Search results for "support"

showing 10 items of 2310 documents

Ultimate Order Statistics-Based Prototype Reduction Schemes

2013

Published version of a chapter in the book: AI 2013: Advances in Artificial Intelligence. Also available from the publisher at: http://dx.doi.org/10.1007/978-3-319-03680-9_42 The objective of Prototype Reduction Schemes (PRSs) and Border Identification (BI) algorithms is to reduce the number of training vectors, while simultaneously attempting to guarantee that the classifier built on the reduced design set performs as well, or nearly as well, as the classifier built on the original design set. In this paper, we shall push the limit on the field of PRSs to see if we can obtain a classification accuracy comparable to the optimal, by condensing the information in the data set into a single tr…

Training setComputer scienceVDP::Mathematics and natural science: 400::Information and communication science: 420::Algorithms and computability theory: 422Order statisticcomputer.software_genreSupport vector machineData setBayes' theoremclassification using Order Statistics (OS)CMOSPrototype Reduction SchemesData miningmoments of OSClassifier (UML)computerParametric statistics
researchProduct

2004

This paper presents the use of Support Vector Machines (SVMs) for prediction and analysis of antisense oligonucleotide (AO) efficacy. The collected database comprises 315 AO molecules including 68 features each, inducing a problem well-suited to SVMs. The task of feature selection is crucial given the presence of noisy or redundant features, and the well-known problem of the curse of dimensionality. We propose a two-stage strategy to develop an optimal model: (1) feature selection using correlation analysis, mutual information, and SVM-based recursive feature elimination (SVM-RFE), and (2) AO prediction using standard and profiled SVM formulations. A profiled SVM gives different weights to …

Training setCorrelation coefficientMean squared errorComputer sciencebusiness.industryApplied MathematicsFeature selectionMutual informationMachine learningcomputer.software_genreBiochemistryComputer Science ApplicationsSupport vector machineStructural BiologyFeature (machine learning)Artificial intelligencebusinessMolecular BiologycomputerEnergy (signal processing)Curse of dimensionalityBMC Bioinformatics
researchProduct

Transformation of the Software Testing Glossary into a Browsable Concept Map

2014

Authors propose a transformation method of the glossary “Standard glossary of terms used in Software Testing” created by ISTQB document into a basic concept map. By applying natural language processing techniques and analyzing the discovered relations between concepts the most essential aspects of the software testing domain are elicited and integrated. As the result a browsable concept map is created. Browsable concept map can be used as a learning support tool.

Transformation (function)GlossarySoftware testingComputer scienceProgramming languagebusiness.industryConcept mapLearning supportArtificial intelligencecomputer.software_genrebusinesscomputerDomain (software engineering)
researchProduct

Patients' sex and emotional support as predictors of death and clinical deterioration in the Waiting for a New Heart Study: results from the 1-year f…

2011

Context—Little is known about the role of patient's sex and emotional support in the prognosis of heart transplant candidates.Objective—To examine patient's sex and emotional support as predictors of outcomes in the Waiting for a New Heart Study.Design, Setting, and Participants—The Waiting for a New Heart Study is a prospective observational study of 318 patients (18% female) newly added to the waiting list for a heart transplant. Demographic, medical, psychosocial characteristics (including social support [ENRICHD Social Support Index; high vs low support]) were assessed at the time of wait-listing.Main Outcomes—Time until death/delisting due to deteriorated health, considering competing …

Transplantationmedicine.medical_specialtyPediatricsbusiness.industryProportional hazards modelMEDLINESurgeryTransplantationSocial supportMedicineObservational studybusinessProspective cohort studySurvival ratePsychosocialProgress in Transplantation
researchProduct

Virtual meetings and social isolation in COVID-19 times: transposable barriers

2020

Transposable element2019-20 coronavirus outbreakmedicine.medical_specialtyCoronavirus disease 2019 (COVID-19)Pneumonia ViralRC435-571MEDLINEOnline SystemsUser-Computer InterfaceSocial supportmedicineHumansSociologySocial isolationPandemicsPsychiatryInternetbusiness.industryCOVID-19Social SupportGeneral MedicineCongresses as Topicmedicine.diseasePsychiatry and Mental healthPneumoniaEditorialSocial IsolationFamily medicineThe Internetmedicine.symptomCoronavirus Infectionsbusiness
researchProduct

A new rotational integral formula for intrinsic volumes in space forms

2010

A new rotational version of Crofton's formula is derived for the intrinsic volumes of a domain Y in a space form. More precisely, a functional is defined on the intersection between Y and a totally geodesic submanifold (plane) through a fixed point, such that the rotational average of this functional is equal to the intrinsic volumes of Y. Particular cases of interest in stereology are considered for the Euclidean case. © 2009 Elsevier Inc. All rights reserved.

TransversalityPlane (geometry)Space formApplied MathematicsStereologyMathematical analysisTransversalitySpace formFixed pointSubmanifoldSpace (mathematics)Integral geometryIntersectionMathematics::Metric GeometrySupport setIntegral geometryIntrinsic volumeRotational integralMathematics
researchProduct

Normal and Abnormal Tissue Classification in Positron Emission Tomography Oncological Studies

2018

Positron Emission Tomography (PET) imaging is increasingly used in radiotherapy environment as well as for staging and assessing treatment response. The ability to classify PET tissues, as normal versus abnormal tissues, is crucial for medical analysis and interpretation. For this reason, a system for classifying PET area is implemented and validated. The proposed classification is carried out using k-nearest neighbor (KNN) method with the stratified K-Fold Cross-Validation strategy to enhance the classifier reliability. A dataset of eighty oncological patients are collected for system training and validation. For every patient, lesion (abnormal tissue) and background (normal tissue around …

Treatment responsepositron emission tomographyK-nearest neighborKernel support vector machineComputer scienceNormal tissueK-Fold cross-validation030218 nuclear medicine & medical imagingk-nearest neighbors algorithmLesion03 medical and health sciences0302 clinical medicinetissue classificationmedicineRadiation treatment planningFuzzy C-Mean1707Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazionimedicine.diagnostic_testbusiness.industryPattern recognitionComputer Graphics and Computer-Aided DesignPredictive valueSupport vector machineFuzzy C-MeansPositron emission tomography030220 oncology & carcinogenesisComputer Vision and Pattern RecognitionArtificial intelligencemedicine.symptombusinessPattern Recognition and Image Analysis
researchProduct

Prediction of lncRNA-Disease Associations from Tripartite Graphs

2021

The discovery of novel lncRNA-disease associations may provide valuable input to the understanding of disease mechanisms at lncRNA level, as well as to the detection of biomarkers for disease diagnosis, treatment, prognosis and prevention. Unfortunately, due to costs and time complexity, the number of possible disease-related lncRNAs verified by traditional biological experiments is very limited. Computational approaches for the prediction of potential disease-lncRNA associations can effectively decrease time and cost of biological experiments. We propose an approach for the prediction of lncRNA-disease associations based on neighborhood analysis performed on a tripartite graph, built upon …

Tripartite graphsDecision support systemComputer scienceDisease mechanismsIdentification (biology)lncRNA-disease associations predictionDiseaseComputational biologyTime complexityGraphDecision support
researchProduct

From tungsten hexacarbonyl adsorption on TiO2(1 1 0) surface to supported tungsten oxide phases.

2008

Abstract Synchrotron-based photoemission spectroscopies were used to study the adsorption of tungsten hexacarbonyl on (1 1 0) TiO 2 surfaces: experiments using W4f and Ti2p intensities variations show that, at 140 K, the hexacarbonyl growth proceeds via a layer-by-layer mode. Moreover, it was evidenced using both core levels and valence band experiments that, after back to room temperature, W(CO) 6 desorbs without significant decomposition. However, low energy (500 eV) ion (Ar + ) irradiation can allow partial decomposition of tungsten hexacarbonyl molecules leading to sub-carbonyl tungsten molecules. The bonding of sub-carbonyl species to the TiO 2 surface was then stronger than the one of…

Tungsten hexacarbonylMaterials scienceAnnealing (metallurgy)Supported nanostructureschemistry.chemical_element02 engineering and technologyGrowthTungsten010402 general chemistryPhotochemistry01 natural sciencesMetalchemistry.chemical_compoundAdsorptionX-ray photoelectron spectroscopyDesorptionTiO2Physical and Theoretical ChemistrySpectroscopyRadiationAtmospheric temperature range021001 nanoscience & nanotechnologyCondensed Matter PhysicsAtomic and Molecular Physics and Optics0104 chemical sciencesElectronic Optical and Magnetic MaterialsPhotoelectron spectroscopychemistryvisual_artvisual_art.visual_art_mediumTungsten hexacarbonyl0210 nano-technology
researchProduct

Corrigendum to “Off-line control of the postprandial glycemia in type 1 diabetes patients by a fuzzy logic decision support” [Expert Systems with App…

2012

Type 1 diabetesDecision support systembusiness.industryControl (management)General Engineeringmedicine.diseasecomputer.software_genreFuzzy logicExpert systemComputer Science ApplicationsPostprandialArtificial IntelligencemedicineArtificial intelligencebusinesscomputerOff lineMathematicsExpert Systems with Applications
researchProduct