[ECG signal analysis by pattern comparison and ECG databanks].
Explore the source record for details and available documents.
Databases as Topic↗
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.
EICO-1: an orthodontist-maintained expert system in clinical orthodontics.
Expert systems are increasingly being used to provide comprehensive interpretative services for diagnosis and treatment planning. Some of these systems are constrained by the complexities of rule-based strategies and a need for knowledge engineers throughout the maintenance phase. A new approach to knowledge acquisition known as Ripple-Down-Rules was used in the development of EICO-1 (Expert Interpretation in Clinical Orthodontics). This expert-maintained system for automating orthodontic reports has a knowledge base of six hundred and eighty rules, and is maintained by an expert trained only in Orthodontics and without the help of knowledge engineers. EICO-1 is the first expert system in Dentistry to use Ripple-Down-Rules. It has potential as an interactive advisory tool and is applicable in a clinical situation.
Artificial Intelligence↗
Using connectionist models to guide assessment of psychological disorder.
Connectionist models are introduced as promising tools for understanding the nature of psychological disorders and guiding their assessment. Specifically, ways in which connectionist models can guide the following aspects of the assessment process are described: understanding what constructs are relevant to assess, designing approaches to assessing these constructs, and understanding individual differences in data from assessments. Two extended examples are given based on the authors' research on cognitive aspects of depression and Alzheimer's disease.
Diagnosis, Computer-Assisted↗
Information encoding and computation with spikes and bursts.
Neurons compute and communicate by transforming synaptic input patterns into output spike trains. The nature of this transformation depends crucially on the properties of voltage-gated conductances in neuronal membranes. These intrinsic membrane conductances can enable neurons to generate different spike patterns including brief, high-frequency bursts that are commonly observed in a variety of brain regions. Here we examine how the membrane conductances that generate bursts affect neural computation and encoding. We simulated a bursting neuron model driven by random current input signal and superposed noise. We consider two issues: the timing reliability of different spike patterns and the computation performed by the neuron. Statistical analysis of the simulated spike trains shows that the timing of bursts is much more precise than the timing of single spikes. Furthermore, the number of spikes per burst is highly robust to noise. Next we considered the computation performed by the neuron: how different features of the input current are mapped into specific output spike patterns. Dimensional reduction and statistical classification techniques were used to determine the stimulus features triggering different firing patterns. Our main result is that spikes, and bursts of different durations, code for different stimulus features, which can be quantified without a priori assumptions about those features. These findings lead us to propose that the biophysical mechanisms of spike generation enables individual neurons to encode different stimulus features into distinct spike patterns.
Computer Simulation↗
Visual representation of cell subpopulation from flow cytometry data.
Flow cytometric systems are useful for protein identification and expression analysis, especially characterizing particular lineage or sublineage of cells. We clustered flow cytometry data of bone marrow cells into subpopulations using a clustering algorithm with its physical characteristics (cell size and cell granularity) and different molecular composition (cell reactivity with monoclonal antibodies). To display the cell subpopulations, we created a colored map according to the mean of 5 flow cytometry parameters based on a cluster. Such a map can reveal subpopulation properties that are not evident in the widely used scatter plot.
Algorithms↗
Quantifying variability in neural responses and its application for the validation of model predictions.
A rate code assumes that a neuron's response is completely characterized by its time-varying mean firing rate. This assumption has successfully described neural responses in many systems. The noise in rate coding neurons can be quantified by the coherence function or the correlation coefficient between the neuron's deterministic time-varying mean rate and noise corrupted single spike trains. Because of the finite data size, the mean rate cannot be known exactly and must be approximated. We introduce novel unbiased estimators for the measures of coherence and correlation which are based on the extrapolation of the signal to noise ratio in the neural response to infinite data size. We then describe the application of these estimates to the validation of the class of stimulus-response models that assume that the mean firing rate captures all the information embedded in the neural response. We explain how these quantifiers can be used to separate response prediction errors that are due to inaccurate model assumptions from errors due to noise inherent in neuronal spike trains.
Action Potentials↗
Constrained camouflage facilitates the evolution of conspicuous warning coloration.
The initial evolution of aposematic and mimetic antipredator signals is thought to be paradoxical because such coloration is expected to increase the risk of predation before reaching a stage when predators associate it effectively with a defense. We propose, however, that constraints associated with the alternative strategy, cryptic coloration, may facilitate the evolution of antipredator signals and thus provide a solution for the apparent paradox. We tested this hypothesis first using an evolutionary simulation to study the effect of a constraint due to habitat heterogeneity, and second using a phylogenetic comparison of the Lepidoptera to investigate the effect of a constraint due to prey motility. In the evolutionary simulation, antipredator warning coloration had an increased probability to invade the prey population when the evolution of camouflage was constrained by visual difference between microhabitats. The comparative study was done between day-active lepidopteran taxa, in which camouflage is constrained by motility, and night-active taxa, which rest during the day and are thus able to rely on camouflage. We compared each of seven phylogenetically independent day-active groups with a closely related nocturnal group and found that antipredator signals have evolved at least once in all the diurnal groups but in none of their nocturnal matches. Both studies lend support to our idea that constraints on crypsis may favor the evolution of antipredator warning signals.
Animals↗
Structured data collection and knowledge-based user guidance for abdominal ultrasound reporting.
This paper describes a system for structured data collection and report generation in abdominal ultrasonography. The system is based on a controlled vocabulary and hierarchies of concepts; it uses a graphical user interface. More than 17,000 reports have been generated by 43 physicians using this system, which is integrated into a departmental information system. Evaluations have shown that it is a well accepted tool for the fast generation of reports of comparatively high quality. The functionality is enhanced by two additional components: a hybrid knowledge-based module for "intelligent" user guidance and an interactive tutoring system to illustrate the terminology.
Abdomen↗
Variational learning for switching state-space models.
We introduce a new statistical model for time series that iteratively segments data into regimes with approximately linear dynamics and learnsthe parameters of each of these linear regimes. This model combines and generalizes two of the most widely used stochastic time-series models -- hidden Markov models and linear dynamical systems -- and is closely related to models that are widely used in the control and econometrics literatures. It can also be derived by extending the mixture of experts neural network (Jacobs, Jordan, Nowlan, & Hinton, 1991) to its fully dynamical version, in which both expert and gating networks are recurrent. Inferring the posterior probabilities of the hidden states of this model is computationally intractable, and therefore the exact expectation maximization (EM) algorithm cannot be applied. However, we present a variational approximation that maximizes a lower bound on the log-likelihood and makes use of both the forward and backward recursions for hidden Markov models and the Kalman filter recursions for linear dynamical systems. We tested the algorithm on artificial data sets and a natural data set of respiration force from a patient with sleep apnea. The results suggest that variational approximations are a viable method for inference and learning in switching state-space models.
Algorithms↗
Artificial neural networks aided deconvolving overlapped peaks in chromatograms.
A novel method for deconvolving overlapped peaks in chromatograms is proposed. The basic idea of this method consists of finding a set of parameters which characterize the shape of the overlapped peaks and using a multi-layered perceptron network for quantitatively correlating the parameters with the percentage area of an individual peak. The proposed method performs very well with high accuracy and less computing time compared to other conventional methods.
Chromatography↗
Abstract and associatively based representations in human sequence learning.
We give an analysis of performance in an artificial neural network for which the claim had been made that it could learn abstract representations. Our argument is that this network is associative in nature, and cannot develop abstract representations. The network thus converges to a solution that is solely based on the statistical regularities of the training set. Inspired by human experiments that have shown that humans can engage in both associative (statistical) and abstract learning, we present a new, hybrid computational model that combines associative and more abstract, cognitive processes. To cross-validate the model we attempted to predict human behaviour in further experiments. One of these experiments reveals some evidence for the use of abstract representations, whereas the others provide evidence for associatively based performance. The predictions of the hybrid model stand in line with our empirical data.
Computer Simulation↗
Modeling the surround of MT cells and their selectivity for surface orientation in depth specified by motion.
The projective transformation onto the retina loses the explicit 3D shape description of a moving object. Theoretical studies show that the reconstruction of 3D shape from 2D motion information (shape from motion, SFM) is feasible provided that the first- and second-order directional derivatives of the 2D velocity field are available. Experimental recordings have revealed that the receptive fields of the majority of the cells in macaque area middle temporal (MT) display an antagonistic (suppressive) surround and that a sizable portion of these surrounds are asymmetrical. This has led to the conjecture that these cells provide a local measure for the directional derivatives of the 2D velocity field. In this article, we adopt a nonparametric and biologically plausible approach to modeling the role played by the MT surrounds in the recovery of the orientation in depth (the slant and tilt) of a moving (translating) plane. A three-layered neural network is trained to represent the slant and tilt from the projected motion vectors. The hidden units of the network have speed-tuning characteristics and represent the MT model neurons with their surrounds. We conjecture that the MT surround results from lateral inhibitory connections with other MT cells and that populations of these cells, with different surround types, code linearly for slant and tilt of translating planes.
Animals↗
Learning-induced synchronization and plasticity of a developing neural network.
Learning-induced synchronization of a neural network at various developing stages is studied by computer simulations using a pulse-coupled neural network model in which the neuronal activity is simulated by a one-dimensional map. Two types of Hebbian plasticity rules are investigated and their differences are compared. For both models, our simulations show a logarithmic increase in the synchronous firing frequency of the network with the culturing time of the neural network. This result is consistent with recent experimental observations. To investigate how to control the synchronization behavior of a neural network after learning, we compare the occurrence of synchronization for four networks with different designed patterns under the influence of an external signal. The effect of such a signal on the network activity highly depends on the number of connections between neurons. We discuss the synaptic plasticity and enhancement effects for a random network after learning at various developing stages.
Algorithms↗
Adaptive categorization of ART networks in robot behavior learning using game-theoretic formulation.
Adaptive Resonance Theory (ART) networks are employed in robot behavior learning. Two of the difficulties in online robot behavior learning, namely, (1) exponential memory increases with time, (2) difficulty for operators to specify learning tasks accuracy and control learning attention before learning. In order to remedy the aforementioned difficulties, an adaptive categorization mechanism is introduced in ART networks for perceptual and action patterns categorization in this paper. A game-theoretic formulation of adaptive categorization for ART networks is proposed for vigilance parameter adaptation for category size control on the categories formed. The proposed vigilance parameter update rule can help improving categorization performance in the aspect of category number stability and solve the problem of selecting initial vigilance parameter prior to pattern categorization in traditional ART networks. Behavior learning using physical robot is conducted to demonstrate the effectiveness of the proposed adaptive categorization mechanism in ART networks.
Algorithms↗
NSL a Neuro-Symbolic Language for a Neuro-Symbolic Processor (NSP).
A Neuro-Symbolic Language for monotonic and non-monotonic parallel logical inference by means of artificial neural networks (ANNs) is presented. Both the language and its compiler have been designed and implemented in order to translate the neural representation of a given problem into a VHDL software, which in turn can set devices such as FPGA. The result of this operation leads to an electronic circuit that we call NSP (Neuro-Symbolic Processor).
Artificial Intelligence↗
Neuron selection for RBF neural network classifier based on data structure preserving criterion.
The central problem in training a radial basis function neural network is the selection of hidden layer neurons. In this paper, we propose to select hidden layer neurons based on data structure preserving criterion. Data structure denotes relative location of samples in the high-dimensional space. By preserving the data structure of samples including those that are close to separation boundaries between different classes, the neuron subset selected retains the separation margin underlying the full set of hidden layer neurons. As a direct result, the network obtained tends to generalize well.
Algorithms↗
Clinical simulation using context-sensitive temporal probability models.
We present a language for representing context-sensitive temporal probabilistic knowledge. Context constraints allow inference to be focused on only the relevant portions of the probabilistic knowledge. We provide a declarative semantics for our language and an implemented algorithm (BNG) that generates Bayesian networks to compute the posterior probabilities of queries. We illustrate the use of the BNG system by applying it to the problem of modeling the effects of medications and other interventions on the condition of a patient in cardiac arrest.
Artificial Intelligence↗
Using neural networks to solve the multicast routing problem in packet radio networks.
The primary function of a packet radio network is the efficient transfer of information between source and destination nodes using minimal bandwidth and end-to-end delay. Many researchers have investigated the problem of minimizing the end-to-end delay from a single source to a single destination for a variety of networks; however, very little work is reported about routing mechanisms for the common case where a particular information packet is intended to be sent to more than one destination in the network. This is known as multicasting. A simplified version of the problem is to ignore the packet delay at each node, then the problem becomes one of finding solutions which require the least number of transmissions. Determination of an optimal solution is NP-complete meaning that suboptimal solutions are frequently tolerated. The problem becomes more rigorous if packet delays are included in the network topology. This paper describes a practical technique for the computation of optimum or near optimum solutions to the multicasting problem with and without packet delay. The method is based on the Hopfield neural network and experiment has shown this method to yield near optimal solutions while requiring a minimum of CPU time.
Algorithms↗