Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Networks”

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 937 records · Page 52Linked to original sources
PubMed1994

Neural networks and psychiatry: candidate applications in clinical decision making.

Neural networks comprise a fundamentally new type of computer system inspired by the functioning of neurons in the brain. Such networks are good at solving problems that involve pattern recognition and categorisation. An important difference between a neural network and a traditional computer system is that in developing an application, a neural network is not programmed; instead, it is trained to solve a particular type of problem. This ability to learn to solve a problem makes neural networks adaptable to solving a wide variety of problems, some of which have proved intractable using a traditional computing approach. Neural networks are particularly suited to tasks involving the categorisation of patterns of information, such as is required in diagnosis and clinical decision making. In the last three years reports of applications involving neural networks have begun to appear in the medical literature, and these are described in this paper. However, a comprehensive search of the literature has shown that there have not as yet been reports of any applications in psychiatry. This paper discusses the nature of clinical decision making, outlines the sorts of problems in psychiatry which neural networks applications might be developed to address, and gives examples of candidate applications in clinical decision making.

Adult↗
PubMed2006

Artificial neural network properties associated with wiring patterns in the visual projections of vertebrates and arthropods.

We model the functioning of different wiring schemes in visual projections using artificial neural networks and so speculate on selective factors underlying taxonomic variation in neural architecture. We model the high connective overlap of vertebrates (where networks have a dense mesh of connections) and the less overlapping, more modular architecture of arthropods. We also consider natural variation in these basic wiring schemes. Generally, arthropod networks are as efficient or more efficient in functioning compared to vertebrate networks. They do not show the confusion effect (decreasing targeting accuracy with increasing input group size), and they train as well or better. Arthropod networks are, however, generally poorer at reconstructing novel inputs. The ability of vertebrate networks to effectively process novel stimuli could promote behavioral sophistication and drive the evolution of vertebrate wiring schemes. Vertebrate networks with less connective overlap have, surprisingly, similar or superior properties compared to those with high connective overlap. Thus, the partial connective overlap seen in real vertebrate visual projections may be an optimal, evolved solution. Arthropod networks with and without whole-cell neural connections within neural layers have similar properties. This indicates that neural connections mediated by offshoots of single cells (dendrites) may be fundamental to generating the confusion effect.

Animals↗
PubMed2004

A neural network method for prediction of beta-turn types in proteins using evolutionary information.

MOTIVATION: The prediction of beta-turns is an important element of protein secondary structure prediction. Recently, a highly accurate neural network based method Betatpred2 has been developed for predicting beta-turns in proteins using position-specific scoring matrices (PSSM) generated by PSI-BLAST and secondary structure information predicted by PSIPRED. However, the major limitation of Betatpred2 is that it predicts only beta-turn and non-beta-turn residues and does not provide any information of different beta-turn types. Thus, there is a need to predict beta-turn types using an approach based on multiple sequence alignment, which will be useful in overall tertiary structure prediction. RESULTS: In the present work, a method has been developed for the prediction of beta-turn types I, II, IV and VIII. For each turn type, two consecutive feed-forward back-propagation networks with a single hidden layer have been used where the first sequence-to-structure network has been trained on single sequences as well as on PSI-BLAST PSSM. The output from the first network along with PSIPRED predicted secondary structure has been used as input for the second-level structure-to-structure network. The networks have been trained and tested on a non-homologous dataset of 426 proteins chains by 7-fold cross-validation. It has been observed that the prediction performance for each turn type is improved significantly by using multiple sequence alignment. The performance has been further improved by using a second level structure-to-structure network and PSIPRED predicted secondary structure information. It has been observed that Type I and II beta-turns have better prediction performance than Type IV and VIII beta-turns. The final network yields an overall accuracy of 74.5, 93.5, 67.9 and 96.5% with MCC values of 0.29, 0.29, 0.23 and 0.02 for Type I, II, IV and VIII beta-turns, respectively, and is better than random prediction. AVAILABILITY: A web server for prediction of beta-turn types I, II, IV and VIII based on above approach is available at http://www.imtech.res.in/raghava/betaturns/ and http://bioinformatics.uams.edu/mirror/betaturns/ (mirror site).

Algorithms↗
PubMed1992

Escherichia coli promoters: neural networks develop distinct descriptions in learning to search for promoters of different spacing classes.

Back-propagation neural networks were trained to recognize promoter sequences of each of the three major spacing classes found in E. coli. These networks were trained with the object of maximizing their ability to generalize while maintaining the level of false positive identifications at a fraction of 1 percent. These objectives were generally met. Networks for the 16 base spacing class captured between 78 and 100% of previously unseen promoters in different tests; networks for the 17 base class identified 97% of the test promoters; networks for the 18 base class identified 79% of the test promoters. A tandem poll of networks for all three spacing classes produced a cumulative false positive level of less than 0.5%. In each case, the weight matrices used by the networks in their classification were analyzed to determine the relative weight assigned to the occurrence of a given base at a given position within the promoter. In this fashion, an approximate description of the network's definition of the promoter can be obtained.

Base Sequence↗
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

Integration of clinical and imaging data to predict the presence of coronary artery disease with the use of neural networks.

AIM: To establish proof of the principle that a computer-based neural network method can be employed that will enhance diagnostic accuracy vis-a-vis image analysis alone in the interpretation of treadmill exercise tests performed in conjunction with myocardial perfusion imaging. MATERIALS AND METHODS: One-hundred-and-two patients underwent myocardial perfusion imaging in association with the standard Bruce protocol. Twenty objective parameters describing each patient's exercise physiology, general clinical status and image appearance were used to train an artificial neural network. Classification accuracy of the neural network and clinical interpretation was determined by coronary angiography. We evaluated the ability of the neural network to integrate clinical, exercise and imaging data to determine the likelihood of coronary artery disease and compared these results with an optimized method of clinical image interpretation, which made use of all available clinical, angiographic and stress test data. RESULTS: The artificial neural network had a sensitivity of 88% and a specificity of 65% for detection of ischemic heart disease and was comparable to that of the optimized clinical method (sensitivity 80%, specificity 69%). Incorporation of clinical and exercise data significantly improved the predictive accuracy of the network compared to a network based on image data alone (P<0.05). CONCLUSION: The results show a computer-based neural network can perform as well as expert readers working under optimal conditions including full knowledge of the patient's clinical, prior angiographic and stress test data. Thus, the method is promising as a diagnostic aid to the recognition of ischemic heart disease in the clinical setting of treadmill exercise testing in conjunction with myocardial perfusion imaging.

Aged↗
PubMed2003

An artificial neural network for prostate cancer staging when serum prostate specific antigen is 10 ng./ml. or less.

PURPOSE: An artificial neural network was developed to improve the prediction of pathological stage before radical prostatectomy based on variables available at biopsy and clinical parameters. MATERIALS AND METHODS: We used the prospectively accrued European prostate cancer detection data base to train an artificial neural network to predict pathological stage in 200 men with serum prostate specific antigen (PSA) 10 ng./ml. or less who underwent radical prostatectomy. Variables included in the artificial neural network were patient age, serum PSA, free-to-total PSA ratio, PSA velocity, transrectal ultrasound calculated total and transition zone volumes with their associated PSA parameters (transition zone PSA density and PSA density), digital rectal examination and Gleason score on biopsy. Two multilayer perceptron neural networks were trained on the remaining variables. Data on the 200 patients were divided randomly into a training set, a test set and a validation or prospective set. RESULTS: Overall classification accuracy of the artificial neural network was 92.7% and 84.2% for organ confined and advanced prostate cancer staging, respectively. For preoperatively predicting local versus advanced stage the area under the ROC curve for the artificial neural network was significantly larger (0.91) compared with logistic regression analysis (0.83), Gleason score (0.69), PSA density (0.68), prostate transition zone volume (0.63) and serum PSA (0.62) (all p <0.01). CONCLUSIONS: The artificial neural network outperformed logistic regression analysis and correctly predicted pathological stage in more than 90% of the validation patients with serum PSA 10 ng./ml. or less based on clinical, biochemical and biopsy data. In the future artificial neural networks may represent a significant step for improved staging of prostate cancer when counseling patients referred for radical prostatectomy or other curative treatments.

Adult↗
PubMed2001

Developing network-based services in the NHS.

Networks, based upon informal relationships, have ensured that care was delivered to patients for many years. This informal organisation of care, based upon personal relationships, ensures that where the bureaucratic organisation fails the patient, health professionals' work together to network the resources the patient needs. Networks are not new. Formalising networks and recognising their potential to deliver seamless care is new. The NHS must ensure that networks are developed, allowing them freedom from bureaucracy to reach their potential. The Northern and Yorkshire Learning Alliance (NYLA) was established as part of the Northern and Yorkshire health community's efforts to radically improve care. The NYLA operates as a network with a small team of change experts working to develop change management and service improvement capacity across 10,000 square miles. As a network based organisation the team has learned many lessons, which may inform the development of clinical networks in England.

Community Networks↗
PubMed2001

A novel large-memory neural network as an aid in medical diagnosis applications.

This paper describes the application of a large memory storage and retrieval (LAMSTAR) neural network to medical diagnosis and medical information retrieval problems. The network is based on Minsky's knowledge-lines (k-lines) theory of memory storage and retrieval in the central nervous system. It employs arrays of self-organized map modules, such that the k-lines are implemented via link weights (address correlation) that are being updated by learning. The network also employs features of forgetting and of interpolation and extrapolation, thus being able to handle incomplete data sets. It can deal equally well with exact and fuzzy information, thus being specifically applicable to medical diagnosis where the diagnosis is based on exact data, fuzzy patient interview information, patient history, observed images, and test records. Furthermore, the network can be operated in closed loop with Internet search engines to intelligently use data from the Internet in a higher hierarchy of learning. All of the above features are shown to make the LAMSTAR network suitable for medical diagnosis problems that concern large data sets of many categories that are often incomplete and fuzzy. Applications of the network to three specific medical diagnosis problems are described: two from nephrology and one related to an emergency-room drug identification problem. It is shown that the LAMSTAR network is hundreds and thousands times faster in its training than back-propagation-based networks when used for the same problem and with exactly the same information.

Computational Biology↗
PubMed2005

Simultaneous perturbation learning rule for recurrent neural networks and its FPGA implementation.

Recurrent neural networks have interesting properties and can handle dynamic information processing unlike ordinary feedforward neural networks. However, they are generally difficult to use because there is no convenient learning scheme. In this paper, a recursive learning scheme for recurrent neural networks using the simultaneous perturbation method is described. The detailed procedure of the scheme for recurrent neural networks is explained. Unlike ordinary correlation learning, this method is applicable to analog learning and the learning of oscillatory solutions of recurrent neural networks. Moreover, as a typical example of recurrent neural networks, we consider the hardware implementation of Hopfield neural networks using a field-programmable gate array (FPGA). The details of the implementation are described. Two examples of a Hopfield neural network system for analog and oscillatory targets are shown. These results show that the learning scheme proposed here is feasible.

Algorithms↗
PubMed2005

Neural and fuzzy computation techniques for playout delay adaptation in VoIP networks.

Playout delay adaptation algorithms are often used in real time voice communication over packet-switched networks to counteract the effects of network jitter at the receiver. Whilst the conventional algorithms developed for silence-suppressed speech transmission focused on preserving the relative temporal structure of speech frames/packets within a talkspurt (intertalkspurt adaptation), more recently developed algorithms strive to achieve better quality by allowing for playout delay adaptation within a talkspurt (intratalkspurt adaptation). The adaptation algorithms, both intertalkspurt and intratalkspurt based, rely on short term estimations of the characteristics of network delay that would be experienced by up-coming voice packets. The use of novel neural networks and fuzzy systems as estimators of network delay characteristics are presented in this paper. Their performance is analyzed in comparison with a number of traditional techniques for both inter and intratalkspurt adaptation paradigms. The design of a novel fuzzy trend analyzer system (FTAS) for network delay trend analysis and its usage in intratalkspurt playout delay adaptation are presented in greater detail. The performance of the proposed mechanism is analyzed based on measured Internet delays. Index Terms-Fuzzy delay trend analysis, intertalkspurt, intratalkspurt, multilayer perceptrons (MLPs), network delay estimation, playout buffering, playout delay adaptation, time delay neural networks (TDNNs), voice over Internet protocol (VoIP).

Algorithms↗
PubMed1996

Automatic detection of diabetic retinopathy using an artificial neural network: a screening tool.

AIMS: To determine if neural networks can detect diabetic features in fundus images and compare the network against an ophthalmologist screening a set of fundus images. METHODS: 147 diabetic and 32 normal images were captured from a fundus camera, stored on computer, and analysed using a back propagation neural network. The network was trained to recognise features in the retinal image. The effects of digital filtering techniques and different network variables were assessed. 200 diabetic and 101 normal images were then randomised and used to evaluate the network's performance for the detection of diabetic retinopathy against an ophthalmologist. RESULTS: Detection rates for the recognition of vessels, exudates, and haemorrhages were 91.7%, 93.1%, and 73.8% respectively. When compared with the results of the ophthalmologist, the network achieved a sensitivity of 88.4% and a specificity of 83.5% for the detection of diabetic retinopathy. CONCLUSIONS: Detection of vessels, exudates, and haemorrhages was possible, with success rates dependent upon preprocessing and the number of images used in training. When compared with the ophthalmologist, the network achieved good accuracy for the detection of diabetic retinopathy. The system could be used as an aid to the screening of diabetic patients for retinopathy.

Diabetic Retinopathy↗
PubMed2001

Modelling and prediction for chaotic fir laser attractor using rational function neural network.

Many real-world systems such as irregular ECG signal, volatility of currency exchange rate and heated fluid reaction exhibit highly complex nonlinear characteristic known as chaos. These chaotic systems cannot be retreated satisfactorily using linear system theory due to its high dimensionality and irregularity. This research focuses on prediction and modelling of chaotic FIR (Far InfraRed) laser system for which the underlying equations are not given. This paper proposed a method for prediction and modelling a chaotic FIR laser time series using rational function neural network. Three network architectures, TDNN (Time Delayed Neural Network), RBF (radial basis function) network and the RF (rational function) network, are also presented. Comparisons between these networks performance show the improvements introduced by the RF network in terms of a decrement in network complexity and better ability of predictability.

Infrared Rays↗
PubMed2002

Hierarchical genetic algorithm for near optimal feedforward neural network design.

In this paper, we propose a genetic algorithm based design procedure for a multi layer feed forward neural network. A hierarchical genetic algorithm is used to evolve both the neural networks topology and weighting parameters. Compared with traditional genetic algorithm based designs for neural networks, the hierarchical approach addresses several deficiencies, including a feasibility check highlighted in literature. A multi objective cost function is used herein to optimize the performance and topology of the evolved neural network simultaneously. In the prediction of Mackey Glass chaotic time series, the networks designed by the proposed approach prove to be competitive, or even superior, to traditional learning algorithms for the multi layer Perceptron networks and radial basis function networks. Based upon the chosen cost function, a linear weight combination decision making approach has been applied to derive an approximated Pareto optimal solution set. Therefore, designing a set of neural networks can be considered as solving a two objective optimization problem.

Algorithms↗
PubMedDate not supplied

A discrete fully recurrent network of max product units for associative memory and classification.

This paper defines the truncated normalized max product operation for the transformation of states of a network and provides a method for solving a set of equations based on this operation. The operation serves as the transformation for the set of fully connected units in a recurrent network that otherwise might consist of linear threshold units. Component values of the state vector and outputs of the units take on the values in the set [0, 0.1,..., 0.9, 1]. The result is a much larger state space given a particular number of units and size of connection matrix than for a network based on threshold units. Since the operation defined here can form the basis of transformations in a recurrent network with a finite number of states, fixed points or cycles are possible and the network based on this operation for transformations can be used as an associative memory or pattern classifier with fixed points taking on the role of prototypes. Discrete fully recurrent networks have proven themselves to be very useful as associative memories and as classifiers. However they are often based on units that have binary states. The effect of this is that the data to be processed consisting of vectors in R(n) have to be converted to vectors in [0, 1]m with m much larger than n since binary encoding based on positional notation is not feasible. This implies a large increase in the number of components. The effect can be lessened by allowing more states for each unit in our network. The network proposed demonstrates those properties that are desirable in an associative memory very well as the simulations show.

Algorithms↗
PubMed1994

Generation of associative processes in a neural network with realistic features of architecture and units.

A recent neural network model of cortical associative memory incorporating neuronal adaptation by a simplified description of its underlying ionic mechanisms is extended towards more realistic network units and architecture. Excitatory units correspond to groups of adapting pyramidal neurons and inhibitory units to groups of nonadapting interneurons. The network architecture is formed from pairs of one pyramidal and one interneuron unit each with inhibitory connections within and excitatory connections between pairs. The degree of adaptability of the pyramidal units controls the character of the network dynamics. An intermediate adaptability generates limit cycles of transitions between stored patterns and regulates oscillation frequencies in the range of theta rhythms observed in the brain. In particular, neuronal adaptation can impose a direction of transitions between overlapping patterns also in a symmetrically connected network. The model permits a detailed analysis of the transition mechanisms. Temporal sequences of patterns thus formed may constitute parts of associative processes, such as recall of stored sequences or search of pattern subspaces. As a special case, neuronal adaptation can accomplish pattern segmentation by which overlapping patterns are temporally resolved. The type of limit cycles produced by neuronal adaptation may also be of significance for central pattern generators, also for networks involving motor neurons. The applied learning rule of Hebbian type is compared to a modified version also common in neural network modelling. It is also shown that the dependence of the network dynamic behaviour on neuronal adaptability, from fixed point attractors at weak adaptability towards more complex dynamics of limit cycles and chaos at strong adaptability, agrees with that recently observed in a more abstract version of the model. The present description of neuronal adaptation is compared to models based on dynamic firing thresholds.

Association↗
PubMed1995

Analysis of training set parallelism for backpropagation neural networks.

Training set parallelism and network based parallelism are two popular paradigms for parallelizing a feedforward (artificial) neural network. Training set parallelism is particularly suited to feedforward neural networks with backpropagation learning where the size of the training set is large in relation to the size of the network. This paper analyzes training set parallelism for feedforward neural networks when implemented on a transputer array configured in a pipelined ring topology. Theoretical expressions for the time per epoch (iteration) and optimal size of a processor network are derived when the training set is equally distributed among the processing nodes. These show that the speed up is a function of the number of patterns per processor, communication overhead per epoch and the total number of processors in the topology. Further analysis of how to optimally distribute the training set on a given processor network when the number of patterns in the training set is not an integer multiple of the number of processors, is also carried out. It is shown that optimal allocation of patterns in such cases is a mixed integer programming problem. Using this analysis it is found that equal distribution of training patterns among the processors is not the optimal way to allocate the patterns even when the training set is an integer multiple of the number of processors. Extension of the analysis to processor networks comprising processors of different speeds is also carried out. Experimental results from a T805 transputer array are presented to verify all the theoretical results.

Algorithms↗
PubMed1995

Locally activated neural networks and stable neural controller design for nonlinear dynamic systems.

A stable neural control scheme using a locally activated neural network has been proposed for a class of nonlinear dynamic systems. The locally activated neural network, for a given input, essentially selects a small subset of the network hidden nodes for output computation using the CMAC-like content addressing mechanism. This network aims to maintain local representations of the system dynamics. Thus, the global control performance in the concerned state space is achieved by the cooperation of many local control efforts and furthermore, real-time control can be facilitated because only a small sized network is involved to control and learn at any given time. The proposed control scheme is composed of two stages: (1) prediction error based learning in which the network attempts to learn the nonlinear basis functions of the plant inverse dynamics by a modified backpropagation learning rule; and (2) tracking error based learning in which the network weights are further fine-tuned using the basis set obtained in (1). This basis set spans the locally partitioned vector space of the system inverse dynamics when the prediction error based learning is achieved within a prescribed error tolerance. For uniform stability, the sliding mode control is introduced as a safety mechanism when the network has not sufficiently learned the plant dynamics yet. With suitable assumptions on the controlled plant, global stability and tracking error convergence proof has been given. Finally, the proposed control scheme is verified with computer simulation.

Adaptation, Physiological↗