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 361 records · Page 20Linked to original sources
PubMedDate not supplied

Extension neural network and its applications.

In this paper, a novel extension neural network (ENN) is proposed. This new neural network is a combination of extension theory and neural network. It uses an extension distance (ED) to measure the similarity between data and cluster center. The learning speed of the proposed ENN is shown to be faster than the traditional neural networks and other fuzzy classification methods. Moreover, the new scheme has been proved to have high accuracy and less memory consumption. Experimental results from two different examples verify the effectiveness and applicability of the proposed work.

Neural Networks, Computer↗
PubMedDate not supplied

Electrical impedance cardiography using artificial neural networks.

This study evaluates the use of artificial neural networks to estimate stroke volume from pre-processed, thoracic impedance plethysmograph signals from 20 healthy subjects. Standard back-propagation was used to train the networks, with Doppler stroke volume estimates as the desired output. The trained networks were then compared to two classical biophysical approaches. The coefficient of determination (R2 x 100%) between the biophysical approaches and the Doppler was 8.20% and 9.90%, while it was 77.38% between the best neural network and the Doppler. Among these methods, only the neural network residuals had a significant zero mean Gaussian distribution (alpha=0.05). Our results indicate that an invertible relationship may exist between thoracic bioimpedance and stroke volume, and that artificial neural networks may offer a potentially advantageous approach for estimating stroke volume from thoracic electrical impedance, both because of their ease of use and their lack of confounding assumptions.

Adult↗
PubMed1992

On the performance of single-layered neural networks.

This paper studies the performance of single-layered neural networks. This study begins with the performance of single-layered neural networks trained using the outer-product rule. The outer-product rule is a suboptimal learning scheme, resulting under certain assumptions from optimal least-squares training of single-layered neural networks with respect to their analog output. Extensive analysis reveals the improvement on the network performance caused by its optimal least-squares training. The effect of the training scheme on the performance of single-layered neural networks with binary output is exhibited by experimentally comparing the performance of single-layered neural networks trained with respect to their analog and binary output.

Mathematics↗
PubMed1993

A unified framework for using neural networks to build QSARs.

We propose a new neural network architecture that explicitly separates linear and nonlinear contributions to the biological activity. To facilitate the use of neural networks as a regular tool we demonstrate that (1) a perceptron with linear output units is equivalent to multiple linear regression and (2) one hidden unit at a time can be added to the network so that QSAR data can be modeled by everything from the simplest linear hypersurfaces to complicated ones. The significant improvements accrued by the use of weight decay are demonstrated. We conclude that models built without attempting weight decay may not be reliable either for interpretation or extrapolation. Finally we compare models generated by neural networks, rank regression, and standard regression on non-normally distributed data and conclude that neural networks like rank regression bring out many facets of the data that are inaccessible to multiple linear regression. All the experiments were done on either triazine inhibition of pure DHFR from L1210 leukemia cells and on the inhibition of intact L1210 leukemia cells sensitive and resistant to methotrexate or on steroid binding to progesterone.

Animals↗
PubMed1998

Incorporation of Long-Range Feedback in Neural Networks Under Stability Conditions.

Feedback endows neural networks with several interesting properties. It is thus not surprising that several well-known models (e.g. ART, Hopfield, neocognitron) include feedback connections. However, neural networks with feedback may possess unstable dynamics and should be carefully designed. In this paper we show how to incorporate long-range feedback in a broad class of dynamically stable neural networks using the basic idea of symmetric connections. The case of networks with binary inputs and binary outputs is treated first. Then, as the main contribution of this paper, the analysis is extended to networks with analog (continuous-time continuous-output) neurons.

Journal Article↗
PubMed1991

Application of an artificial neural network in radiographic diagnosis.

The description of 44 cases of bone tumors was used by an artificial neural network to rank the likelihood of 55 possible pathologic diagnoses. The performance of the artificial neural network was compared with the performance of experienced (3 or more years of radiology training) residents and inexperienced (less than 1 year of radiology training) residents. The artificial neural network was trained using descriptions of 110 radiographs of bone tumors with known diagnoses. The descriptions of a separate set of 44 cases were used to test the neural network. The neural network ranked 55 possible pathologic diagnoses on a scale from 1 to 55. Experienced and inexperienced residents also ranked the possible diagnoses in the same 44 cases. Inexperienced residents had a significantly lower mean proportion of diagnoses ranked first or second than did the neural network. Experienced residents had a significantly higher proportion of correct diagnoses ranked first than did the network. Otherwise, a significant difference between the performance of the network and experienced or inexperienced residents was not identified. These results demonstrate that artificial neural networks can be trained to classify bone tumors. Whether neural network performance in classification of bone tumors can be made accurate enough to assist radiologists in clinical practice remains an open question. These preliminary results indicate that further investigation of this technology for interpretation assistance is warranted.

Bone Neoplasms↗
PubMed2005

Applications of Artificial Neural Networks in integrated water management: fiction or future?

An Artificial Neural Network (ANN) is nowadays recognized as a very promising tool for relating input data to output data. It is said that the possibilities of artificial neural networks are unlimited. Here we focus on the potential role of neural networks in integrated water management. An Artificial Neural Network (ANN) is a mathematical methodology which describes relations between cause (input data) and effects (output data) irrespective of the process laying behind and without the need for making assumptions considering the nature of the relations. The applications are widespread and vary from optimization of measuring networks, operational water management, prediction of drinking water consumption, on-line steering of wastewater treatment plants and sewage systems, up to more specific applications such as establishing a relationship between the observed erosion of groyne field sediments and the characteristics of passing vessels on the river Rhine. Especially where processes are complex, neural networks can open new possibilities for understanding and modelling these kinds of complex processes. Besides explaining the method of ANN this paper shows different applications. Three examples have been worked out in more detail. An intelligent monitoring system is shown for the on-line prediction of water consumption, ANN are successfully used for sludge cost monitoring and optimizing wastewater treatment and the usage of ANN is shown in optimizing and monitoring water quality measuring networks. An ANN appears to be a multiuse and powerful tool for modelling complex processes.

Conservation of Natural Resources↗
PubMed1996

Neural networks to identify glaucoma with structural and functional measurements.

PURPOSE: Neural networks can recognize patterns and classify complex variables. We assessed the ability of neural networks to discriminate between normal and glaucomatous eyes by using structural and functional measurements. METHODS: Several neural network algorithms were tested with a database of 185 eyes of patients with early glaucomatous visual field loss (average mean defect, 4.5 dB) and 54 eyes of age-matched normal control subjects. The information used included automated visual field indices (mean defect, corrected loss variance, and short-term fluctuation) and structural data (cup/disk ratio, rim area, cup volume, and nerve fiber layer height) from computerized image analysis. RESULTS: A back propagation network with two intermediate layers assigned an estimated probability of being glaucomatous to each eye and correctly identified 88% of all eyes with 90% sensitivity and 84% specificity. The same neural network trained with only structural data correctly identified 80% of the eyes with 87% sensitivity and 56% specificity, and when trained with functional data only, it correctly identified 84% of the eyes with 84% sensitivity and 86% specificity. CONCLUSION: Analysis of several optic nerve and visual field variables by neural networks can help identify early glaucomatous damage and assign an estimated probability that early damage is present in individual patients.

Algorithms↗
PubMedDate not supplied

Artificial neural networks for cancer research: outcome prediction.

The use of artificial neural networks in biological and medical research has increased tremendously in the last few years. Artificial neural networks are being used in cancer research for image processing, the analysis of laboratory data for breast cancer diagnosis, the discovery of chemotherapeutic agents, and for cancer outcome prediction. A neural network generalizes from the input data to patterns inherent in the data, and its uses these patterns to make predictions or to classify. This paper explains how neural networks work, and it shows that a neural network is more accurate at predicting breast cancer patient outcome than the current staging system.

Breast Neoplasms↗
PubMed1994

Classification of action potentials in multi-unit intrafascicular recordings using neural network pattern-recognition techniques.

Neural network pattern-recognition techniques were applied to the problem of identifying the sources of action potentials in multi-unit neural recordings made from intrafascicular electrodes implanted in cats. The network was a three-layer connectionist machine that used digitized action potentials as input. On average, the network was able to reliably separate 6 or 7 units per recording. As the number of units present in the recording increased beyond this limit, the number separable by the network remained roughly constant. The results demonstrate the utility of neural networks for classifying neural activity in multi-unit recordings.

Action Potentials↗
PubMed1993

Rapid identification of streptomycetes by artificial neural network analysis of pyrolysis mass spectra.

An artificial neural network was trained to distinguish between three putatively novel species of Streptomyces using normalised, scaled prolysis mass spectra from three representative strains of each of the taxa, each sampled in triplicate. Once trained, the artificial neural network was challenged with spectral data from the original organisms, the 'training set', from additional members of the putative novel taxa and from over a hundred strains representing six other actinomycete genera. All of the streptomycetes were correctly identified but many of the other actinomycetes were mis-identified. A modified network topology was developed to recognise the mass spectral patterns of the non-streptomycete strains. The resultant neural network correctly identified the streptomycetes, whereas all of the remaining actinomycetes were recognised as unknown organisms. The improved artificial neural network provides a rapid, reliable and cost-effective method of identifying members of the three target streptomycete taxa.

Actinomycetales↗
PubMed2003

Reliable prediction of T-cell epitopes using neural networks with novel sequence representations.

In this paper we describe an improved neural network method to predict T-cell class I epitopes. A novel input representation has been developed consisting of a combination of sparse encoding, Blosum encoding, and input derived from hidden Markov models. We demonstrate that the combination of several neural networks derived using different sequence-encoding schemes has a performance superior to neural networks derived using a single sequence-encoding scheme. The new method is shown to have a performance that is substantially higher than that of other methods. By use of mutual information calculations we show that peptides that bind to the HLA A*0204 complex display signal of higher order sequence correlations. Neural networks are ideally suited to integrate such higher order correlations when predicting the binding affinity. It is this feature combined with the use of several neural networks derived from different and novel sequence-encoding schemes and the ability of the neural network to be trained on data consisting of continuous binding affinities that gives the new method an improved performance. The difference in predictive performance between the neural network methods and that of the matrix-driven methods is found to be most significant for peptides that bind strongly to the HLA molecule, confirming that the signal of higher order sequence correlation is most strongly present in high-binding peptides. Finally, we use the method to predict T-cell epitopes for the genome of hepatitis C virus and discuss possible applications of the prediction method to guide the process of rational vaccine design.

Amino Acid Sequence↗
PubMed1994

Application of backpropagation neural networks to diagnosis of breast and ovarian cancer.

Neural network programs have been developed in an attempt to improve the diagnosis of breast and ovarian cancer using a group of laboratory tests and the age of the patient. The laboratory tests employed in this study include albumin, cholesterol, HDL-cholesterol, triglyceride, apolipoproteins A1 and B, NMR linewidth (the Fossel Index) and a tumor marker (i.e., CA 15-3 or CA 125). The breast cancer study involved 104 patients (45 malignant and 59 benign subjects). The ovarian cancer study involved 98 individuals (35 malignant, 36 benign and 27 control subjects). Methods are outlined for identification of the most influential input parameters and optimization of network structure and training. Network characteristics were contrasted with the test results of the appropriate serum tumor marker assay. For the breast cancer study, the best neural network program, using six input parameters, had a sensitivity of only 55.6% and a specificity of 72.9%. The tumor marker CA 15-3 alone gave results of 61.3% and 64.4%, respectively. For the ovarian cancer study, the best neural network program, using six input parameters, had a sensitivity of 80.6% and a specificity of 85.5%. The tumor marker CA 125 alone gave results of 77.8% and 82.3%, respectively. These methods provide an objective approach to neural network optimization and parameter selection applicable to other data bases of clinical and laboratory data.

Biomarkers, Tumor↗
PubMed1999

Hidden neural networks.

A general framework for hybrids of hidden Markov models (HMMs) and neural networks (NNs) called hidden neural networks (HNNs) is described. The article begins by reviewing standard HMMs and estimation by conditional maximum likelihood, which is used by the HNN. In the HNN, the usual HMM probability parameters are replaced by the outputs of state-specific neural networks. As opposed to many other hybrids, the HNN is normalized globally and therefore has a valid probabilistic interpretation. All parameters in the HNN are estimated simultaneously according to the discriminative conditional maximum likelihood criterion. The HNN can be viewed as an undirected probabilistic independence network (a graphical model), where the neural networks provide a compact representation of the clique functions. An evaluation of the HNN on the task of recognizing broad phoneme classes in the TIMIT database shows clear performance gains compared to standard HMMs tested on the same task.

Databases as Topic↗
PubMed1993

A genetic algorithm to improve a neural network to predict a patient's response to warfarin.

The ability of neural networks to predict the international normalised ratio (INR) for patients treated with Warfarin was investigated. Neural networks were obtained by using all the predictor variables in the neural network, or by using a genetic algorithm to select an optimal subset of predictor variables in a neural network. The use of a genetic algorithm gave a marked and significant improvement in the prediction of the INR in two of the three cases investigated. The mean error in these cases, typically, reduced from 1.02 +/- 0.29 to 0.28 +/- 0.25 (paired t-test, t = -4.71, p < 0.001, n = 30). The use of a genetic algorithm with Warfarin data offers a significant enhancement of the predictive ability of a neural network with Warfarin data, identifies significant predictor variables, reduces the size of the neural network and thus the speed at which the reduced network can be trained, and reduces the sensitivity of a network to over-training.

Algorithms↗
PubMed2001

A study on rule extraction from several combined neural networks.

The problem of rule extraction from neural networks is NP-hard. This work presents a new technique to extract "if-then-else" rules from ensembles of DIMLP neural networks. Rules are extracted in polynomial time with respect to the dimensionality of the problem, the number of examples, and the size of the resulting network. Further, the degree of matching between extracted rules and neural network responses is 100%. Ensembles of DIMLP networks were trained on four data sets in the public domain. Extracted rules were on average significantly more accurate than those extracted from C4.5 decision trees.

Neural Networks, Computer↗
PubMedDate not supplied

Neural networks in clinical medicine.

Neural networks are parallel, distributed, adaptive information-processing systems that develop their functionality in response to exposure to information. This paper is a tutorial for researchers intending to use neural nets for medical decision-making applications. It includes detailed discussion of the issues particularly relevant to medical data as well as wider issues relevant to any neural net application. The article is restricted to back-propagation learning in multilayer perceptrons, as this is the neural net model most widely used in medical applications.

Algorithms↗
PubMed2002

Hybrid neural network modeling of a full-scale industrial wastewater treatment process.

In recent years, hybrid neural network approaches, which combine mechanistic and neural network models, have received considerable attention. These approaches are potentially very efficient for obtaining more accurate predictions of process dynamics by combining mechanistic and neural network models in such a way that the neural network model properly accounts for unknown and nonlinear parts of the mechanistic model. In this work, a full-scale coke-plant wastewater treatment process was chosen as a model system. Initially, a process data analysis was performed on the actual operational data by using principal component analysis. Next, a simplified mechanistic model and a neural network model were developed based on the specific process knowledge and the operational data of the coke-plant wastewater treatment process, respectively. Finally, the neural network was incorporated into the mechanistic model in both parallel and serial configurations. Simulation results showed that the parallel hybrid modeling approach achieved much more accurate predictions with good extrapolation properties as compared with the other modeling approaches even in the case of process upset caused by, for example, shock loading of toxic compounds. These results indicate that the parallel hybrid neural modeling approach is a useful tool for accurate and cost-effective modeling of biochemical processes, in the absence of other reasonably accurate process models.

Biodegradation, Environmental↗