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 163 records · Page 9Linked to original sources
PubMed2001

Prediction of protein functional domains from sequences using artificial neural networks.

An artificial neural network (ANN) solution is described for the recognition of domains in protein sequences. A query sequence is first compared to a reference database of domain sequences by use of and the output data, encoded in the form of six parameters, are forwarded to feed-forward artificial neural networks with six input and six hidden units with sigmoidal transfer function. The recognition is based on the distribution of scores precomputed for the known domain groups in a database versus database comparison. Applications to the prediction of function are discussed.

Computational Biology↗
PubMed2006

[The results of quantitative cytological analysis of the structure of follicular thyroid tumors using computer and neural network technologies].

Artificial neural network is a complex system capable of gathering and synthesizing data and capable of learning using particular given parameters. This technology was applied to studying cytological diagnostics of thyroid diseases to differentiate between follicular cancer and follicular adenoma. A complex of quantitative cytological characteristics was used to describe cytological preparations by examples of known cytological diagnosis to train the neural network. Among offered cytological examples, 96% were recognized correctly during testing.

Adenocarcinoma, Follicular↗
PubMed1994

Data qualification: logic analysis applied toward neural network training.

For neural networks to develop good internal representations for pattern mapping, noise in the training set data must be controlled. Because of the many difficulties associated with manually validating training data, we have focused on using decision table techniques as a practical, domain-independent means of optimizing training set formulation. Decision tables provide a variety of mechanisms whereby training set data can be processed to remove ambiguity, contradictions, and other noise. In addition to serving as data filters, decision tables can be used in the evaluation of neural network training.

Algorithms↗
PubMed2006

Comparison of Gompertz and neural network models of broiler growth.

Neural networks offer an alternative to regression analysis for biological growth modeling. Very little research has been conducted to model animal growth using artificial neural networks. Twenty-five male chicks (Ross x Ross 308) were raised in an environmental chamber. Body weights were determined daily and feed and water were provided ad libitum. The birds were fed a starter diet (23% CP and 3,200 kcal of ME/kg) from 0 to 21 d, and a grower diet (20% CP and 3,200 kcal of ME/ kg) from 22 to 70 d. Dead and female birds were not included in the study. Average BW of 18 birds were used as the data points for the growth curve to be modeled. Training data consisted of alternate-day weights starting with the first day. Validation data consisted of BW at all other age periods. Comparison was made between the modeling by the Gompertz nonlinear regression equation and neural network modeling. Neural network models were developed with the Neuroshell Predictor. Accuracy of the models was determined by mean square error (MSE), mean absolute deviation (MAD), mean absolute percentage error (MAPE), and bias. The Gompertz equation was fit for the data. Forecasting error measurements were based on the difference between the model and the observed values. For the training data, the lowest MSE, MAD, MAPE, and bias were noted for the neural-developed neural network. For the validation data, the lowest MSE and MAD were noted with the genetic algorithm-developed neural network. Lowest bias was for the neural-developed network. As measured by bias, the Gompertz equation underestimated the values whereas the neural- and genetic-developed neural networks produced little or no overestimation of the observed BW responses. Past studies have attempted to interpret the biological significance of the estimates of the parameters of an equation. However, it may be more practical to ignore the relevance of parameter estimates and focus on the ability to predict responses.

Animals↗
PubMed2004

Recognition of patients with cardiovascular disease by artificial neural networks.

BACKGROUND: Artificial neural networks (ANNs) are computer algorithms inspired by the highly interactive processing of the human brain. When exposed to complex data sets, ANNs can learn the mechanisms that correlate different variables and perform complex classification tasks. AIMS: A database, of 949 patients and 54 variables, was analysed to evaluate the capacity of ANNs to recognise patients with (VE+, n = 196) or without (VE-, n = 753) a history of vascular events on the basis of vascular risk factors (VRFs), carotid ultrasound variables (UVs) or both. METHOD: The performance of ANN was assessed by calculating the percentage of correct identifications of VE+ and VE- patients (sensitivity and specificity, respectively) and the prediction accuracy (weighted mean between sensitivity and specificity). RESULTS: The results showed that ANNs can be trained to identify VE+ and VE- subjects more accurately than discriminant analyses. When VRFs and UVs were used as input variables, the prediction accuracies of the ANN providing the best results were 80.8% and 79.2%, respectively. The addition of gender, age, weight, height and body mass index to UVs increased accuracy of prediction to 83.0%. When the ANNs were allowed to choose the relevant input data automatically (I.S. system-Semeion), 37 variables were selected among 54, five of which were UVs. Using this set of variables as input data, the performance of the ANNs in the classification task reached a prediction accuracy of 85.0%. with the 92.0% correct classification of VE+ patients. CONCLUSIONS: Artificial neural network technology is highly promising in the development of accurate diagnostic tools designed to recognize patients at high risk of cardiovascular diseases.

Adult↗
PubMed2006

Solving pseudomonotone variational inequalities and pseudoconvex optimization problems using the projection neural network.

In recent years, a recurrent neural network called projection neural network was proposed for solving monotone variational inequalities and related convex optimization problems. In this paper, we show that the projection neural network can also be used to solve pseudomonotone variational inequalities and related pseudoconvex optimization problems. Under various pseudomonotonicity conditions and other conditions, the projection neural network is proved to be stable in the sense of Lyapunov and globally convergent, globally asymptotically stable, and globally exponentially stable. Since monotonicity is a special case of pseudomononicity, the projection neural network can be applied to solve a broader class of constrained optimization problems related to variational inequalities. Moreover, a new concept, called componentwise pseudomononicity, different from pseudomononicity in general, is introduced. Under this new concept, two stability results of the projection neural network for solving variational inequalities are also obtained. Finally, numerical examples show the effectiveness and performance of the projection neural network.

Algorithms↗
PubMed1992

Neural networks in forensic science.

Neural networks were developed to study and mimic the functioning of the human brain. Humans are good at pattern recognition; the question is how good neural networks are at it, particularly with problems of forensic science interest. Simulation experiments with a type of neural network known as a Hopfield net indicate that it may have value for the storage of toolmark patterns (including bullet striation patterns) and for the subsequent retrieval of the matching pattern using another mark by the same tool for input. Another type of neural network, the back-propagation network (BPN), is useful for applications similar to those for which standard statistical methods of pattern classification can be used. This would be an appropriate approach to the matching of general component patterns, such as gas chromatograms of gasoline, or pyrolysis patterns from materials of forensic science interest, such as paint. The BPN may provide better results than statistical methods, but it is currently necessary to try both to determine which would be best for any given situation.

Forensic Medicine↗
PubMed1996

POPFNN: A Pseudo Outer-product Based Fuzzy Neural Network.

A novel fuzzy neural network, called the pseudo outer-product based fuzzy neural network (POPFNN), is proposed in this paper. The functions performed by each layer in the proposed POPFNN strictly correspond to the inference steps in the truth value restriction method in fuzzy logic [[Mantaras (1990)] Approximate reasoning models, Ellis Horwood]. This correspondence gives it a strong theoretical basis. Similar to most of the existing fuzzy neural networks, the proposed POPFNN uses a self-organizing algorithm ([Kohonen, 1988], Self-organization and associative memories, Springer) to learn and initialize the membership functions of the input and output variables from a set of training data. However, instead of employing the popularly used competitive learning [[Kosko (1990)] IEEE Trans. Neural Networks, 3(5), 801], this paper proposes a novel pseudo outer-product (POP) learning algorithm to identify the fuzzy rules that are supported by the training data. The proposed POP learning algorithm is fast, reliable, and highly intuitive. Extensive experimental results and comparisons are presented at the end of the paper for discussion. Copyright 1996 Elsevier Science Ltd.

Journal Article↗
PubMed1992

Data processing for multi-channel optical recording: action potential detection by neural network.

Using a neural network, we have developed a program for fast and precise detection of action potentials (AP) in raw multi-channel optical recording data. The AP detection was performed in two steps: first, peaks were detected in raw optical data, and, second, the peaks were classified by the neural network into APs, noise and undecided peaks. The network was optimized and trained by the backpropagation learning algorithm, employing some thousands of manually classified peaks. The performance of the optimized network was found to be not completely satisfactory, although it was better than the classification by template matching and nearest-neighbor rules. The addition of a signal-to-noise ratio (SNR) of a peak to the network classification improved the classification performance: in comparison with the manual classification results, 96% of manually classified APs were detected. The causes of classification errors were discussed. In spite of the fact that the program required a slight amount of human intervention for undecided peaks, the program could allow mostly automatic AP detection.

Action Potentials↗
PubMed1996

Confidence intervals for calibration with neural networks.

Based on neural network calibration the confidence intervals of aromaticity determination from infrared reflectance spectra of raw brown coals were estimated by means of the bootstrap method, a simplified Monte Carlo Simulation. The standard deviations and the confidence intervals were estimated to characterise the analysis error.It is shown that confidence intervals of non-linear analysis methods like Back Propagation Neural Networks (BPNN) can be estimated by the bootstrap method. The estimated confidence intervals of the calibration confirm the analysis by BPNN.

Journal Article↗
PubMed2006

[Simultaneous quantitative analysis of three kinds of phenols by Elman recurrent neural network].

Elman recurrent neural network ( ERNN) was applied to study the simultaneous quantitative analysis of seriously overlapped spectra of a p-nitrophenol, o-nitrophenol and 2,4-dinitrophenol system. The multivariate linear regression (MLR) method was also applied in this study for comparison. Two programs (PERNN and PMLR) were designed to perform the calculations. By optimization, the structure and parameters of Elman recurrent neural network were defined. The relative standard errors of prediction (RSEP) for all components with ERNN and MLR were 3.1% and 2 027.3%, respectively. Experimental results showed the method to be successful even where there was a severe overlap of spectra. The ERNN method is a valuable tool in solving the minimum problem and improving the convergence rate, and can be used to analyze the whole spectra rather than just picking out a few characteristic values. The method provides a new way of simultaneous determination of severely overlapped molecular spectra without prior separation.

English Abstract↗
PubMedDate not supplied

Optimization and empirical modeling of HG-ICP-AES analytical technique through artificial neural networks.

An artificial neural network technique has been applied to the optimization of a hydride generation-inductively coupled plasma-atomic emission spectrometry (HG-ICP-AES) coupling for the determination of Ge at trace levels. The back propagation of errors net architecture was used. Experimental parameters and their relationship have been studied, obtaining a surface response of the system. The results and optimization aspects achieved with the neural network approach have been compared to the "one variable at time" and SIMPLEX methods.

Journal Article↗
PubMed1997

Toward implementation of artificial neural networks that "really work".

Artificial neural networks are established analytical methods in bio-medical research. They have repeatedly outperformed traditional tools for pattern recognition and clinical outcome prediction while assuring continued adaptation and learning. However, successful experimental neural networks systems seldom reach a production state. That is, they are not incorporated into clinical information systems. It could be speculated that neural networks simply must undergo a lengthy acceptance process before they become part of the day to day operations of health care systems. However, our experience trying to incorporate experimental neural networks into information systems lead us to believe that there are technical and operational barriers that greatly difficult neural network implementation. A solution for these problems may be the delineation of policies and procedures for neural network implementation and the development a new class of neural network client/server applications that fit the needs of current clinical information systems.

Hospital Information Systems↗
PubMedDate not supplied

Codes, operations, measurements and neural networks.

Numerous neural codes and primary neural operations (logical and arithmetical ones, mappings, transformations) were listed [e.g. Perkel, D., Bullock, T.H., 1968. Neurosci. Res. Program Bull 6, 221-348] during the past decades. None of them is ubiquitous or universal. In reality neural operations take place in continuous time and working with unreliable elements, but they still can be simulated with synchronized discrete time scales and chaotic models. Here, a possible neural mechanism, called 'measure like' code is introduced and examined. The neurons are regarded as measuring devices, dealing with 'measures', more or less in mathematical sense. The subadditivity--eminent property of measures--may be implemented with neuronal refractoriness and such synapses operate like particle counters with dead time. This hypothetical code is neither ubiquitous, nor universal, e.g. temporal summation (multiplication) causes just the opposite phenomenon, the supra-additivity also with respect to the number of spikes (anti-measures). This is a cause of more difficult neural implementation of OR gate, than that of the AND. Possibilities for transitional mechanisms (e.g. between traditional logical gates, etc.) are stressed here. Parameter tuning might change either code or operation.

Action Potentials↗
PubMed2002

Lung cancer cell identification based on artificial neural network ensembles.

An artificial neural network ensemble is a learning paradigm where several artificial neural networks are jointly used to solve a problem. In this paper, an automatic pathological diagnosis procedure named Neural Ensemble-based Detection (NED) is proposed, which utilizes an artificial neural network ensemble to identify lung cancer cells in the images of the specimens of needle biopsies obtained from the bodies of the subjects to be diagnosed. The ensemble is built on a two-level ensemble architecture. The first-level ensemble is used to judge whether a cell is normal with high confidence where each individual network has only two outputs respectively normal cell or cancer cell. The predictions of those individual networks are combined by a novel method presented in this paper, i.e. full voting which judges a cell to be normal only when all the individual networks judge it is normal. The second-level ensemble is used to deal with the cells that are judged as cancer cells by the first-level ensemble, where each individual network has five outputs respectively adenocarcinoma, squamous cell carcinoma, small cell carcinoma, large cell carcinoma, and normal, among which the former four are different types of lung cancer cells. The predictions of those individual networks are combined by a prevailing method, i.e. plurality voting. Through adopting those techniques, NED achieves not only a high rate of overall identification, but also a low rate of false negative identification, i.e. a low rate of judging cancer cells to be normal ones, which is important in saving lives due to reducing missing diagnoses of cancer patients.

Adenocarcinoma↗
PubMed1996

Analog versus discrete neural networks.

We show that neural networks with three-times continuously differentiable activation functions are capable of computing a certain family of n-bit boolean functions with two gates, whereas networks composed of binary threshold functions require at least omega(log n) gates. Thus, for a large class of activation functions, analog neural networks can be more powerful than discrete neural networks, even when computing Boolean functions.

Computers, Analog↗
PubMed1989

Prediction of beta-turns in proteins using neural networks.

The use of neural networks to improve empirical secondary structure prediction is explored with regard to the identification of the position and conformational class of beta-turns, a four-residue chain reversal. Recently an algorithm was developed for beta-turn predictions based on the empirical approach of Chou and Fasman using different parameters for three classes (I, II and non-specific) of beta-turns. In this paper, using the same data, an alternative approach to derive an empirical prediction method is used based on neural networks which is a general learning algorithm extensively used in artificial intelligence. Thus the results of the two approaches can be compared. The most severe test of prediction accuracy is the percentage of turn predictions that are correct and the neural network gives an overall improvement from 20.6% to 26.0%. The proportion of correctly predicted residues is 71%, compared to a chance level of about 58%. Thus neural networks provide a method of obtaining more accurate predictions from empirical data than a simpler method of deriving propensities.

Algorithms↗
PubMed2004

Adaptive control for uncertain nonlinear systems based on multiple neural networks.

A new adaptive multiple neural network controller (AMNNC) with a supervisory controller for a class of uncertain nonlinear dynamic systems was developed in this paper. The AMNNC is a kind of adaptive feedback linearizing controller where nonlinearity terms are approximated with multiple neural networks. The weighted sum of the multiple neural networks was used to approximate system nonlinearity for the given task. Each neural network represents the system dynamics for each task. For a job where some tasks are repeated but information on the load is not defined and unknown or varying, the proposed controller is effective because of its capability to memorize control skill for each task with each neural network. For a new task, most similar existing control skills may be used as a starting point of adaptation. With the help of a supervisory controller, the resulting closed-loop system is globally stable in the sense that all signals involved are uniformly bounded. Simulation results on a cartpole system for the changing mass of the pole were illustrated to show the effectiveness of the proposed control scheme for the comparison with the conventional adaptive neural network controller (ANNC).

Journal Article↗