PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “regularized model”

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 91 records · Page 5Linked to original sources
PubMed2005

Mixture models with adaptive spatial regularization for segmentation with an application to FMRI data.

Mixture models are often used in the statistical segmentation of medical images. For example, they can be used for the segmentation of structural images into different matter types or of functional statistical parametric maps (SPMs) into activations and nonactivations. Nonspatial mixture models segment using models of just the histogram of intensity values. Spatial mixture models have also been developed which augment this histogram information with spatial regularization using Markov random fields. However, these techniques have control parameters, such as the strength of spatial regularization, which need to be tuned heuristically to particular datasets. We present a novel spatial mixture model within a fully Bayesian framework with the ability to perform fully adaptive spatial regularization using Markov random fields. This means that the amount of spatial regularization does not have to be tuned heuristically but is adaptively determined from the data. We examine the behavior of this model when applied to artificial data with different spatial characteristics, and to functional magnetic resonance imaging SPMs.

Algorithms↗
PubMed2006

Adaptive regularization network based neural modeling paradigm for nonlinear adaptive estimation of cerebral evoked potentials.

In this paper we report an adaptive regularization network (ARN) approach to realizing fast blind separation of cerebral evoked potentials (EPs) from background electroencephalogram (EEG) activity with no need to make any explicit assumption on the statistical (or deterministic) signal model. The ARNs are proposed to construct nonlinear EEG and EP signal models. A novel adaptive regularization training (ART) algorithm is proposed to improve the generalization performance of the ARN. Two adaptive neural modeling methods based on the ARN are developed and their implementation and performance analysis are also presented. The computer experiments using simulated and measured visual evoked potential (VEP) data have shown that the proposed ARN modeling paradigm yields computationally efficient and more accurate VEP signal estimation owing to its intrinsic model-free and nonlinear processing characteristics.

Algorithms↗
PubMed2005

The effect of cross-channel synchrony on the perception of temporal regularity.

Temporal models of pitch are based on the assumption that the auditory system measures the time intervals between neural events, and that pitch corresponds to the most common time interval. The current experiments were designed to test whether time intervals are analyzed independently in each peripheral channel, or whether the time-interval analysis in one channel is affected by synchronous activity in other channels. Regular and irregular click trains were filtered into narrow frequency bands to produce target and flanker stimuli. The threshold for discriminating a regular target from an irregular distracter click train was measured in the presence of an irregular masker click train in the target band, as a function of the frequency separation between the target band and a flanker band. The flanker click train was either regular or irregular. The threshold for detecting the regular target was 5-7 dB lower when the flanker was regular. The data indicate that the detection of temporal regularity (and thus, pitch) involves cross-channel processes that can operate over widely separated channels. Model simulations suggest that these cross-channel processes occur after the time-interval extraction stage and that they depend on the similarity, or consistency, of the time-interval patterns in the relevant channels.

Acoustic Stimulation↗
PubMed2005

Application of Bayesian regularized BP neural network model for analysis of aquatic ecological data-a case study of chlorophyll-a prediction in Nanzui water area of Dongting Lake.

Bayesian regularized BP neural network(BRBPNN) technique was applied in the chlorophyll-a prediction of Nanzui water area in Dongting Lake. Through BP network interpolation method, the input and output samples of the network were obtained. After the selection of input variables using stepwise/multiple linear regression method in SPSS 11.0 software, the BRBPNN model was established between chlorophyll-a and environmental parameters, biological parameters. The achieved optimal network structure was 3-11-1 with the correlation coefficients and the mean square errors for the training set and the test set as 0.999 and 0.00078426, 0.981 and 0.0216 respectively. The sum of square weights between each input neuron and the hidden layer of optimal BRBPNN models of different structures indicated that the effect of individual input parameter on chlorophyll-a declined in the order of alga amount > secchi disc depth (SD) > electrical conductivity (EC). Additionally, it also demonstrated that the contributions of these three factors were the maximal for the change of chlorophyll-a concentration, total phosphorus (TP) and total nitrogen (TN) were the minimal. All the results showed that BRBPNN model was capable of automated regularization parameter selection and thus it may ensure the excellent generation ability and robustness. Thus, this study laid the foundation for the application of BRBPNN model in the analysis of aquatic ecological data(chlorophyll-a prediction) and the explanation about the effective eutrophication treatment measures for Nanzui water area in Dongting Lake.

Bayes Theorem↗
PubMed1991

Regularity analysis in a compartmental model of chopper units in the anteroventral cochlear nucleus.

1. We investigate the discharge patterns of chopper units in the anteroventral cochlear nucleus (AVCN) by developing an equivalent cylinder compartmental model of AVCN stellate cells, which are the sources of the chopper response pattern. The model consists of a passive dendritic tree connected to somatic and axonal compartments with voltage-sensitive channels. Synaptic inputs to the model are simulated auditory nerve fiber responses to best-frequency tones. 2. We adjust the anatomic and electrical parameters of the model to agree with available intracellular data from stellate cells in the AVCN of the mouse and the cat and compare the response of the model to injected current with responses recorded in vitro. The model shows approximately linear current-voltage characteristics for small hyperpolarizing currents. The model's input resistance and the time course of its response to hyperpolarizing current applied at the soma are comparable with those measured from stellate cells in vitro. In response to sustained depolarizing current, the model fires repetitively with nearly perfect regularity, a property also observed in vitro. 3. Auditory nerve inputs to the cell are modeled as deadtime-modified Poisson processes with a multiexponential adaptation in the Poisson rate. We are able to adjust the number, rate, and location of excitatory and inhibitory inputs to the model and succeed in simulating chopper response patterns seen in vivo. 4. Chopper units exhibit a variety of regularity and adaptation patterns in response to tone stimuli. Physiological data from brain slice experiments and experiments in vivo imply that this heterogeneity is primarily due to differences in input configurations. By systematically varying the number and position of excitatory and inhibitory inputs, we can simulate a range of chopper response patterns. 5. We quantify the regularity of the model's response using the coefficient of variation (CV) of the interspike interval. We find that the CV decreases, i.e., the regularity increases, as the number of converging inputs or their distance from the soma increases. The regularity of the output is more sensitive to the number of converging inputs than to their location on the dendritic tree. The statistics of the first spike latency (FSL) are also sensitive to the configuration of excitatory inputs. The mean and minimum FSL are more sensitive to the electrotonic distance of the inputs from the soma than to the number of inputs, whereas the standard deviation of the FSL is highly dependent on the number of converging inputs and is nearly independent of their location.(ABSTRACT TRUNCATED AT 400 WORDS)

Axons↗
PubMed2005

[Bayesian regularized BP neural network model for quantitative relationship between the electrochemical reduction potential and molecular structures of chlorinated aromatic compounds].

Bayesian regularized BP neural network (BRBPNN) technique was applied in QSPR model in environmental field. The BRBPNN model for quantitative relationship between the electrochemical reduction potential (ERP) and chemical structures of 87 chlorinated aromatic compounds was established. The structure descriptor pool is consisted of Cl number (Cl), molecular weight (MW) and 6 quantum chemistry parameters which are calculated by MOPAC2000 built in ChemOffice2004, including energy of the highest occupied molecular orbital (E(HOMO)), energy of the lowest occupied molecular orbital (E(LUMO)), heat of formation(HF), dipole(DIP), electronic energy(EE), core-core repulsion(CCR). The achieved optimal network structure was 6-20-1, which possessed stronger fitting and prediction capacity than that of the stepwise linear regression and with the correlation coefficients square and the mean square error for the training set and the test set as 0.999 and 0.000105, 0.965 and 0.00159 respectively. The sum of square weights between each input neuron and the hidden layer of BRBPNN(6-20-1) indicate the effect of descriptor on the electric potential declining in the order of ELUMO > EHOMO > HF> CCR > EE > DIP. The scatter diagrams show that the EE descriptors had positive effect on ERP, and ELUMO, HF, DIP had negative effects, and EHOMO and CCR showed ambiguous effects. Results show that Bayesian regularized BP neural network is of automated regularization parameter selection capability and thus may ensure the excellent generation ability and robustness. This study threw more light on the applicability of electrochemical treatment for the chlorinated aromatic compounds and the analysis on electrochemical reduction mechanism.

Bayes Theorem↗
PubMed2002

NMR and Bayesian regularized neural network regression for impurity determination of 4-aminophenol.

A method for the determination of 4-aminophenol as an impurity in paracetamol (N-(4-hydroxyphenyl)-acetamide) by proton nuclear magnetic resonance ((1)H-NMR) spectroscopy has been developed. The (13)C-satellite from the protons in the ortho position from the hydroxyl group in paracetamol was used as an internal standard, although these peaks interfered with the peaks from the protons in 4-aminophenol. Because of interference in the spectra and non-linearity over a wide calibration range, a Bayesian regularized neural network model was used for calibration. Various kinds of data preprocessing were examined: zero filling, multiplication by a negative exponential function (line broadening), followed by Fourier transformation of the free induction decay (FID). The NMR spectral data were automatically phased and shift-adjusted by means of a genetic algorithm. Multiplicative scatter correction and data compression by wavelets and sequential zeroing of weights variable selection were performed to obtain an optimal calibration model. Neither zero filling of the FID nor line broadening improved the calibration models with regard to error of prediction, so these processes were excluded in the final model. The generated Bayesian regularized network model was evaluated with an independent test set. Four different models with different test sets were constructed to explore the quality of the calibration. The mean error of the optimal calibration model was 25.3 x 10(-6) weight of 4-aminophenol per weight paracetamol. The method is characterized by being relative fast, simple and sufficient sensitive for typical pharmaceutical impurity determinations.

Acetaminophen↗
PubMed2005

Image up-sampling using total-variation regularization with a new observation model.

This paper presents a new formulation of the regularized image up-sampling problem that incorporates models of the image acquisition and display processes. We give a new analytic perspective that justifies the use of total-variation regularization from a signal processing perspective, based on an analysis that specifies the requirements of edge-directed filtering. This approach leads to a new data fidelity term that has been coupled with a total-variation regularizer to yield our objective function. This objective function is minimized using a level-sets motion that is based on the level-set method, with two types of motion that interact simultaneously. A new choice of these motions leads to a stable solution scheme that has a unique minimum. One aspect of the human visual system, perceptual uniformity, is treated in accordance with the linear nature of the data fidelity term. The method was implemented and has been verified to provide improved results, yielding crisp edges without introducing ringing or other artifacts.

Algorithms↗
PubMed1997

Physiological gain leads to high ISI variability in a simple model of a cortical regular spiking cell.

To understand the interspike interval (ISI) variability displayed by visual cortical neurons (Softky & Koch, 1993), it is critical to examine the dynamics of their neuronal integration, as well as the variability in their synaptic input current. Most previous models have focused on the latter factor. We match a simple integrate-and-fire model to the experimentally measured integrative properties of cortical regular spiking cells (McCormick, Connors, Lighthall, & Prince, 1985). After setting RC parameters, the post-spike voltage reset is set to match experimental measurements of neuronal gain (obtained from in vitro plots of firing frequency versus injected current). Examination of the resulting model leads to an intuitive picture of neuronal integration that unifies the seemingly contradictory 1/square root of N and random walk pictures that have previously been proposed. When ISIs are dominated by postspike recovery, 1/square root of N arguments hold and spiking is regular; after the "memory" of the last spike becomes negligible, spike threshold crossing is caused by input variance around a steady state and spiking is Poisson. In integrate-and-fire neurons matched to cortical cell physiology, steady-state behavior is predominant, and ISIs are highly variable at all physiological firing rates and for a wide range of inhibitory and excitatory inputs.

Animals↗
PubMed1980

Three factors predicting irregular versus regular dental attendance: a model fitting to empirical data.

A tentative theory, based upon the results of a survey that was performed in an urbanized village in the Netherlands, and proposing that the (ir)regularity of dental attendance is predicted by 1) dental anxiety, 2) the family dental health pattern and 3) the preference for preservation of the teeth, has been explored with loglinear models (logit approach). It has been shown that dental anxiety in combination with preference for preservation of the teeth is significantly associated with the (ir)regularity, but the family dental health pattern has a modifying effect. The probabilities of being an irregular dental attender were estimated for the levels discernible in the two predictor variables and with the odds of irregular dental attendance corresponding 95% confidence intervals were approximated. The results were discussed and it seems warranted to conclude that (ir)regular dental attendance dependent on the levels of the variables, mentioned above, is predicted more or less accurately. A further exploration of the theory and the variables involved seems worthwhile.

Adolescent↗
PubMedDate not supplied

Performance of a canopy light interception model for conifer shoots, trees and stands.

A hierarchical approach was used to evaluate the behavior of a canopy light interception model using submodels for interception at levels of the shoot, crown and stand. Mean silhouette areas of individual shoots of lodgepole pine (Pinus contorta var. latifolia Engelm.) calculated assuming spherical shoot orientation agreed well with silhouette areas measured with a video projection system. A theoretical mean silhouette to total leaf area ratio (STAR) calculated using measured shoot characteristics and a model of shoot geometry agreed reasonably well with STAR values from measured shoot silhouette and leaf areas, although the range of calculated STAR values was slightly lower than that of the measured values. The shadow areas of tree crowns were underestimated for lodgepole pine; however, a model using regular shoot dispersion in the crown gave better agreement than a model based on random shoot dispersion. The underestimates may have been caused by underestimation either of leaf or branch area for the crowns or of the extinction coefficient. Two equations used to calculate leaf area from sapwood area measurements both underestimated leaf area. Accordingly, there are too many uncertainties to determine whether crown interception is best represented by a random or regular distribution of shoots. Mean canopy transmission in the Engelmann spruce (Picea engelmannii Parry ex Engelm.) stand was estimated very well by a random (Poisson) model of the spatial distribution of trees, whereas, in the lodgepole pine stand, a regular (hexagonal) model gave the best results. The Engelmann spruce stand had less regular tree spacing than the lodgepole pine stand. Taken as a whole, the weakest submodel for calculating canopy interception was the model for individual crown transmission, which underestimated crown shadow areas. However, the problem may be in leaf area estimates rather than in model performance.

Journal Article↗
PubMed2003

Singularities in mixture models and upper bounds of stochastic complexity.

A learning machine which is a mixture of several distributions, for example, a gaussian mixture or a mixture of experts, has a wide range of applications. However, such a machine is a non-identifiable statistical model with a lot of singularities in the parameter space, hence its generalization property is left unknown. Recently an algebraic geometrical method has been developed which enables us to treat such learning machines mathematically. Based on this method, this paper rigorously proves that a mixture learning machine has the smaller Bayesian stochastic complexity than regular statistical models. Since the generalization error of a learning machine is equal to the increase of the stochastic complexity, the result of this paper shows that the mixture model can attain the more precise prediction than regular statistical models if Bayesian estimation is applied in statistical inference.

Bayes Theorem↗
PubMed1998

Lexical representation of gender: a quasiregular domain.

The relationship between gender and word ending in French is a quasiregular one (e.g., most words ending in -ette are feminine, but not all). As such, the gender of low-frequency irregular forms (e.g., squelette, which is masculine) should take longer to classify than low-frequency regular forms according to neural network models. A regularity effect was found in Experiment 1, but it did not interact with word frequency. It was further revealed that there was difficulty in making gender decisions (Experiment 2) and gender verification responses (Experiment 3) to words whose endings were highly informative of gender, but whose associated article was not. These words were place names beginning with a vowel, like Australie, which do not take an indefinite article and whose definite article is ambiguous (1'). How a neural network might handle these results is discussed, and an alternative account is considered whereby there are two potential sources of gender information, lexical and nonlexical, with the latter being used to confirm the former.

Female↗
PubMed1999

Psychosocial correlates of dietary intake: advancing dietary intervention.

Psychosocial variables that predict dietary behavior become important targets for change in nutrition education programs. Psychosocial variables in models with higher predictability provide more effective levers to promote healthy dietary change. A review of the literature on models with psychosocial variables predicting dietary fat and fruit and vegetable consumption revealed generally low predictiveness, R2 < 0.3 (where R2 is the squared multiple correlation of the statistical model). No single theory provided models that regularly out-predicted others. When models predicted narrower categories of behavior (e.g. milk or salad consumption), predictiveness tended to be higher. Substantial problems were revealed in the psychometrics of both the independent and dependent variables. Little theory-based research has been conducted with adolescents, and the few studies done with children had low predictiveness. In order to increase the predictiveness of models, future research should combine variables from several theories, attend to the psychometrics of all variables, and incorporate variables that moderate the relationship of psychosocial to dietary behavior (e.g. genetics of taste, stage in the life course). Refinements on current research would include longitudinal designs and use of non-self-report methods of dietary behavior to supplement the self-report methods. Improved understanding of dietary behavior should lead to more effective dietary behavior change interventions.

Adolescent↗
PubMed2004

Mixed micelles containing sodium oleate: the effect of the chain length and the polar head group.

We have investigated the mixing behavior of binary mixtures of the alkylglucosides (CnG) octyl beta-D-glucoside and decyl D-glucoside in combination with sodium oleate (NaOl), and the amine oxide surfactants (AO) N,N-dimethyldodecylamine oxide, N,N-bis (2-hydroxyethyl)dodecylamine oxide, and 3-lauramidopropyl-N,N-dimethylamine oxide in combination with NaOl. From the equilibrium surface tension measurements, the critical micelle concentration (cmc) data were obtained as functions of the composition. Values of the cmc were analyzed according to both the regular solution model developed by Rubingh for mixed micelles and Maeda's formulation for ionic/nonionic mixed micelles. Two interaction parameters, beta and B1, were estimated from the regular solution model and Maeda's formulation, respectively. For NaOl/CnG mixed systems, a decrease in the hydrocarbon chain length of CnG resulted in a stronger interaction with NaOl from both beta and B1 values. For NaOl/AO mixed systems, the bulkiness of a polar head group of AO surfactants influenced the interaction between NaOl and AO. The dynamic surface tension measurements show that all surface tension values of surfactant solutions examined decreased with the time. We found that the time dependence of surface tension values for NaOl mixed systems was greatly influenced by the presence of NaOl rather than the other component.

Chemical Phenomena↗
PubMed2004

Dense motion estimation using regularization constraints on local parametric models.

This paper presents a method for dense optical flow estimation in which the motion field within patches that result from an initial intensity segmentation is parametrized with models of different order. We propose a novel formulation which introduces regularization constraints between the model parameters of neighboring patches. In this way, we provide the additional constraints for very small patches and for patches whose intensity variation cannot sufficiently constrain the estimation of their motion parameters. In order to preserve motion discontinuities, we use robust functions as a regularization mean. We adopt a three-frame approach and control the balance between the backward and forward constraints by a real-valued direction field on which regularization constraints are applied. An iterative deterministic relaxation method is employed in order to solve the corresponding optimization problem. Experimental results show that the proposed method deals successfully with motions large in magnitude, motion discontinuities, and produces accurate piecewise-smooth motion fields.

Algorithms↗
PubMed1989

[DNA complexes with synthetic oligopeptides: a model for studying the regularity of DNA compactization in vivo].

The electron microscopic data on compactization of DNA at interaction with the synthetic oligopeptides having the trend of beta-structures formation in solutions are summarized. The new types of intramolecular and intermolecular compact structures are described in brief. Sequence of compactization process steps is discussed, the models of DNA packaging in the structures are presented. On the basis of the data presented the general principles of arrangement of the described compact structures are formulated, the mechanisms are proposed for formation of different types of compact particles on the final stage of the process of DNA condensation. Some processes of the genetic material compactization in vivo are discussed in which the proposed mechanisms for compact structures formation may have realization.

DNA↗