problems, associated with the validation of predictive abilities, will be discussed. Furthermore, this paper comprises a general outline of the PCV program. Finally, the parallel PCV application is used to validate the predictive ability of an MLF network modeling a chemical non-linear function approximation problem which is described extensively in the literature.

Artificial Intelligence↗
PubMed2004

An alternative approach based on artificial neural networks to study controlled drug release.

An alternative methodology based on artificial neural networks is proposed to be a complementary tool to other conventional methods to study controlled drug release. Two systems are used to test the approach; namely, hydrocortisone in a biodegradable matrix and rhodium (II) butyrate complexes in a bioceramic matrix. Two well-established mathematical models are used to simulate different release profiles as a function of fundamental properties; namely, diffusion coefficient (D), saturation solubility (C(s)), drug loading (A), and the height of the device (h). The models were tested, and the results show that these fundamental properties can be predicted after learning the experimental or model data for controlled drug release systems. The neural network results obtained after the learning stage can be considered to quantitatively predict ideal experimental conditions. Overall, the proposed methodology was shown to be efficient for ideal experiments, with a relative average error of <1% in both tests. This approach can be useful for the experimental analysis to simulate and design efficient controlled drug-release systems.

Algorithms↗
PubMedDate not supplied

Defining a neural network controller structure for a rubbertuator robot.

Rubbertuator (Rubber-Actuator) robot arm is a pneumatic robot, unique with its lightweight, high power, compliant and spark free nature. Compressibility of air in the actuator tubes and the elastic nature of the rubber, however, are the two major sources of increased non-linearity and complexity in motion control. Soft computing, exploiting the tolerance of uncertainty and vagueness in cognitive reasoning has been offering easy to handle, robust, and low-priced solutions to several non-linear industrial applications. Nonetheless, the black-box approach in these systems results in application specific architectures with some important design parameters left for fine tuning (i.e. number of nodes in a neural network). In this study we propose a more systematic method in defining the structure of a soft computing technique, namely the backpropagation neural network, when used as a controller for rubbertuator robot systems. The structure of the neural network is based on the physical model of the robot, while the neural network itself is trained to learn the trajectory independent parameters of the model that are essential for defining the robot dynamics. The proposed system performance was compared with a well-tuned PID controller and shown to be more accurate in trajectory control for rubbertuator robots.

Elasticity↗
PubMed2002

A neural network approach to burst detection.

This paper describes how hydraulic and water quality data from a distribution network may be used to provide a more efficient leakage management capability for the water industry. The research presented concerns the application of artificial neural networks to the issue of detection and location of leakage in treated water distribution systems. An architecture for an Artificial Neural Network (ANN) based system is outlined. The neural network uses time series data produced by sensors to directly construct an empirical model for predication and classification of leaks. Results are presented using data from an experimental site in Yorkshire Water's Keighley distribution system.

Algorithms↗
PubMed2005

Automatic detection of epileptiform events in EEG by a three-stage procedure based on artificial neural networks.

This paper introduces a three-stage procedure based on artificial neural networks for the automatic detection of epileptiform events (EVs) in a multichannel electroencephalogram (EEG) signal. In the first stage, two discrete perceptrons fed by six features are used to classify EEG peaks into three subgroups: 1) definite epileptiform transients (ETs); 2) definite non-ETs; and 3) possible ETs and possible non-ETs. The pre-classification done in the first stage not only reduces the computation time but also increases the overall detection performance of the procedure. In the second stage, the peaks falling into the third group are aimed to be separated from each other by a nonlinear artificial neural network that would function as a postclassifier whose input is a vector of 41 consecutive sample values obtained from each peak. Different networks, i.e., a backpropagation multilayer perceptron and two radial basis function networks trained by a hybrid method and a support vector method, respectively, are constructed as the postclassifier and then compared in terms of their classification performances. In the third stage, multichannel information is integrated into the system for contributing to the process of identifying an EV by the electroencephalographers (EEGers). After the integration of multichannel information, the overall performance of the system is determined with respect to EVs. Visual evaluation, by two EEGers, of 19 channel EEG records of 10 epileptic patients showed that the best performance is obtained with a radial basis support vector machine providing an average sensitivity of 89.1%, an average selectivity of 85.9%, and a false detection rate (per hour) of 7.5.

Adolescent↗
PubMed2005

Outcome prediction after moderate and severe head injury using an artificial neural network.

Many studies have constructed predictive models for outcome after traumatic brain injury. Most of these attempts focused on dichotomous result, such as alive vs dead or good outcome vs poor outcome. If we want to predict more specific levels of outcome, we need more sophisticated models. We conducted this study to determine if artificial neural network modeling would predict outcome in five levels of Glasgow Outcome Scale (death, persistent vegetative state, severe disability, moderate disability, and good recovery) after moderate to severe head injury. The database was collected from a nation-wide epidemiological study of traumatic brain injury in Taiwan from July 1, 1995 to June 30, 1998. There were total 18583 records in this database and each record had thirty-two parameters. After pruning the records with minor cases (GCS 13) and missing data in the 132 variables, the number of cases decreased from 18583 to 4460. A step-wise logistic regression was applied to the remaining data set and 10 variables were selected as being statically significant in predicting outcome. These 10 variables were used as the input neurons for constructing neural network. Overall, 75.8% of predictions of this model were correct, 14.6% were pessimistic, and 9.6% optimistic. This neural network model demonstrated a significant difference of performance between different levels of Glasgow Outcome Scale. The prediction performance of dead or good recovery is best and the prediction of vegetative state is worst. An artificial neural network may provide a useful "second opinion" to assist neurosurgeon to predict outcome after traumatic brain injury.

Brain Injuries↗
PubMed2005

Application of artificial neural networks for predicting the aqueous acidity of various phenols using QSAR.

Artificial neural networks (ANNs) have been successfully trained to model and predict the acidity constants (pK(a)) of 128 various phenols with diverse chemical structures using a quantitative structure-activity relationship. An ANN with 6-14-1 architecture was generated using six molecular descriptors that appear in the multi-parameter linear regression (MLR) model. The polarizability term (pi (I)), most positive charge of acidic hydrogen atom (q+), molecular weight (MW), most negative charge of the phenolic oxygen atom (q-), the hydrogen-bond accepting ability (epsilon(B)) and partial-charge weighted topological electronic (PCWTE) descriptors are inputs and its output is pK(a). It was found that a properly selected and trained neural network with 106 phenols could represent the dependence of the acidity constant on molecular descriptors fairly well. For evaluation of the predictive power of the ANN, an optimized network was used to predict the pK(a)s of 22 compounds in the prediction set, which were not used in the optimization procedure. A squared correlation coefficient (R2) and root mean square error (RMSE) of 0.8950 and 0.5621 for the prediction set by the MLR model should be compared with the values of 0.99996 and 0.0114 by the ANN model. These improvements are due to the fact that the pK(a) of phenols shows non-linear correlations with the molecular descriptors. [Figure: see text].

Acids↗
PubMed2006

Parameter space structure of continuous-time recurrent neural networks.

A fundamental challenge for any general theory of neural circuits is how to characterize the structure of the space of all possible circuits over a given model neuron. As a first step in this direction, this letter begins a systematic study of the global parameter space structure of continuous-time recurrent neural networks (CTRNNs), a class of neural models that is simple but dynamically universal. First, we explicitly compute the local bifurcation manifolds of CTRNNs. We then visualize the structure of these manifolds in net input space for small circuits. These visualizations reveal a set of extremal saddle node bifurcation manifolds that divide CTRNN parameter space into regions of dynamics with different effective dimensionality. Next, we completely characterize the combinatorics and geometry of an asymptotically exact approximation to these regions for circuits of arbitrary size. Finally, we show how these regions can be used to calculate estimates of the probability of encountering different kinds of dynamics in CTRNN parameter space.

Animals↗
PubMed1999

Prediction of inhibitor binding free energies by quantum neural networks. Nucleoside analogues binding to trypanosomal nucleoside hydrolase.

A computational method has been developed to predict inhibitor binding energy for untested inhibitor molecules. A neural network is trained from the electrostatic potential surfaces of known inhibitors and their binding energies. The algorithm is then able to predict, with high accuracy, the binding energy of unknown inhibitors. IU-nucleoside hydrolase from Crithidia fasciculata and the inhibitor molecules described previously [Miles, R. W. Tyler, P. C. Evans, G. Furneaux R. H., Parkin, D. W., and Schramm, V. L. (1999) Biochemistry 38, xxxx-xxxx] are used as the test system. Discrete points on the molecular electrostatic potential surface of inhibitor molecules are input to neural networks to identify the quantum mechanical features that contribute to binding. Feed-forward neural networks with back-propagation of error are trained to recognize the quantum mechanical electrostatic potential and geometry at the entire van der Waals surface of a group of training molecules and to predict the strength of interactions between the enzyme and novel inhibitors. The binding energies of unknown inhibitors were predicted, followed by experimental determination of K(i)() values. Predictions of K(i)() values using this theory are compared to other methods and are more robust in estimating inhibitory strength. The average deviation in estimating K(i)() values for 18 unknown inhibitor molecules, with 21 training molecules, is a factor of 5 x K(i)() over a range of 660 000 in K(i)() values for all molecules. The a posteriori accuracy of the predictions suggests the method will be effective as a guide for experimental inhibitor design.

Animals↗
PubMed1993

Neural network approach for computer-assisted interpretation of ultrasound images of the gallbladder.

Multi-formatted films of 90 ultrasound examinations of the gallbladder (stones 56 cases, sludge 20 cases, hydrops five cases, normal gallbladder nine cases) have been digitalized and stored in a personal computer. Image data of each examination was processed to extract a 19-dimensional vector that represents the essential diagnostic information of each examination. This vector was evaluated by three different classification algorithms: (1) classical nearest neighbor principle, (2) classical linear discriminant analysis, (3) multilayered backpropagation neural network. The correct classification rate was 64% (58/90) for the nearest neighbor principle, 97% (87/90) for the linear discriminant analysis, and 99% (89/90) for the backpropagation neural network. We conclude that, (1) automated classification of ultrasound images is possible for limited diagnostic problems, (2) a neural network approach can be used successfully for that goal, and (3) the efficiency of the more flexible neural network approach is comparable to large-scale classical methods.

Cholecystography↗
PubMed1999

Application of neural networks to the modelling of some constitutive laws.

This study investigates the modelling of constitutive laws of materials by neural networks. Material behaviour is no longer represented mathematically but is described by neuronal modelling. The main aim is to build a neural network directly from experimental results (the learning phase). We give several examples of constitutive laws (Hooke, Sargin, etc.) using a backpropagation algorithm. Then we show that abilities of adjustment, memorisation and anticipation of neural networks permit us to develop a method of classification of constitutive laws.

Journal Article↗