SEARCH · PubMed Health

Results for “Computing Methodologies”

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 235 records · Page 13Linked to original sources

PubMed2005

Electroactive polymer-based devices for e-textiles in biomedicine.

This paper describes the early conception and latest developments of electroactive polymer (EAP)-based sensors, actuators, electronic components, and power sources, implemented as wearable devices for smart electronic textiles (e-textiles). Such textiles, functioning as multifunctional wearable human interfaces, are today considered relevant promoters of progress and useful tools in several biomedical fields, such as biomonitoring, rehabilitation, and telemedicine. After a brief outline on ongoing research and the first products on e-textiles under commercial development, this paper presents the most highly performing EAP-based devices developed by our lab and other research groups for sensing, actuation, electronics, and energy generation/storage, with reference to their already demonstrated or potential applicability to electronic textiles.

Biomedical Engineering↗

PubMed2005

Organic field effect transistors for textile applications.

In this paper, several issues concerning the development of textiles endowed with electronic functions will be discussed. In particular, issues concerning materials, structures, electronic models, and the mechanical constraints due to textile technologies will be detailed. The idea starts from an already developed organic field-effect transistor that is realized on a flexible film that can be applied, after the assembly, on whatever kind of substrate, in particular, on textiles. This could pave the way to a variety of applications aimed to conjugate the favorable mechanical properties of textiles with the electronic functions of transistors. Furthermore, a possible perspective for the developments of organic sensors based on this structure are described.

Clothing↗

PubMed2005

Smooth function approximation using neural networks.

An algebraic approach for representing multidimensional nonlinear functions by feedforward neural networks is presented. In this paper, the approach is implemented for the approximation of smooth batch data containing the function's input, output, and possibly, gradient information. The training set is associated to the network adjustable parameters by nonlinear weight equations. The cascade structure of these equations reveals that they can be treated as sets of linear systems. Hence, the training process and the network approximation properties can be investigated via linear algebra. Four algorithms are developed to achieve exact or approximate matching of input-output and/or gradient-based training sets. Their application to the design of forward and feedback neurocontrollers shows that algebraic training is characterized by faster execution speeds and better generalization properties than contemporary optimization techniques.

Algorithms↗

PubMed2005

A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation.

This paper presents a new sequential learning algorithm for radial basis function (RBF) networks referred to as generalized growing and pruning algorithm for RBF (GGAP-RBF). The paper first introduces the concept of significance for the hidden neurons and then uses it in the learning algorithm to realize parsimonious networks. The growing and pruning strategy of GGAP-RBF is based on linking the required learning accuracy with the significance of the nearest or intentionally added new neuron. Significance of a neuron is a measure of the average information content of that neuron. The GGAP-RBF algorithm can be used for any arbitrary sampling density for training samples and is derived from a rigorous statistical point of view. Simulation results for bench mark problems in the function approximation area show that the GGAP-RBF outperforms several other sequential learning algorithms in terms of learning speed, network size and generalization performance regardless of the sampling density function of the training data.

Algorithms↗

PubMed2005

A flexible coefficient smooth transition time series model.

In this paper, we consider a flexible smooth transition autoregressive (STAR) model with multiple regimes and multiple transition variables. This formulation can be interpreted as a time varying linear model where the coefficients are the outputs of a single hidden layer feedforward neural network. This proposal has the major advantage of nesting several nonlinear models, such as, the self-exciting threshold autoregressive (SETAR), the autoregressive neural network (AR-NN), and the logistic STAR models. Furthermore, if the neural network is interpreted as a nonparametric universal approximation to any Borel measurable function, our formulation is directly comparable to the functional coefficient autoregressive (FAR) and the single-index coefficient regression models. A model building procedure is developed based on statistical inference arguments. A Monte Carlo experiment showed that the procedure works in small samples, and its performance improves, as it should, in medium size samples. Several real examples are also addressed.

Algorithms↗

PubMed2006

Analysis and simulation of a mixed-mode neuron architecture for sensor conditioning.

The design, analysis, and system simulation of an adaptive processor based on a current-mode mixed analog-digital circuit is presented. The processor consists of a mixed four-quadrant multiplier and a current conveyor that performs the nonlinearity. Schematics, circuit parameters, and a high-level model are shown. The results achieved when applying this processor model to conditioning several sensor types are discussed.

Algorithms↗

PubMed2006

Feed-forward support vector machine without multipliers.

In this letter, we propose a coordinate rotation digital computer (CORDIC)-like algorithm for computing the feed-forward phase of a support vector machine (SVM) in fixed-point arithmetic, using only shift and add operations and avoiding resource-consuming multiplications. This result is obtained thanks to a hardware-friendly kernel, which greatly simplifies the SVM feed-forward phase computation and, at the same time, maintains good classification performance respect to the conventional Gaussian kernel.

Algorithms↗

PubMed2006

Generalized core vector machines.

Kernel methods, such as the support vector machine (SVM), are often formulated as quadratic programming (QP) problems. However, given m training patterns, a naive implementation of the QP solver takes O(m3) training time and at least O(m2) space. Hence, scaling up these QPs is a major stumbling block in applying kernel methods on very large data sets, and a replacement of the naive method for finding the QP solutions is highly desirable. Recently, by using approximation algorithms for the minimum enclosing ball (MEB) problem, we proposed the core vector machine (CVM) algorithm that is much faster and can handle much larger data sets than existing SVM implementations. However, the CVM can only be used with certain kernel functions and kernel methods. For example, the very popular support vector regression (SVR) cannot be used with the CVM. In this paper, we introduce the center-constrained MEB problem and subsequently extend the CVM algorithm. The generalized CVM algorithm can now be used with any linear/nonlinear kernel and can also be applied to kernel methods such as SVR and the ranking SVM. Moreover, like the original CVM, its asymptotic time complexity is again linear in m and its space complexity is independent of m. Experiments show that the generalized CVM has comparable performance with state-of-the-art SVM and SVR implementations, but is faster and produces fewer support vectors on very large data sets.

Algorithms↗

PubMed2006

Improvements of complex-valued Hopfield associative memory by using generalized projection rules.

In this letter, new design methods for the complex-valued multistate Hopfield associative memories (CVHAMs) are presented. We show that the well-known projection rule proposed by Personnaz et al. can be generalized to complex domain such that the weight matrix of the CVHAM can be designed by using a simple and effective method. The stability of the proposed CVHAM is analyzed by using energy function approach which shows that in synchronous update mode the proposed model is guaranteed to converge to a fixed point from any given initial state. Moreover, the projection geometry of the generalized projection rule (GPR) is discussed. In order to enhance the recall capability, a strategy of eliminating the spurious memories is also reported. The validity and the performance of the proposed methods are investigated by computer simulation.

Algorithms↗

PubMed2004

A probabilistic active support vector learning algorithm.

The paper describes a probabilistic active learning strategy for support vector machine (SVM) design in large data applications. The learning strategy is motivated by the statistical query model. While most existing methods of active SVM learning query for points based on their proximity to the current separating hyperplane, the proposed method queries for a set of points according to a distribution as determined by the current separating hyperplane and a newly defined concept of an adaptive confidence factor. This enables the algorithm to have more robust and efficient learning capabilities. The confidence factor is estimated from local information using the k nearest neighbor principle. The effectiveness of the method is demonstrated on real-life data sets both in terms of generalization performance, query complexity, and training time.

Algorithms↗

PubMed2005

Feature space interpretation of SVMs with indefinite kernels.

Kernel methods are becoming increasingly popular for various kinds of machine learning tasks, the most famous being the support vector machine (SVM) for classification. The SVM is well understood when using conditionally positive definite (cpd) kernel functions. However, in practice, non-cpd kernels arise and demand application in SVMs. The procedure of "plugging" these indefinite kernels in SVMs often yields good empirical classification results. However, they are hard to interpret due to missing geometrical and theoretical understanding. In this paper, we provide a step toward the comprehension of SVM classifiers in these situations. We give a geometric interpretation of SVMs with indefinite kernel functions. We show that such SVMs are optimal hyperplane classifiers not by margin maximization, but by minimization of distances between convex hulls in pseudo-Euclidean spaces. By this, we obtain a sound framework and motivation for indefinite SVMs. This interpretation is the basis for further theoretical analysis, e.g., investigating uniqueness, and for the derivation of practical guidelines like characterizing the suitability of indefinite SVMs.

Algorithms↗

PubMed2006

Parallelization of multicategory support vector machines (PMC-SVM) for classifying microarray data.

BACKGROUND: Multicategory Support Vector Machines (MC-SVM) are powerful classification systems with excellent performance in a variety of data classification problems. Since the process of generating models in traditional multicategory support vector machines for large datasets is very computationally intensive, there is a need to improve the performance using high performance computing techniques. RESULTS: In this paper, Parallel Multicategory Support Vector Machines (PMC-SVM) have been developed based on the sequential minimum optimization-type decomposition method for support vector machines (SMO-SVM). It was implemented in parallel using MPI and C++ libraries and executed on both shared memory supercomputer and Linux cluster for multicategory classification of microarray data. PMC-SVM has been analyzed and evaluated using four microarray datasets with multiple diagnostic categories, such as different cancer types and normal tissue types. CONCLUSION: The experiments show that the PMC-SVM can significantly improve the performance of classification of microarray data without loss of accuracy, compared with previous work.

Algorithms↗

PubMed1998

[Biological calculation methods and their application in pharmaceutical science].

This article gives an introduction to certain mathematical methods, that were developed with biological processes as model. Three methods are described: clustering and the more recently developed genetic algorithms and neural nets. Mainly the last two methods were applied first outside the medical and biological domain but are now used also in the medical and pharmaceutical sciences. There are many applications in the drug discovery field, but these methods are also becoming increasingly important in other domains of the pharmaceutical sciences (such as pharmaceutical technologies).

Algorithms↗

PubMedDate not supplied

[ECG compression method by using multiple polynomial modelling: comparison with wavelet-changing technique].

The proposed ECG compression combined two approaches, ECG beat alignment and polynomial modeling. QRS complexes are firstly detected then aligned in order to reduce high frequency changes from beat to beat. These changes are modeled by means a polynomial projection. ECG from MIT-BIH database are used to evaluate the performances of the proposed technique. A comparison with the wavelet approach is performed by means the compression ratio (CR) versus the RRD curve.

Algorithms↗

PubMed1998

Object-oriented analysis and design: a methodology for modeling the computer-based patient record.

The article highlights the importance of an object-oriented analysis and design (OOAD) methodology for the computer-based patient record (CPR) in the military environment. Many OOAD methodologies do not adequately scale up, allow for efficient reuse of their products, or accommodate legacy systems. A methodology that addresses these issues is formulated and used to demonstrate its applicability in a large-scale health care service system. During a period of 6 months, a team of object modelers and domain experts formulated an OOAD methodology tailored to the Department of Defense Military Health System and used it to produce components of an object model for simple order processing. This methodology and the lessons learned during its implementation are described. This approach is necessary to achieve broad interoperability among heterogeneous automated information systems.

Abstracting and Indexing↗

PubMed2001

Computational expansion of genetic networks.

We present a new methodology for computational analysis of gene and protein networks. The aim is to generate new educated hypotheses on gene functions and on the logic of the biological network circuitry, based on gene expression profiles. The framework supports the incorporation of biologically motivated network constraints and rules to improve specificity. Since current data is insufficient for de-novo reconstruction, the method receives as input a known pathway core and suggests likely expansions to it. Network modeling is combinatorial, yet data can be probabilistic. At the heart of the approach are a fitness function which estimates the quality of suggested network expansions given the core and the data, and a specificity measure of the expansions. The approach has been implemented in an interactive software tool called GENESYS. We report encouraging results in preliminary analysis of yeast ergosterol pathway based on transcription profiles. In particular, the analysis suggests a novel ergosterol transcription factor.

Algorithms↗

PubMedDate not supplied

Evaluation of three methodologies for assessing work activity during computer use.

The overall goal of this study was to evaluate three separate methodologies for gathering work activity information among computer users. These methodologies included worker self-report, work sampling, and activity monitoring. A repeated measures design was employed whereby data were collected simultaneously on each subject (n = 51) across three consecutive workdays. Exposure information gathered included keying time, mouse usage, and time spent performing various work tasks (i.e., writing, proofreading, handling documents). Subjects were recruited to represent a wide range of keyboard activity and mouse usage. The study found that worker self-reports overestimated actual keyboard usage by a factor of approximately 1.5 for workers using the keyboard an average of 4 hours per day to a factor of 4 for workers using the keyboard an average of 30 min per day. On average, there was an approximate twofold difference between worker self-reported keying time and that obtained via activity monitoring and work sampling. This trend was similar with regard to time spent using the computer mouse. Worker self-reported mouse usage was approximately twofold higher than that obtained via activity monitoring or work sampling. Self-reported exposure information not only resulted in different estimates, but showed greater variance compared with the other methodologies. The results of this study suggest that the use of worker self-reported exposure information on keying time and mouse usage may not represent an accurate account of time spent performing these tasks. In the context of epidemiological studies work sampling and/or activity monitoring would be more suitable methodologies for obtaining such information.

Adult↗

PubMed2007

Computational alanine scanning mutagenesis--an improved methodological approach.

Alanine scanning mutagenesis of protein-protein interfacial residues can be applied to a wide variety of protein complexes to understand the structural and energetic characteristics of the hot-spots. Binding free energies have been estimated with reasonable accuracy with empirical methods, such as Molecular Mechanics/Poisson-Boltzmann surface area (MM-PBSA), and with more rigorous computational approaches like Free Energy Perturbation (FEP) and Thermodynamic Integration (TI). The main objective of this work is the development of an improved methodological approach, with less computational cost, that predicts accurately differences in binding free energies between the wild-type and alanine mutated complexes (DeltaDeltaG(binding)). The method was applied to three complexes, and a mean unsigned error of 0.80 kcal/mol was obtained in a set of 46 mutations. The computational method presented here achieved an overall success rate of 80% and an 82% success rate in residues for which alanine mutation causes an increase in the binding free energy > 2.0 kcal/mol (warm- and hot-spots). This fully atomistic computational methodological approach consists in a computational Molecular Dynamics simulation protocol performed in a continuum medium using the Generalized Born model. A set of three different internal dielectric constants, to mimic the different degree of relaxation of the interface when different types of amino acids are mutated for alanine, have to be used for the proteins, depending on the type of amino acid that is mutated. This method permits a systematic scanning mutagenesis of protein-protein interfaces and it is capable of anticipating the experimental results of mutagenesis, thus guiding new experimental investigations.

Alanine↗