PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Neural Networks, Computer”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 181 records · Page 10Linked to original sources
PubMed1994

EEG-based, neural-net predictive classification of Alzheimer's disease versus control subjects is augmented by non-linear EEG measures.

Attempts to classify Alzheimer's disease (AD) subjects versus controls using spectral-band measures of electroencephalographic (EEG) data typically achieve around 80% success. This study assessed the ability of adding non-linear EEG measures and using a neural-net classification procedure to improve this performance level. The non-linear EEG measures were estimated correlation dimension ("dimensional complexity," or DCx) and saturation (degree of leveling-off of DCx with increasing embedding dimension). In a sample of 39 subjects (14 ADs, 25 controls), it was found that (a) the addition of non-linear EEG measures improved the classification accuracy of the AD/control status of subjects, and (b) a back-percolation neural net predictively classified the subjects much better than the standard linear techniques of multivariate discriminant analysis or nearest-neighbor discriminant analysis.

Aged↗
PubMed1994

An object-oriented approach to knowledge representation in a biomedical domain.

An object-oriented approach has been applied to the different stages involved in developing a knowledge base about insulin metabolism. At an early stage the separation of terminological and assertional knowledge was made. The terminological component was developed by medical experts and represented in CORE. An object-oriented knowledge acquisition process was applied to the assertional knowledge. A frame description is proposed which includes features like states and events, inheritance and collaboration. States and events are formalized with qualitative calculus. The terminological knowledge was very useful in the development of the assertional component. It assisted in understanding the problem domain, and in the implementation stage, it assisted in building good inheritance hierarchies.

Algorithms↗
PubMed1992

Context, cortex, and dopamine: a connectionist approach to behavior and biology in schizophrenia.

Connectionist models are used to explore the relationship between cognitive deficits and biological abnormalities in schizophrenia. Schizophrenic deficits in tasks that tap attention and language processing are reviewed, as are biological disturbances involving prefrontal cortex and the mesocortical dopamine system. Three computer models are then presented that simulate normal and schizophrenic performance in the Stroop task, the continuous performance test, and a lexical disambiguation task. They demonstrate that a disturbance in the internal representation of contextual information can provide a common explanation for schizophrenic deficits in several attention- and language-related tasks. The models also show that these behavioral deficits may arise from a disturbance in a model parameter (gain) corresponding to the neuromodulatory effects of dopamine, in a model component corresponding to the function of prefrontal cortex.

Computer Simulation↗
PubMed1994

Integration of quantitative and qualitative reasoning: an expert system for cardiosurgical patients.

In this work the possibility of building an expert system to reason on the status of post-operative cardiac patients in intensive care units is analysed. The long-term knowledge consists of causal network which describes the main relationships between hemodynamic and metabolic quantities involved in the evolution after cardiac surgery. The inference engine uses an original hybrid formalism, which integrates numerical simulation and qualitative methods. If available, the numerical values of quantities and their exact mathematical relationships are employed; otherwise, the inference engine reasons by using a discrete qualitative representation of quantities. Simulations performed using real data indicate that integration of quantitative and qualitative methods reduces the number of diagnostic scenarios compatible with patient data, and constitutes a valid tool for reasoning about physiological disorders in terms of deep causal knowledge.

Atrial Function, Right↗
PubMed1994

Hippocampal conjunctive encoding, storage, and recall: avoiding a trade-off.

The hippocampus and related structures are thought to be capable of 1) representing cortical activity in a way that minimizes overlap of the representations assigned to different cortical patterns (pattern separation); and 2) modifying synaptic connections so that these representations can later be reinstated from partial or noisy versions of the cortical activity pattern that was present at the time of storage (pattern completion). We point out that there is a trade-off between pattern separation and completion and propose that the unique anatomical and physiological properties of the hippocampus might serve to minimize this trade-off. We use analytical methods to determine quantitative estimates of both separation and completion for specified parameterized models of the hippocampus. These estimates are then used to evaluate the role of various properties and of the hippocampus, such as the activity levels seen in different hippocampal regions, synaptic potentiation and depression, the multi-layer connectivity of the system, and the relatively focused and strong mossy fiber projections. This analysis is focused on the feedforward pathways from the entorhinal cortex (EC) to the dentate gyrus (DG) and region CA3. Among our results are the following: 1) Hebbian synaptic modification (LTP) facilitates completion but reduces separation, unless the strengths of synapses from inactive presynaptic units to active postsynaptic units are reduced (LTD). 2) Multiple layers, as in EC to DG to CA3, allow the compounding of pattern separation, but not pattern completion. 3) The variance of the input signal carried by the mossy fibers is important for separation, not the raw strength, which may explain why the mossy fiber inputs are few and relatively strong, rather than many and relatively weak like the other hippocampal pathways. 4) The EC projects to CA3 both directly and indirectly via the DG, which suggests that the two-stage pathway may dominate during pattern separation and the one-stage pathway may dominate during completion; methods the hippocampus may use to enhance this effect are discussed.

Algorithms↗
PubMed1995

Computerized consensus diagnosis: a classification strategy for the robust analysis of MR spectra. I. Application to 1H spectra of thyroid neoplasms.

We introduce and apply a new classification strategy we call computerized consensus diagnosis (CCD). Its purpose is to provide robust, reliable classification of biomedical data. The strategy involves the cross-validated training of several classifiers of diverse conceptual and methodological origin on the same data, and appropriately combining their outcomes. The strategy is tested on proton magnetic resonance spectra of human thyroid biopsies, which are successfully allocated to normal or carcinoma classes. We used Linear Discriminant Analysis, a Neural Net-based method, and Genetic Programming as independent classifiers on two spectral regions, and chose the median of the six classification outcomes as the consensus. This procedure yielded 100% specificity and 100% sensitivity on the training sets, and 100% specificity and 98% sensitivity on samples of known malignancy in the test sets. We discuss the necessary steps any classification approach must take to guarantee reliability, and stress the importance of fuzziness and undecidability in robust classification.

Adenocarcinoma, Follicular↗
PubMed1992

Generalized multiple-regression techniques with interaction and nonlinearity for system identification in biological treatment processes.

A class of multiple regression models, called "generalized multiple-regression" (GMR) is proposed. GMR has the advantages of being easy and rapid to fit, and uses standard multilinear regression software. It has an advantage over ARIMA models in modeling nonlinearity and linear and nonlinear interactions among variables. Its main disadvantage is that, if there are many independent variables, the reduction of degrees of freedom may be important. It is less parsimonious than other models, but availability of increased computational power makes this not a serious disadvantage. The GMR models are compared to autoregressive transfer function models and feedforward back propagation neural network models. In the case of modeling effluent volatile suspended solids, GMR models were superior to both linear autoregressive models and neural network models. The neural network models did, however, outperform the linear models. In the case of modeling sludge volume index, both GMR and the neural network model were unable to improve upon ARIMA models. It was concluded that ARIMA models may, in some cases, produce the most parsimonious model, but in other cases they may miss important process behaviors. The GMR models showed robust capability to describe complex data.

Models, Theoretical↗
PubMed1992

Natural language processing in psychiatry. Artificial intelligence technology and psychopathology.

The potential benefit of artificial intelligence (AI) technology as a tool of psychiatry has not been well defined. In this essay, the technology of natural language processing and its position with regard to the two main schools of AI is clearly outlined. Past experiments utilizing AI techniques in understanding psychopathology are reviewed. Natural language processing can automate the analysis of transcripts and can be used in modeling theories of language comprehension. In these ways, it can serve as a tool in testing psychological theories of psychopathology and can be used as an effective tool in empirical research on verbal behavior in psychopathology.

Computer Simulation↗
PubMed1991

A computer based model for realistic simulations of neural networks. I. The single neuron and synaptic interaction.

The use of computer simulations as a neurophysiological tool creates new possibilities to understand complex systems and to test whether a given model can explain experimental findings. Simulations, however, require a detailed specification of the model, including the nerve cell action potential and synaptic transmission. We describe a neuron model of intermediate complexity, with a small number of compartments representing the soma and the dendritic tree, and equipped with Na+, K+, Ca2+, and Ca2+ dependent K+ channels. Conductance changes in the different compartments are used to model conventional excitatory and inhibitory synaptic interactions. Voltage dependent NMDA-receptor channels are also included, and influence both the electrical conductance and the inflow of Ca2+ ions. This neuron model has been designed for the analysis of neural networks and specifically for the simulation of the network generating locomotion in a simple vertebrate, the lamprey. By assigning experimentally established properties to the simulated cells and their synapses, it has been possible to verify the sufficiency of these properties to account for a number of experimental findings of the network in operation. The model is, however, sufficiently general to be useful for realistic simulation also of other neural systems.

Computer Simulation↗
PubMed1994

HYCONES II: a tool to build hybrid connectionist expert systems.

This paper describes HYCONES II--a tool to enable the construction of hybrid connectionist expert systems to solve classification problems. HYCONES II offers to the knowledge engineer a hybrid knowledge base that integrates frames with three different neural network models: the combinatorial neural model--CNM, the Fuzzy ARTMAP and the Semantic ART--SMART models. The latter is a new model, introduced by this paper, based on a combination of the two previous models. The validation section compares the performance of these three neural models to solve diagnostic problems in two medical domains. This paper also presents HYCONES II knowledge representation features, built in the symbolic component of its hybrid knowledge-base, to deal and represent fuzzy medical variables. Finally, the present status and future developments of the project are presented.

Algorithms↗
PubMed1995

Protein molecules as computational elements in living cells.

Many proteins in living cells appear to have as their primary function the transfer and processing of information, rather than the chemical transformation of metabolic intermediates or the building of cellular structures. Such proteins are functionally linked through allosteric or other mechanisms into biochemical 'circuits' that perform a variety of simple computational tasks including amplification, integration and information storage.

Animals↗
PubMed1995

Estimation of dynamic joint torques and trajectory formation from surface electromyography signals using a neural network model.

In this study, human arm movement was reconstructed from electromyography (EMG) signals using a forward dynamics model acquired by an artificial neural network within a modular architecture. Dynamic joint torques at the elbow and shoulder were estimated for movements in the horizontal plane from the surface EMG signals of 10 flexor and extensor muscles. Using only the initial conditions of the arm and the EMG time course as input, the network reliably reconstructed a variety of movement trajectories. The results demonstrate that posture maintenance and multijoint movements, entailing complex via-point specification and co-contraction of muscles, can be accurately computed from multiple surface EMG signals. In addition to the model's empirical uses, such as calculation of arm stiffness during motion, it allows evaluation of hypothesized computational mechanisms of the central nervous system such as virtual trajectory control and optimal trajectory planning.

Arm↗
PubMed1994

Advanced clinical monitoring: considerations for real-time hemodynamic diagnostics.

In an effort to ease staffing burdens and potentially improve patient outcome in an intensive care unit (ICU) environment, we are developing a real-time system to accurately and efficiently diagnose cardiopulmonary emergencies. The system is being designed to utilize all relevant routinely-monitored physiological data in order to automatically diagnose potentially fatal events. The initial stage of this project involved formulating the overall system design and appropriate methods for real-time data acquisition, data storage, data trending, waveform analysis, and implementing diagnostic rules. Initially, we defined a conceptual analysis of the minimum physiologic data set, and the monitoring time-frames (trends) which would be required to diagnose cardiopulmonary emergencies. Following that analysis, we used a fuzzy logic diagnostic engine to analyze physiological data during a simulated arrhythmic cardiac arrest (ACA) in order to assess the validity of our diagnostic methodology. We used rate, trend, and morphologic data extracted from the following signals: expired CO2 time-concentration curve (capnogram), electrocardiogram, and arterial blood pressure. The system performed well: The fuzzy logic engine effectively diagnosed the likelihood of ACA from the subtle hemodynamic trends which preceded the complete arrest. As the clinical picture worsened, the fuzzy logic-based system accurately indicated the change in patient condition. Termination of the simulated arrest was rapidly detected by the diagnostic engine. In view of the effectiveness of this fuzzy logic implementation, we plan to develop additional fuzzy logic modules to diagnose other cardiopulmonary emergencies.

Algorithms↗
PubMed1995

More about the difference between men and women: evidence from linear neural networks and the principal-component approach.

The ability of a statistical/neural network to classify faces by sex by means of a pixel-based representation has not been fully investigated. Simulations with pixel-based codes have provided sex-classification results that are less impressive than those reported for measurement-based codes. In no case, however, have the reported pixel-based simulations been optimized for the task of classifying faces by sex. A series of simulations is described in which four network models were applied to the same pixel-based face code. These simulations involved either a radial basis function network or a perceptron as a classifier, preceded or not by a preprocessing step of eigendecomposition. It is shown that performance comparable to that of the measurement-based models can be achieved with pixel-based input (90%) when the data are preprocessed. The effect of the eigendecomposition preprocessing of the faces is then compared with spatial-frequency analysis of face images and analyzed in terms of the perceptual information it captures. It is shown that such an examination may offer insight into the facial aspects important to the sex-classification process. Finally, the contribution of hair information to the performance of the model is evaluated. It is shown that, although the hair contributes to the sex-classification process, it is not the only important contributor.

Algorithms↗
PubMed1995

Neural network system for the evaluation of side-chain packing in protein structures.

An artificial neural network system is used for pattern recognition in protein side-chain-side-chain contact maps. A back-propagation network was trained on a set of patterns which are popular in side-chain contact maps of protein structures. Several neural network architectures and different training parameters were tested to decide on the best combination for the neural network. The resulting network can distinguish between original (from protein structures) and randomized patterns with an accuracy of 84.5% and a Matthews' coefficient of 0.72 for the testing set. Applications of this system for protein structure evaluation and refinement are also proposed. Examples include structures obtained after the application of molecular dynamics to crystal structures, structures obtained from X-ray crystallography at various stages of refinement, structures obtained from a de novo folding algorithm and deliberately misfolded structures.

Amino Acid Sequence↗