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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 433 records · Page 24Linked to original sources

PubMed1998

The extended piecewise quadratic neural network.

We present a new neural network for detection and classification problems that is capable of creating spherical, elliptical, hyperbolic and linear decision surfaces. This new classifier is called the extended piecewise quadratic neural network (E-PQNN) and uses complex-valued weights and a square-law non-linearity. We prove that our simple E-PQNN architecture is able to generate piecewise quadratic decision surfaces of arbitrary rank and we develop new methods for selecting the number of hidden-layer neurons in the E-PQNN. The weights are optimized using a modified perceptron error criterion and a conjugate gradient optimizer. We present results obtained for a synthetic problem.

Journal Article↗

PubMed1996

Comparison of shoe insole materials by neural network analysis.

The effects of two insole materials within the shoe are compared using neural network analysis. Seven male subjects without locomotor disorders walk on a treadmill at a controlled speed and cadence wearing a common shoe and no socks, under three conditions; these are two types of insole of the same thickness, and a no insole condition. Pressure-related data from under the foot, within the shoe, are obtained by the MICRO-EMED system during walking. A back-propagation neural network is trained to associate sets of pressure-related data with the insole conditions. Subsequently neural network analysis is performed to reveal the abstract rules that govern the decision-making processes within the neural network, based on the synergistic interactions between the measured variables. Data are also analysed using ANOVA. The neural network analysis finds trends in the way in which the trained neural network responds. The interpretation of those trends gives a delicate description of the dynamic behaviour of the insoles despite the fact that no significant differences are found using ANOVA. It is concluded that neural network analysis can distinguish between insole behaviour during use, even though these differences are not significantly different based on statistical tests.

Adult↗

PubMed2002

A new approach to stability of neural networks with time-varying delays.

The stability of neural networks is a prerequisite for successful applications of the networks as either associative memories or optimization solvers. Because the integration and communication delays are ubiquitous, the stability of neural networks with delays has received extensive attention. However, the approach used in the previous investigation is mainly based on Liapunov's direct method. Since the construction of Liapunov function is very skilful, there is little compatibility among the existing results. In this paper, we develop a new approach to stability analysis of Hopfield-type neural networks with time-varying delays by defining two novel quantities of nonlinear function similar to the matrix norm and the matrix measure, respectively. With the new approach, we present sufficient conditions of the stability, which are either the generalization of those existing or new. The developed approach may be also applied for any general system with time delays rather than Hopfield-type neural networks.

Neural Networks, Computer↗

PubMed2004

A comparative study of two modeling approaches in neural networks.

The neuron state modeling and the local field modeling provides two fundamental modeling approaches to neural network research, based on which a neural network system can be called either as a static neural network model or as a local field neural network model. These two models are theoretically compared in terms of their trajectory transformation property, equilibrium correspondence property, nontrivial attractive manifold property, global convergence as well as stability in many different senses. The comparison reveals an important stability invariance property of the two models in the sense that the stability (in any sense) of the static model is equivalent to that of a subsystem deduced from the local field model when restricted to a specific manifold. Such stability invariance property lays a sound theoretical foundation of validity of a useful, cross-fertilization type stability analysis methodology for various neural network models.

Algorithms↗

PubMedDate not supplied

Neural networks convergence using physicochemical data.

An investigation of the neural network convergence and prediction based on three optimization algorithms, namely, Levenberg-Marquardt, conjugate gradient, and delta rule, is described. Several simulated neural networks built using the above three algorithms indicated that the Levenberg-Marquardt optimizer implemented as a back-propagation neural network converged faster than the other two algorithms and provides in most of the cases better prediction. These conclusions are based on eight physicochemical data sets, each with a significant number of compounds comparable to that usually used in the QSAR/QSPR modeling. The superiority of the Levenberg-Marquardt algorithm is revealed in terms of functional dependence of the change of the neural network weights with respect to the gradient of the error propagation as well as distribution of the weight values. The prediction of the models is assessed by the error of the validation sets not used in the training process.

ATP Binding Cassette Transporter, Subfamily B, Mem↗

PubMed2001

ECG beat recognition using fuzzy hybrid neural network.

This paper presents the application of the fuzzy neural network for electrocardiographic (ECG) beat recognition and classification. The new classification algorithm of the ECG beats, applying the fuzzy hybrid neural network and the features drawn from the higher order statistics has been proposed in the paper. The cumulants of the second, third, and fourth orders have been used for the feature selection. The hybrid fuzzy neural network applied in the solution consists of the fuzzy self-organizing subnetwork connected in cascade with the multilayer perceptron, working as the final classifier. The c-means and Gustafson-Kessel algorithms for the self-organization of the neural network have been applied. The results of experiments of recognition of different types of beats on the basis of the ECG waveforms have confirmed good efficiency of the proposed solution. The investigations show that the method may find practical application in the recognition and classification of different type heart beats.

Algorithms↗

PubMedDate not supplied

Robustness of a neural network model for differencing.

A neural network, originally proposed as a model for nuclei in the auditory brainstem, uses gradients of cell thresholds to reliably compute the difference of inputs over wide input ranges. The encoding of difference is linear even though the individual components of the network are finite, saturating, nonlinear devices highly dependent on input level. Theorems are proven that explain the linear dependence of network output on difference and that show the robustness of the network to perturbations of the threshold gradients. There is some evidence that the network exists in the neural tissue of the auditory brainstem.

Action Potentials↗

PubMed1996

Evaluation and scoring of radiotherapy treatment plans using an artificial neural network.

PURPOSE: The objective of this work was to demonstrate the feasibility of using an artificial neural network to predict the clinical evaluation of radiotherapy treatment plans. METHODS AND MATERIALS: Approximately 150 treatment plans were developed for 16 patients who received external-beam radiotherapy for soft-tissue sarcomas of the lower extremity. Plans were assigned a figure of merit by a radiation oncologist using a five-point rating scale. Plan scoring was performed by a single physician to ensure consistency in rating. Dose-volume information extracted from a training set of 511 treatment plans on 14 patients was correlated to the physician-generated figure of merit using an artificial neural network. The neural network was tested with a test set of 19 treatment plans on two patients whose plans were not used in the training of the neural net. RESULTS: Physician scoring of treatment plans was consistent to within one point on the rating scale 88% of the time. The neural net reproduced the physician scores in the training set to within one point approximately 90% of the time. It reproduced the physician scores in the test set to within one point approximately 83% of the time. CONCLUSIONS: An artificial neural network can be trained to generate a score for a treatment plan that can be correlated to a clinically-based figure of merit. The accuracy of the neural net in scoring plans compares well with the reproducibility of the clinical scoring. The system of radiotherapy treatment plan evaluation using an artificial neural network demonstrates promise as a method for generating a clinically relevant figure of merit.

Feasibility Studies↗

PubMed1992

Quantitative analysis of protein far UV circular dichroism spectra by neural networks.

A new method based on neural network theory is presented to analyze and quantify the information content of far UV circular dichroism spectra. Using a backpropagation network model with a single hidden layer between input and output, it was possible to deduce five different secondary structure fractions (helix, parallel and antiparallel beta-sheet, beta-turn and random coil) with satisfactory correlations between calculated and measured secondary structure data. We demonstrate that for each wavelength interval a specific network is suitable. The remaining discrepancy between the secondary structure data from neural network prediction and crystallography may be attributed to errors in the determination of protein concentration and random noise in the CD signal, as indicated by simulations.

Circular Dichroism↗

PubMed2000

A comparison between two neural network rule extraction techniques for the diagnosis of hepatobiliary disorders.

Neural networks have been widely used as tools for prediction in medicine. We expect to see even more applications of neural networks for medical diagnosis as recently developed neural network rule extraction algorithms make it possible for the decision process of a trained network to be expressed as classification rules. These rules are more comprehensible to a human user than the classification process of the networks which involves complex nonlinear mapping of the input data. This paper reports the results from two neural network rule extraction techniques, NeuroLinear and NeuroRule applied to the diagnosis of hepatobiliary disorders. The dataset consists of nine measurements collected from patients in a Japanese hospital and these measurements have continuous values. NeuroLinear generates piece-wise linear discriminant functions for this dataset. The continuous measurements have previously been discretized by domain experts. NeuroRule is applied to the discretized dataset to generate symbolic classification rules. We compare the rules generated by the two techniques and find that the rules generated by NeuroLinear from the original continuously valued dataset to be slightly more accurate and more concise than the rules generated by NeuroRule from the discretized dataset.

Algorithms↗

PubMed1996

A restoration algorithm for P-32 and Y-90 bremsstrahlung emission nuclear imaging: a wavelet-neural network approach.

A novel wavelet-based neural network (WNN) filter is proposed for image restoration as required for imaging of beta emitters by bremsstrahlung detection using a gamma camera. Quantitative imaging of beta emitters is important for the in vivo management of antibody therapy using either P-32 or Y-90. The theoretical basis for the general case for M-channel multiresolution wavelet decomposition of the nuclear image into different subimages is developed with the objective of isolating the signal from noise. A modified Hopfield neural network (NN) architecture is then used for multichannel image restoration using the dominant signal subimages. The NN model avoids the common inverse problem associated with other image restoration filters such as the Wiener filter. The relative performance of the WNN for image restoration, for M = 2 channel, is compared to a previously reported order statistic neural network hybrid (OSNNH) filter. Initially simulated degraded images of known structures with different noise levels are used. Quantitative metrics such as the normalized mean square error (NMSE) and signal-to-noise ratio (SNR) are used to compare filter performance. The WNN yields comparable results for image restoration with suggested slightly better performance for the images with higher noise levels as often encountered in bremsstrahlung detection. Attenuation measurements were performed using two radionuclides, 32P and 90Y as required for calibration of the gamma camera for quantitative measurements. Similar values for an effective attenuation coefficient were observed for the restored images using the OSNNH filters (32P: mu = 0.122 cm-1, 90Y: mu = 0.135 cm-1) and WNN (32P: mu = 0.122 cm-1, 90Y: mu = 0.135 cm-1) filters with slightly higher values obtained for the raw data (32P: mu = 0.142 cm-1, 90Y: mu = 0.142 cm-1) for a 3.5-cm source size. The WNN, however, was computationally more efficient by a factor of 4 to 6 compared to the OSNNH filter. The filter architecture, in turn, is also optimum for parallel processing or VLSI implementation as required for planar and particularly for SPECT mode of detection.

Algorithms↗

PubMed2002

A multiple circular path convolution neural network system for detection of mammographic masses.

A multiple circular path convolution neural network (MCPCNN) architecture specifically designed for the analysis of tumor and tumor-like structures has been constructed. We first divided each suspected tumor area into sectors and computed the defined mass features for each sector independently. These sector features were used on the input layer and were coordinated by convolution kernels of different sizes that propagated signals to the second layer in the neural network system. The convolution kernels were trained, as required, by presenting the training cases to the neural network. In this study, randomly selected mammograms were processed by a dual morphological enhancement technique. Radiodense areas were isolated and were delineated using a region growing algorithm. The boundary of each region of interest was then divided into 36 sectors using 36 equi-angular dividers radiated from the center of the region. A total of 144 Breast Imaging-Reporting and Data System-based features (i.e., four features per sector for 36 sectors) were computed as input values for the evaluation of this newly invented neural network system. The overall performance was 0.78-0.80 for the areas (Az) under the receiver operating characteristic curves using the conventional feed-forward neural network in the detection of mammographic masses. The performance was markedly improved with Az values ranging from 0.84 to 0.89 using the MCPCNN. This paper does not intend to claim the best mass detection system. Instead it reports a potentially better neural network structure for analyzing a set of the mass features defined by an investigator.

Breast Neoplasms↗

PubMed1994

Application of neural networks to the classification of giant cell arteritis.

OBJECTIVE: Neural networks are a group of computer-based pattern recognition methods that have recently been applied to clinical diagnosis and classification. In this study, we applied one type of neural network, the backpropagation network, to the diagnostic classification of giant cell arteritis (GCA). METHODS: The analysis was performed on the 807 cases in the vasculitis database of the American College of Rheumatology. Classification was based on the 8 clinical criteria previously used for classification of this data set: 1) age > or = 50 years, 2) new localized headache, 3) temporal artery tenderness or decrease in temporal artery pulse, 4) polymyalgia rheumatica, 5) abnormal result on artery biopsy, 6) erythrocyte sedimentation rate > or = 50 mm/hour, 7) scalp tenderness or nodules, and 8) claudication of the jaw, of the tongue, or on swallowing. To avoid overtraining, network training was terminated when the generalization error reached a minimum. True cross-validation classification rates were obtained. RESULTS: Neural networks correctly classified 94.4% of the GCA cases (n = 214) and 91.9% of the other vasculitis cases (n = 593). In comparison, classification trees correctly classified 91.6% of the GCA cases and 93.4% of the other vasculitis cases. Neural nets and classification trees were compared by receiver operating characteristic (ROC) analysis. The ROC curves for the two methods crossed, indicating that the better classification method depended on the choice of decision threshold. At a decision threshold that gave equal costs to percentage increases in false-positive and false-negative results, the methods were not significantly different in their performance (P = 0.45). CONCLUSION: Neural networks are a potentially useful method for developing diagnostic classification rules from clinical data.

Diagnosis, Computer-Assisted↗

PubMed2002

Characterization and prediction of linker sequences of multi-domain proteins by a neural network.

In this paper, we describe a neural network analysis of sequences connecting two protein domains (domain linkers). The neural network was trained to distinguish between domain linker sequences and non-linker sequences, using a SCOP-defined domain library. The analysis indicated that a significant difference existed between domain linkers and non-linker regions, including intra-domain loop regions. Moreover, the resulting Hinton diagram showed a position-dependent amino acid preference of the domain linker sequences, and implied their non-random nature. We then applied the neural network to predict domain linkers in multi-domain protein sequences. As the result of a Jack-knife test, 58% of the predicted regions matched actual linker regions (specificity), and 36% of the SCOP-derived domain linkers were predicted (sensitivity). This prediction efficiency is superior to simpler methods derived from secondary structure prediction that assume that long loop regions are putative domain linkers. Altogether, these results suggest that domain linkers possess local characteristics different from those of loop regions.

Amino Acid Sequence↗

PubMed1999

novel Award Third Prize Paper. Assessment of the horizontal,fore-aft component of the ground reaction force from insole pressure patterns by using artificial neural networks.

OBJECTIVE: In this study it was investigated whether an artificial neural network can be used to determine the horizontal, fore-aft component of the ground reaction force from insole pressure patterns. DESIGN: An artificial neural network was applied to map insole pressures and ground reaction forces. METHOD: To train an artificial neural network insole pressure patterns and ground reaction force data were simultaneously determined for a wide range of different speeds (0.9-2.3 m s(-1)) for five subjects. Both intrasubject and intersubject generalizability were evaluated. RESULTS: At the intrasubject level generalizability was good when the speed for which the force was to be predicted was within the range of speeds from which data were used to train the network. Besides in some cases, generalizability to a condition outside the range of training conditions could be demonstrated. At the intersubject level the quality of generalization differed widely over subjects, from poor to good. CONCLUSIONS: It was found that an artificial neural network is able to map the relationship between insole pressure patterns and the fore-aft component of the ground reaction force. RELEVANCE: Good intrasubject generalization of 'knowledge' obtained by an artificial neural network will allow the assessment of the fore-aft component of ground reaction force in condition that cannot be evaluated with force plates, e.g. activities of daily living or real sport situations. Additionally, intersubject generalization will allow shear-force recordings in subjects that are not able to complete a great number of runs to acquire enough force-plate hits.

Biomechanical Phenomena↗

PubMed2002

Prediction of ambient PM10 and toxic metals using artificial neural networks.

In this study, an artificial neural network is employed to predict the concentration of ambient respirable particulate matter (PM10) and toxic metals observed in the city of Jaipur, India. A feed-forward network with a back-propagation learning algorithm is used to train the neural network the behavior of the data patterns. The meteorological variables of wind speed, wind direction, relative humidity, temperature, and time are taken as input to the network. The results indicate that the network is able to predict concentrations of PM10 and toxic metals quite accurately.

Air Pollutants↗

PubMed1996

Dynamics of a Winner-Take-All Neural Network.

This paper describes a neural network with lateral inhibition, which exhibits dynamic winner-take-all (WTA) behavior. The equations of this network model a current input MOSFET WTA circuit, which motivates the discussion. A very general sufficient condition for the network to have a WTA equilibrium point is obtained and sufficient conditions for the network to converge to the WTA point are presented. This gives explicit expressions for the resolution and lower bound of the input currents. We also show that whenever the network gets into the WTA region, it will stay in that region and settle down exponentially fast to the WTA point. This provides a speed up procedure for the decision making: as soon as it gets into the region, the winner can be picked up. Finally, we show that this WTA neural network has a self-resetting property. Copyright 1996 Elsevier Science Ltd

Journal Article↗

PubMed1993

A neural network to analyze fertility data.

OBJECTIVE: To program an artificial intelligence system, a neural network, and use it to predict results of sperm penetration in bovine cervical mucus (Penetrak assay; Serono Laboratories, Norwell, MA) and zona-free hamster egg penetration from the semen analysis. DESIGN: Results of 139 Penetrak assays, 1,416 zona-free hamster egg penetration assays, and the corresponding semen analyses were retrospectively analyzed by an artificial neural network. MAIN OUTCOME MEASURES: Classification errors of the neural network were compared with those of linear and quadratic discriminant function analyses. RESULTS: Data were separated into training and test sets. For the Penetrak result, linear and quadratic discriminant function analysis correctly predicted 58% and 74% of the training set results and only 64.1% and 69.2% of the test data, respectively. The neural network correctly predicted 92% of training set results and 80% of test set results. For the zona-free hamster egg penetration assay outcome, linear and quadratic discriminant function analysis correctly classified 66.3% and 46.0% of the training set and 64.9% and 44.7% of the test set, respectively. The neural network correctly classified 75.7% of the training data and 67.8% of the test data. CONCLUSIONS: Using the semen analysis, the neural network correctly classified 67.8% of zona-free hamster egg penetration assay results and 80% of Penetrak results it had not encountered previously, suggesting that this method of data analysis may be successfully employed to predict fertility potential.

Animals↗