Search results for "predictive modelling."

showing 10 items of 22 documents

Complementary frailty and mortality prediction models on older patients as a tool for assessing palliative care needs.

2021

Background: Palliative care (PC) has demonstrated benefits for life-limiting illnesses. Cancer patients have mainly accessed these services, but there is growing consensus about the importance of promoting access for patients with non-malignant disease. Bad survival prognosis and patient9s frailty are usual dimensions to decide PC inclusion. Objectives: The main aim of this work is to design and evaluate three quantitative models based on machine learning approaches to predict frailty and mortality on older patients in the context of supporting palliative care decision making: one-year mortality, survival regression and one-year frailty classification. Methods: The dataset used in this stud…

GerontologyPalliative careReceiver operating characteristicFrailtybusiness.industryPalliative CareHealth InformaticsContext (language use)Regression analysisRegressionCorrelationROC CurveArea Under CurveMedicineHumansGradient boostingNeural Networks ComputerbusinessPredictive modellingAgedHealth informatics journal
researchProduct

On the relationship between some production parameters and a vegetation index in viticulture

2013

The use and timing of many agronomical practices such as the scheduling of irrigation and harvesting are dependent on accurate vineyard sampling of qualitative and productive parameters. Crop forecasting also depends on the representativeness of vineyard samples during the whole phenological period. This manuscript summarizes the last two years of precision viticulture in Sicily (Italy); agronomic campaigns were carried out in 2012 and 2013 within the "Tenute Rapitalà" and "Donnafugata" farms. Normalized Difference Vegetation Index derived from satellite images (RapidEye) acquired at berry set, pre-veraison and ripening phenological stages (occurred at June, July and August respectively) ha…

HydrologyIrrigationPhenologySettore ICAR/02 - Costruzioni Idrauliche E Marittime E IdrologiaForestryVineyardNormalized Difference Vegetation IndexSettore AGR/03 - Arboricoltura Generale E Coltivazioni ArboreeGeographyVegetation indexPrecision viticultureSettore AGR/08 - Idraulica Agraria E Sistemazioni Idraulico-ForestaliCultivarViticultureAnthocyanin contentPredictive modellingSugar contentSettore ICAR/06 - Topografia E CartografiaPrecision viticulture
researchProduct

Basis of predictive mycology.

2005

Abstract For over 20 years, predictive microbiology focused on food-pathogenic bacteria. Few studies concerned modelling fungal development. On one hand, most of food mycologists are not familiar with modelling techniques; on the other hand, people involved in modelling are developing tools dedicated to bacteria. Therefore, there is a tendency to extend the use of models that were developed for bacteria to moulds. However, some mould specificities should be taken into account. The use of specific models for predicting germination and growth of fungi was advocated previously [ Dantigny, P., Guilmart, A., Bensoussan, M., 2003. Basis of predictive mycology. In Proceedings of the 4th Internatio…

Management scienceEcologyFungiTemperatureGeneral MedicineMycologyBiologyMicrobiologyModels BiologicalKineticsSpecies SpecificityPredictive Value of TestsMycologyFood MicrobiologyPredictive microbiologyPredictive modellingFood ScienceInternational journal of food microbiology
researchProduct

Data fusion analysis applied to different climate change models: An application to the energy consumptions of a building office

2019

Abstract The paper aims to achieve the modelling of climate change effects on heating and cooling in the building sector, through the use of the available Intergovernmental Panel on Climate Change forecasted data. Data from several different climate models will be fused with regards to mean air temperature, wind speed and horizontal solar radiation. Several climatic models data were analysed ranging from January 2006 to December 2100. Rather than considering each model in isolation, we propose a data fusion approach for providing a robust combined model for morphing an existing weather data file. The final aim is simulating future energy use for heating and cooling of a reference building a…

Meteorology020209 energyMechanical Engineering0211 other engineering and technologiesClimate change02 engineering and technologyBuilding and ConstructionOverfittingSensor fusionWind speedData setRobustness (computer science)021105 building & construction0202 electrical engineering electronic engineering information engineeringEnvironmental scienceClimate modelClimate change Building simulation Heating and cooling Data fusion IPCC Regression Elastic netElectrical and Electronic EngineeringPredictive modellingCivil and Structural Engineering
researchProduct

QSAR Analysis of Hypoglycemic Agents Using the Topological Indices

2001

The molecular topology model and discriminant analysis have been applied to the prediction of some pharmacological properties of hypoglycemic drugs using multiple regression equations with their statistical parameters. Regression analysis showed that the molecular topology model predicts these properties. The corresponding stability (cross-validation) studies performed on the selected prediction models confirmed the goodness of the fits. The method used for hypoglycemic activity selection was a linear discriminant analysis (LDA). We make use of the pharmacological distribution diagrams (PDDs) as a visualizing technique for the identification and selection of new hypoglycemic agents, and we …

Quantitative structure–activity relationshipbusiness.industryStatistical parameterRegression analysisPattern recognitionGeneral ChemistryMachine learningcomputer.software_genreLinear discriminant analysisStability (probability)Computer Science ApplicationsComputational Theory and MathematicsLinear regressionArtificial intelligencebusinesscomputerPredictive modellingSelection (genetic algorithm)Information SystemsMathematics
researchProduct

A Comprehensive Check of Usle-Based Soil Loss Prediction Models at the Sparacia (South Italy) Site

2020

At first, in this paper a general definition of the event rainfall-runoff erosivity factor for the USLE-based models, REFe = (QR)b1(EI30)b2, in which QR is the event runoff coefficient, EI30 is the single-storm erosion index and b1 and b2 are coefficients, was introduced. The rainfall-runoff erosivity factors of the USLE (b1 = 0, b2 = 1), USLE-M (b1 = b2 = 1), USLE-MB (b1 ≠ 1, b2 = 1), USLE-MR (b1 = 1, b2 ≠ 1), USLE-MM (b1 = b2 ≠ 1) and USLE-M2 (b1 ≠ b2 ≠ 1) can be defined using REFe. Then, the different expressions of REFe were simultaneously tested against a dataset of normalized bare plot soil losses, AeN, collected at the Sparacia (south Italy) site. As expected, the poorest AeN predict…

Runoff coefficientUSLE-type erosion modelsSoil lossSoil loss predictionStatisticsExponentEvent soil loSoil erosionSettore AGR/08 - Idraulica Agraria E Sistemazioni Idraulico-ForestaliPredictive modellingPlot (graphics)MathematicsEvent (probability theory)
researchProduct

Geospatial modelling and map analysis allowed measuring regression of the upper limit of Posidonia oceanica seagrass meadows under human pressure

2018

Abstract Marine coastal ecosystems are facing structural and functional changes due to the increasing human footprint worldwide, and the assessment of their long-term changes becomes particularly challenging. Measures of change can be done by comparing the observed ecosystem status to a purposely defined reference condition. In this paper, a geospatial modelling approach based on 2D mapping and morphodynamic data was used to predict the natural position of the upper limit (i.e., the landward continuous front) of Posidonia oceanica seagrass meadows settled on soft bottom. This predictive model, formerly developed at the regional spatial scale, was here applied for the first time at the Medit…

Settore BIO/07 - Ecologia0106 biological sciencesMediterranean climateGeospatial analysis010504 meteorology & atmospheric sciencesMediterranean sea Morphodynamic sPosidonia oceanica Predictive modelling Reference conditions SeagrassAquatic ScienceOceanographycomputer.software_genre01 natural sciencesMorphodynamicZoologíaEcosystemSeagrasssPosidonia oceanica0105 earth and related environmental sciencesbiology010604 marine biology & hydrobiologySeagraPredictive modellingFragmentation (computing)Posidonia oceanicaReference conditionsbiology.organism_classificationSeagrass;Predictive modelling;Reference conditions;Morphodynamics;Posidonia oceanica;Mediterranean seaMorphodynamicsRegressionSeagrassPosidonia oceanicaSettore BIO/03 - Botanica Ambientale E ApplicataMediterranean seaSpatial ecologyEnvironmental scienceReference conditionPhysical geographycomputerEstuarine, Coastal and Shelf Science
researchProduct

Probabilité d'apparition d'un phénomène parasitaire et choix de modèles de régression logistique

2007

Epidemiological processes are now using spatial statistics and modelling tools. The main objective of most health risks studies consists in identifying potential contamination sources and factors capable of explaining their localization. Health data often prove binary (typically presence/absence) and specific methods such as binary logistic regression have to be used. This method's output consists in a probability for the pathogen of interest. A posterior classification of each sample is then conducted using a probability threshold. The method used to maximize this threshold is called the ROC curve which consists in giving a representation of the behaviour of the model and then to choose th…

Spatial epidemiology Binary logistic regression ROC curves Predictive modelling[SHS.GEO] Humanities and Social Sciences/Geography[SHS.GEO]Humanities and Social Sciences/GeographyÉpidémiologie spatiale Régression logistique binaire Courbes ROC Modélisation prédictive[ SHS.GEO ] Humanities and Social Sciences/Geography
researchProduct

Towards the improvement of food flavour analysis: Modelling chemical and sensory data and expert knowledge integration

2019

International audience

[SDV.AEN] Life Sciences [q-bio]/Food and Nutritionmixture of odorantsfood flavorexpert knowledgefuzzy logicpredictive modelling[SDV.AEN]Life Sciences [q-bio]/Food and NutritionComputingMilieux_MISCELLANEOUSolfaction
researchProduct

Contextes spatiaux et transformation du système de peuplement: approche comparative et prédictive

2011

We propose a method to identify and simulate settling choices Roman rural settlements using predictive modeling, based on the method developed in the 1990s by F.-P. Tourneux within the Archaeomedes project to characterize and compare the environmental contexts of Roman rural settlements in several areas of southern France. We have developped the model for three regions with very different topographical conditions : The Vaunage region (Languedoc, France), the Argens-Maures region (Provence, France) and Zuid-Limburg (Netherlands).

[SHS.ARCHEO] Humanities and Social Sciences/Archaeology and Prehistoryspatial analysis[SHS.ARCHEO]Humanities and Social Sciences/Archaeology and PrehistoryLimbourgmodélisation prédictiveGISSIGAntiquitéantiquity[ SHS.ARCHEO ] Humanities and Social Sciences/Archaeology and PrehistoryLanguedocVarpredictive modellinganalyse spatiale
researchProduct