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 541 records · Page 30Linked to original sources
PubMedDate not supplied

Neural network applications in physical medicine and rehabilitation.

The purpose of this article is to provide an overview of neural networks and their applications in physical medicine and rehabilitation. Conventional statistical models may present certain limitations that can be overcome by neural networks. We show what neural networks are, how they "learn" regularities from the data, and how they can classify previously unseen cases. We present advantages and disadvantages of using neural networks and compare them with regression models. We explain how neural networks can be used as statistical tools for making inferences using the example of a prognostic model that predicts ambulation after spinal cord injury.

Humans↗
PubMed2005

Comparative analysis of logistic regression and artificial neural network for computer-aided diagnosis of breast masses.

RATIONALE AND OBJECTIVE: To compare logistic regression and artificial neural network for computer-aided diagnosis on breast sonograms. MATERIALS AND METHODS: Ultrasound images of 24 malignant and 30 benign masses were analyzed quantitatively for margin sharpness, margin echogenicity, and angular variation in margin. These features and age of patients were used with two pattern classifiers, logistic regression, and an artificial neural network to differentiate between malignant and benign masses. The performance of two methods was compared by receiver operating characteristic (ROC) analysis. RESULTS: The area under the ROC curve Az (+/-SD) of the logistic regression analysis was 0.853 +/- 0.059 with 95% confidence limit (0.760-0.950). The area under the ROC curve of the artificial neural network analysis was 0.856 +/- 0.058 with 95% confidence limit (0.734-0.936). Although both the logistic regression and the artificial neural network had the same area under the ROC curve, the shapes of two curves were different. At 95% sensitivity, the artificial neural network had 76.5% specificity, whereas logistic regression had 64.7% specificity. CONCLUSION: There was no difference in performance between logistic regression and the artificial neural network as measured by the area under the ROC curve. However, at a fixed 95% sensitivity, the artificial neural network had higher (12%) specificity compared with logistic regression value.

Breast Neoplasms↗
PubMed1979

Structure and dynamics of neural network oscillators.

Techniques are given to represent oscillating neural networks by asynchronous logical switching networks, and to analyze the oscillating networks using a directed graph called a state transition diagram. Consideration is restricted to network oscillators containing no rhythm determining pacemaker neurons, and no neurons exhibiting self-limiting properties such as post-inhibitory rebound or accumulating refractoriness. In the state transition diagrams, stable oscillations are associated with a particular geometric configuration called a cyclic attractor (the heavy cycle in Fig. 2). We show that given the network connectivity it is possible to predict autonomous dynamic behaviour, as well as behaviour following hyperpolarizing or depolarizing inputs to neurons of the network. Conversely, given information about patterns of firing activity during cycles and transients of neural networks, the network connectivity can be predicted. The theoretical techniques can be used to generate a census of network structures capable of generating stable oscillations. Several representative network oscillators are discussed in the context of previous theoretical and experimental studies of the structure of neural network oscillators. Although the number of theoretically possile network oscillators capable of generating sustained oscillations is very large, the techniques which are given should be useful in the design of experiments capable of distinguishing between equally plausible hypotheses.

Action Potentials↗
PubMed2000

Higherorder neural network group models for financial simulation.

Real world financial data is often discontinuous and non-smooth. If we attempt to use neural networks to simulate such functions, then accuracy will be a problem. Neural network group models perform this function much better. Both Polynomial Higher Order Neural network Group (PHONG) and Trigonometric polynomial Higher Order Neural network Group (THONG) models are developed. These HONG models are open box, convergent models capable of approximating any kind of piecewise continuous function, to any degree of accuracy. Moreover they are capable of handling higher frequency, higher order non-linear and discontinuous data. Results obtained using a Higher Order Neural network Group financial simulator are presented, which confirm that HONG group models converge without difficulty, and are considerably more accurate than neural network models (more specifically, around twice as good for prediction, and a factor of four improvement in the case of simulation).

Computer Simulation↗
PubMed2006

Solving quadratic programming problems by delayed projection neural network.

In this letter, the delayed projection neural network for solving convex quadratic programming problems is proposed. The neural network is proved to be globally exponentially stable and can converge to an optimal solution of the optimization problem. Three examples show the effectiveness of the proposed network.

Algorithms↗
PubMed2001

Artificial neural networks for discriminating pathologic from normal peripheral vascular tissue.

The identification of the state of human peripheral vascular tissue by using artificial neural networks is discussed in this paper. Two different laser emission lines (He-Cd, Ar+) are used to excite the chromophores of tissue samples. The fluorescence spectrum obtained, is passed through a nonlinear filter based on a high-order (HO) neural network neural network (NN) [HONN] whose weights are updated by stable learning laws, to perform feature extraction. The values of the feature vector reveal information regarding the tissue state. Then a classical multilayer perceptron is employed to serve as a classifier of the feature vector, giving 100% successful results for the specific data set considered. Our method achieves not only the discrimination between normal and pathologic human tissue, but also the successful discrimination between the different types of pathologic tissue (fibrous, calcified). Furthermore, the small time needed to acquire and analyze the fluorescence spectra together with the high rates of success, proves our method very attractive for real-time applications.

Arteriosclerosis↗
PubMed1995

Recognition of Telugu characters using neural networks.

The aim of the present work is to recognize printed and handwritten Telugu characters using artificial neural networks (ANNs). Earlier work on recognition of Telugu characters has been done using conventional pattern recognition techniques. We make an initial attempt here of using neural networks for recognition with the aim of improving upon earlier methods which do not perform effectively in the presence of noise and distortion in the characters. The Hopfield model of neural network working as an associative memory is chosen for recognition purposes initially. Due to limitation in the capacity of the Hopfield neural network, we propose a new scheme named here as the Multiple Neural Network Associative Memory (MNNAM). The limitation in storage capacity has been overcome by combining multiple neural networks which work in parallel. It is also demonstrated that the Hopfield network is suitable for recognizing noisy printed characters as well as handwritten characters written by different "hands" in a variety of styles. Detailed experiments have been carried out using several learning strategies and results are reported. It is shown here that satisfactory recognition is possible using the proposed strategy. A detailed preprocessing scheme of the Telugu characters from digitized documents is also described.

Algorithms↗
PubMed1993

Neural Network Analysis of DNA flow cytometry histograms.

A pattern recognition system based on Neural Network Analysis, a form of artificial intelligence, was used to search DNA flow cytometry histograms for features that correlated with breast cancer patients' risk of relapse. DNA flow cytometry histograms and clinical follow-up information from 796 breast cancer patients were used to train a Neural Network to predict the clinical outcome of patients in a separate independent set of 794 patients. Median follow-up in this patient data base was short, 23 months. Neural Network Analysis resulted in a model that evaluated DNA flow cytometry histograms differently than conventional analysis, which categorizes the histograms by ploidy and S-phase fraction. Neural Network Analysis appeared to identify low risk and high risk subsets of patients as accurately as conventional analysis. Neural Network Analysis placed heavy emphasis on the region to the right of the diploid G2/M peak, where a subpopulation of nuclei with high DNA content is seen even in many histograms scored as diploid by conventional techniques. The number of nuclei in this region was found to be a powerful predictor of patient outcome, and multivariate analysis showed that the number of nuclei in this region and the S-phase fraction both were independently predictive of relapse. This pilot study suggests that conventional analysis (based on a mechanistic interpretation of regions in flow cytometry histograms) might be used in conjunction with and improved by pattern recognition systems or insights derived from them.

Breast Neoplasms↗
PubMed2000

Isolated directional preponderance of caloric nystagmus: II. A neural network model.

HYPOTHESIS: The purpose of this study was to simulate an isolated directional preponderance (DP) on bithermal caloric testing by constructing a realistic neural network model. The simulation was designed to capture not only the characteristics of the nystagmus response to caloric stimulation but also the response to rotational stimulation in patients with an isolated caloric DP. BACKGROUND: The nature of an isolated DP--that is, a DP in the absence of a significant spontaneous nystagmus or canal paresis--is outlined in the preceding article. In this article, the authors investigate the possible neural basis for an isolated caloric DP using the mathematic modeling technique of neural network simulation. Neural network models are typically abstract in nature; however, in this case the network was based on the known structure and function of the central vestibular system. METHODS: The neural network model was based on the known neuroanatomy and neurophysiology of the horizontal vestibuloocular reflex pathway. A leftward-rightward asymmetric modification of the dynamic responses of simulated medial vestibular nucleus type IA neurons on one side, or of type 2 neurons on the other side, to peripheral input would generate an isolated caloric DP. RESULTS: The values of DP and associated canal paresis produced by the network were within the same range as in the patient group. The network also predicted that the rotational DP would be lower than the caloric DP: between 2.5% and 56.9% of the caloric DP value. The actual rotational DP value was between 3% and 57% (average 41%) of the corresponding caloric DP value. CONCLUSIONS: An isolated caloric DP can be simulated by a neural network model by modifying the activity of model units that represent medial vestibular nucleus neurons. An asymmetric dynamic response by a gain-enhancement function of either type 1A neurons on one side or of type 2 neurons on the other was sufficient to produce an isolated caloric DP. Excitatory gain enhancement of type 2 neurons produced a smaller rotational DP than a similar modification of type 1 neurons. This result indicates a potential neural locus for the generation of an isolated DP in patients with vestibular disorders.

Caloric Tests↗
PubMed1997

Visualization of clinical data with neural networks, case study: polycystic ovary syndrome.

In medicine, the use of neural networks has concentrated mainly on classification problems. Clinicians are often interested in knowing what a patient's status is compared with other similar cases. Compared with biostatistics neural networks have one major drawback: the reliability of the classification is difficult to express. Therefore, clear visualization of the measurements can be more helpful than the calculated probability of a disease. The self-organizing map is the most widely used neural network for data visualization. Although, visualization can be attached to almost any feed-forward network as well. In this paper, we describe a topology-preserving feed-forward network and compare it with the self-organizing map. The two neural network models are used in a case study on the diagnosis of polycystic ovary syndrome, which is a common female endocrine disorder characterized by menstrual abnormalities, hirsutism and infertility.

Adolescent↗
PubMed2005

A recurrent neural network for solving nonlinear convex programs subject to linear constraints.

In this paper, we propose a recurrent neural network for solving nonlinear convex programming problems with linear constraints. The proposed neural network has a simpler structure and a lower complexity for implementation than the existing neural networks for solving such problems. It is shown here that the proposed neural network is stable in the sense of Lyapunov and globally convergent to an optimal solution within a finite time under the condition that the objective function is strictly convex. Compared with the existing convergence results, the present results do not require Lipschitz continuity condition on the objective function. Finally, examples are provided to show the applicability of the proposed neural network.

Neural Networks, Computer↗
PubMedDate not supplied

Inversion of simulated positron annihilation lifetime spectrum using a neural network.

Inversion of positron annihilation lifetime spectroscopy, based on a neural network Hopfield model, is presented in this paper. From a previous reported density function for lysozyme in water a simulated spectrum, without the superposition of statistical fluctuation and spectrometer resolution effects, was generated. These results were taken as the exact results from which the neural network was trained. The precision of the inverted density function was analyzed taking into account the number of neurons and the learning time of the neural network. A fair agreement was obtained when comparing the neural network results with the exact results. For example, the maximum of the density function, with a precision of 0.4% for the percentual relative error, was obtained for 64 neurons.

Journal Article↗
PubMed1998

Diagnostic classification of autoantibody repertoires in endocrine ophthalmopathy using an artificial neural network.

PURPOSE: The aim of this study was to classify the human IgG autoantibody repertoire of sera from patients suffering from endocrine ophthalmopathy (EOP) and healthy subjects (CTRL) for diagnostic purposes using the recently developed Megablot technique. This technique allows for the simultaneous and quantitative screening of a large set of antigens and uses multivariate statistical techniques and an artificial neural network. METHODS: Sera were tested against Western blots (WBs) of SDS-PAGE preparations of proteins from human extraorbital eye muscle (EOP: n = 16; CTRL: n = 11). Digital image analysis was performed. The blots were subsequently analyzed by multivariate statistical techniques (analysis of discriminance) and an artificial neural network (probalistic neural network). RESULTS: The sera of both the EOP and CTRL groups showed a complex staining pattern against WBs of SDS-PAGEs from human eye muscle. Using the multivariate statistical technique for classification, all of the known samples and 85% of the unknown samples (not presented during calculation) were assigned to their correct clinical group. Using the artificial neural network as classifier, all of the samples presented during training and 96.3% of the unknown samples (not trained) were assigned correctly. CONCLUSIONS: The artificial neural network exceeds the ability of multivariate statistical techniques such as analysis of discriminance to assign unknown samples to their correct predefined group. Thus, the neural network exceeds other methods in generalizing some similarities of blots used for classification. This study reveals that our new technique and its evaluation using a neural network can be used as a helpful diagnostic tool in autoimmune diseases such as endocrine ophthalmopathy.

Adult↗
PubMed1992

Neural networks for classification of ECG ST-T segments.

The usefulness of neural networks for pattern recognition in electrocardiographic (ECG) ST-T segments was assessed. Two thousand ST-T segments from the 12-lead ECG were visually classified singly into 7 different groups. The material was divided into a training set and a test set. Computer-measured ST-T data for each element in the training set, paired with the corresponding classification, was input to various configurations of software-based neural networks during a learning process. Thereafter, the networks correctly classified 90-95% of the individual ST-T segments in the test set. The importance of the size and composition of the training set in determining the performance of a network was clearly demonstrated. In conclusion, neural networks can be used for classification of ST-T segments. If carefully incorporated into a conventional ECG interpretation program, neural networks may well be of value for automated ECG interpretation in the near future.

Electrocardiography↗
PubMed1993

Self-organizing neural networks as a means of cluster analysis in clinical chemistry.

Connectionist systems (often termed "neural networks") are an alternative way to solve data processing tasks. They differ radically from conventional "von-Neumann" computing devices. Recent work on neural networks in clinical chemistry was done using supervised learning schemes, resulting in models which resemble classical discriminant analysis. The aim of the present study is to make clinical chemists familiar with basic concepts of self-organizing neural networks employing unsupervised learning schemes. Using a benchmark data set on the composition of milk from 22 different mammals, it is demonstrated that self-organizing neural networks are capable of performing tasks similar to classical cluster analysis and principal component analysis. Self-organizing neural networks could be envisaged to provide an alternative way for reducing the dimensionality of complex multivariate data sets, thus producing easily comprehensible low-dimensional "maps" of essential features.

Animals↗
PubMed1994

Modelling of human acute toxicity from physicochemical properties and non-vertebrate acute toxicity of the 38 organic chemicals of the MEIC priority list by PLS regression and neural network.

Linear and non-linear modelling of human acute toxicity (as human lethal concentrations; HLCs) of the 38 organic chemicals from the 50 priority compounds of the Multicentre Evaluation of In Vitro Cytotoxicity (MEIC) programme was investigated. The models obtained were derived either from a set of 23 physicochemical properties of the compounds or from their acute toxicities to five aquatic non-vertebrates together with the physicochemical properties. For the linear type, modelling was performed using a partial least square projection to latent structures (PLS) regression method; for the non-linear models, both PLS regression and neural network were utilized. A neural network using a combination of backpropagation and cascade-correlation algorithms was applied in this study. The results generally reveal a slightly better predictive performance of the models obtained from PLS regression than those obtained from neural networks. However, the model composed of physicochemical properties (PC-model) from the trained neural network using a back propagation algorithm with pruning technique proved superior to that trained with a combination of backpropagation and cascade-correlation algorithms after leave-one-out cross-validation. The predictive power of the PC-models, whether linear or non-linear, was comparable with that of the corresponding models consisting of both structural descriptors and the ecotoxicological tests (ECOPC-models), except for the battery (ECOPC-model) from the neural network. The composition of the 'best' PLS and neural network models points to the importance of the combination of physicochemical properties reflecting lipophilicity, size, volume, intermolecular binding forces and electronic properties of the molecule. All the aquatic non-vertebrate tests are shown to be essential in explaining human acute toxicity. However, the degree of contribution differed, with the crustacean (Artemia salina) and the bacterial (Microtox) bioassays being more important to the linear and non-linear PLS models, whereas the crustacean (Artemia salina and Streptocephalus proboscideus) tests, and the rotifer (Brachionus calyciflorus) assay were important to the neural network models. The organochlorine (lindane) and bipyridinium (paraquat) pesticides were common outliers in all the models. Moreover, the latter two compounds and the organophosphate (malathion) pesticide were also common outliers in all ECOPC-models. Other types of pesticides, however, fit the models. The predicted HLCs of a number of non-pesticides, including some chlorinated compounds, also deviated from the observed HLCs by more than one order of magnitude.

Algorithms↗
PubMed1992

Artificial neural networks in bioprocess state estimation.

The application of artificial neural networks to the estimation and prediction of bioprocess variables is presented in this paper. A neural network methodology is discussed, which uses environmental and physiological information available from on-line sensors, to estimate concentration of species in the bioreactor. Two case studies are presented, both based on the ethanol production by Zymomonas mobilis. An efficient optimization algorithm which reduces the number of iterations required for convergence is proposed. Results are presented for different training sets and different training methodologies. It is shown that the neural network estimator provides good on-line bioprocess state estimations.

Biomedical Engineering↗
PubMed2006

A convolutional neural network approach for objective video quality assessment.

This paper describes an application of neural networks in the field of objective measurement method designed to automatically assess the perceived quality of digital videos. This challenging issue aims to emulate human judgment and to replace very complex and time consuming subjective quality assessment. Several metrics have been proposed in literature to tackle this issue. They are based on a general framework that combines different stages, each of them addressing complex problems. The ambition of this paper is not to present a global perfect quality metric but rather to focus on an original way to use neural networks in such a framework in the context of reduced reference (RR) quality metric. Especially, we point out the interest of such a tool for combining features and pooling them in order to compute quality scores. The proposed approach solves some problems inherent to objective metrics that should predict subjective quality score obtained using the single stimulus continuous quality evaluation (SSCQE) method. This latter has been adopted by video quality expert group (VQEG) in its recently finalized reduced referenced and no reference (RRNR-TV) test plan. The originality of such approach compared to previous attempts to use neural networks for quality assessment, relies on the use of a convolutional neural network (CNN) that allows a continuous time scoring of the video. Objective features are extracted on a frame-by-frame basis on both the reference and the distorted sequences; they are derived from a perceptual-based representation and integrated along the temporal axis using a time-delay neural network (TDNN). Experiments conducted on different MPEG-2 videos, with bit rates ranging 2-6 Mb/s, show the effectiveness of the proposed approach to get a plausible model of temporal pooling from the human vision system (HVS) point of view. More specifically, a linear correlation criteria, between objective and subjective scoring, up to 0.92 has been obtained on a set of typical TV videos.

Algorithms↗