Search results for "feature"

showing 10 items of 4091 documents

Machine learning for mortality analysis in patients with COVID-19

2020

This paper analyzes a sample of patients hospitalized with COVID-19 in the region of Madrid (Spain). Survival analysis, logistic regression, and machine learning techniques (both supervised and unsupervised) are applied to carry out the analysis where the endpoint variable is the reason for hospital discharge (home or deceased). The different methods applied show the importance of variables such as age, O2 saturation at Emergency Rooms (ER), and whether the patient comes from a nursing home. In addition, biclustering is used to globally analyze the patient-drug dataset, extracting segments of patients. We highlight the validity of the classifiers developed to predict the mortality, reaching…

feature importanceComputer scienceHealth Toxicology and MutagenesisPneumonia ViralDecision treelcsh:MedicineSample (statistics)Machine learningcomputer.software_genreLogistic regressionArticlesurvival analysisBiclustering03 medical and health sciencesBetacoronavirus0302 clinical medicineMachine learningRisk of mortalitygraphical modelsHumans030212 general & internal medicineGraphical modelPandemicsSurvival analysisInformática0303 health sciences030306 microbiologybusiness.industrySARS-CoV-2Decision Treeslcsh:RPublic Health Environmental and Occupational HealthCOVID-19Decision ruleSurvival analysisFeature importancemachine learningSpainArtificial intelligenceGraphical modelsbusinessCoronavirus Infectionscomputer
researchProduct

Exploiting Data Analytics and Deep Learning Systems to Support Pavement Maintenance Decisions

2021

Road networks are critical infrastructures within any region and it is imperative to maintain their conditions for safe and effective movement of goods and services. Road Management, therefore, plays a key role to ensure consistent efficient operation. However, significant resources are required to perform necessary maintenance activities to achieve and maintain high levels of service. Pavement maintenance can typically be very expensive and decisions are needed concerning planning and prioritizing interventions. Data are key towards enabling adequate maintenance planning but in many instances, there is limited available information especially in small or under-resourced urban road authorit…

feature importancepavement management systemComputer science0211 other engineering and technologiespavement maintenance decision02 engineering and technologypavement management systemslcsh:Technologylcsh:ChemistryGoods and services021105 building & construction0502 economics and business11. SustainabilitySettore ICAR/04 - Strade Ferrovie Ed AeroportiGeneral Materials Scienceroad asset databasesInstrumentationlcsh:QH301-705.5Fluid Flow and Transfer Processes050210 logistics & transportationbusiness.industryLevel of servicelcsh:TProcess Chemistry and TechnologyDeep learning05 social sciencesGeneral EngineeringPavement managementdeep learningTimelinedata mininglcsh:QC1-999Computer Science Applicationsroad asset databaseWorkflowRisk analysis (engineering)lcsh:Biology (General)lcsh:QD1-999lcsh:TA1-2040Key (cryptography)Settore ICAR/17 - DisegnoArtificial intelligencepavement maintenance decisionsbusinesslcsh:Engineering (General). Civil engineering (General)Predictive modellinglcsh:PhysicsApplied Sciences
researchProduct

A Curvature Based Method for Blind Mesh Visual Quality Assessment Using a General Regression Neural Network

2016

International audience; No-reference quality assessment is a challenging issue due to the non-existence of any information related to the reference and the unknown distortion type. The main goal is to design a computational method to objectively predict the human perceived quality of a distorted mesh and deal with the practical situation when the reference is not available. In this work, we design a no reference method that relies on the general regression neural network (GRNN). Our network is trained using the mean curvature which is an important perceptual feature representing the visual aspect of a 3D mesh. Relatively to the human subjective scores, the trained network successfully asses…

feature learning[ INFO.INFO-TS ] Computer Science [cs]/Signal and Image ProcessingComputer sciencemedia_common.quotation_subjectFeature extractiondistorted meshGRNNmean curvature02 engineering and technologyMachine learningcomputer.software_genreCurvaturevisual aspect representation[INFO.INFO-TS]Computer Science [cs]/Signal and Image ProcessingDistortioncomputational method0202 electrical engineering electronic engineering information engineeringFeature (machine learning)computational geometrymean opinion scoresQuality (business)Polygon meshmedia_commonArtificial neural networkbusiness.industrycompetitive scores Author Keywords Blind mesh visual quality assessmentperceptual feature020207 software engineeringregression analysis INSPEC: Non-Controlled Indexing curvature based methodblind mesh visual quality assessmentno-reference quality assessmentvisual qualityVisualizationgeneral regression neural network traininggeneral regression neural networkmesh generationneural netssubject scoreshuman perceived quality predictionhuman subjective scores020201 artificial intelligence & image processinglearning (artificial intelligence)Artificial intelligencepredicted objective scoresbusiness3D meshcomputer
researchProduct

Robust Selective Stereo SLAM without Loop Closure and Bundle Adjustment

2013

This paper presents a novel stereo SLAM framework, where a robust loop chain matching scheme for tracking keypoints is combined with an effective frame selection strategy. The proposed approach, referred to as selective SLAM (SSLAM), relies on the observation that the error in the pose estimation propagates from the uncertainty of the three-dimensional points. This is higher for distant points, corresponding to matches with low temporal flow disparity in the images. Comparative results based on the reference KITTI evaluation framework show that SSLAM is effective and can be implemented efficiently, as it does not require any loop closure or bundle adjustment.

feature matchingSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniScheme (programming language)RANSACSettore INF/01 - InformaticaMatching (graph theory)business.industryFrame (networking)Bundle adjustmentTracking (particle physics)Structure from MotionLoop (topology)Flow (mathematics)SLAMComputer visionframe selectionArtificial intelligencebusinessPosecomputerVisual SLAMMathematicscomputer.programming_language
researchProduct

Prototyping Crop Traits Retrieval Models for CHIME: Dimensionality Reduction Strategies Applied to PRISMA Data

2022

In preparation for new-generation imaging spectrometer missions and the accompanying unprecedented inflow of hyperspectral data, optimized models are needed to generate vegetation traits routinely. Hybrid models, combining radiative transfer models with machine learning algorithms, are preferred, however, dealing with spectral collinearity imposes an additional challenge. In this study, we analyzed two spectral dimensionality reduction methods: principal component analysis (PCA) and band ranking (BR), embedded in a hybrid workflow for the retrieval of specific leaf area (SLA), leaf area index (LAI), canopy water content (CWC), canopy chlorophyll content (CCC), the fraction of absorbed photo…

feature selectionCHIMEactive learningGeneral Earth and Planetary Scienceshybrid methodPRISMAprincipal component analysibiochemical and biophysical traitGaussian process regressionPRISMA; CHIME; hybrid methods; biochemical and biophysical traits; Gaussian process regression; active learning; principal component analysis; feature selectionRemote Sensing
researchProduct

Source Mechanisms of Laboratory Earthquakes During Fault Nucleation and Formation

2021

Identifying deformation and pre-failure mechanisms preceding faulting is key for fault mechanics and for interpreting precursors to fault rupture. This study presents the results of a new and robust derivation of first motion polarity focal mechanism solutions (FMS) applied to acoustic emission (AE). FMS are solved using a least squares minimization of the fit between projected polarity measurements and the deviatoric stress field induced by dilatational (T-type), shearing (S-type), and compressional (C-type) sources. 4 × 10 cm cylindrical samples of Alzo Granite (AG, porosity <1%) and Darley Dale Sandstone (DDS, porosity ≈14%) underwent conventional triaxial tests in order to investigat…

focal mechanismAcoustic EmissionsNucleationEarthquakes Source mechanisms Rock Deformation Acoustic EmissionsFault (geology)Geochemistry and PetrologyEarth and Planetary Sciences (miscellaneous)Earthquakes/dk/atira/pure/subjectarea/asjc/1900/1912precusorySource mechanismsgeographyFocal mechanism/dk/atira/pure/subjectarea/asjc/1900/1908geography.geographical_feature_category/dk/atira/pure/subjectarea/asjc/1900/1906rock deformationGeophysicsAcoustic emissionfractureSpace and Planetary ScienceFracture (geology)/dk/atira/pure/subjectarea/asjc/1900/1901acoustic emissionRock DeformationSeismologyGeology
researchProduct

Stilistiskie izteiksmes līdzekļi pārtikas produktu reklāmas plakātos

2021

Bakalaura darba tiek pētīti stilistiski līdzekļi ar pārtiku saistītās drukas reklāmās. Reklāma ir īpaši nozīmīga un izplatīta mūsdienu sabiedrībā, tāpat kā nepieciešamība pēc zinātniskiem pētījumiem un izpratne par tās ietekmes sfērām, kas lielā mērā nosaka reklāmas tekstu lingvistiskās un stilistiskās iezīmes. Darbā tiek pētīti stilistiski pārtikas produktu reklāmas līdzekļi, ko izmanto vadošie starptautiskie pārtikas mazumtirgotāji, kas darbojas Latvijas tirgū. Pētījuma rezultāti tika apkopoti un analizēti, izmantojot nejaušas izlases metodi materiāla atlasei un strukturālās analīzes metodi, kas ļāva šī darba autoram veikt secinājumus, kas pierādīja, ka stilistiskie līdzekļi tiek plaši iz…

food productsValodniecībaprinted advertisementsstylistic featuresfood advertisementsstylistic means
researchProduct

Veronico beccabungae-callitrichetum stagnalis (Oberd. 1957) Müller 1962, a plant association new to Poland - Quality of habitat

2011

The paper presents a community of water plants that is new to Poland, <em>Veronico beccabungae-Callitrichetum</em> stagnalis (Oberd. 1957) Müller 1962. This community belongs to the class <em>Potametea</em>. It was discovered in the village of Odrowąż near the town of Krapkowice in Silesia (SW Poland). <em>Veronico beccabungae-Callitrichetum stagnalis</em> in Poland occurs within an irregularly shaped shallow underwater spring, located in the distal part of the Oder River’s flood terrace. This plant community covered 0.2 ha in 2008. <em>Callitriche stagnalis</em> predominated in this community. Species such as <em>Callitriche hamulata&lt…

food.ingredientphytosociologyEndangered speciesCallitriche stagnalisPlant Sciencequality of habitatPotametea classfoodVeronico beccabungae-Callitrichetum stagnalisAquatic plantlcsh:BotanyBotanySpring (hydrology)distributionendangered associationgeographygeography.geographical_feature_categorybiologyPhytosociologyEcologyCallitriche vernaPlant communitybiology.organism_classificationlcsh:QK1-989HabitatPoland
researchProduct

Insights on Hydrothermal‐Magmatic Interactions and Eruptive Processes at Poás Volcano (Costa Rica) From High‐Frequency Gas Monitoring and Drone Measu…

2019

Texto completo del documento Identification of unambiguous signals of volcanic unrest is crucial in hazard assessment. Processes leading to phreatic and phreatomagmatic eruptions remain poorly understood, inhibiting effective eruption forecasting. Our 5‐year gas record from Poás volcano, combined with geophysical data, reveals systematic behavior associated with hydrothermal‐magmatic eruptions. Three eruptive episodes are covered, each with distinct geochemical and geophysical characteristics. Periods with larger eruptions tend to be associated with stronger excursions in monitoring data, particularly in SO2/CO2 and SO2 flux. The explosive 2017 phreatomagmatic eruption was the largest erupt…

gas monitoringVOLCANOESGeochemistryPARQUE NACIONAL VOLCAN POAS (COSTA RICA)Hydrothermal circulationVOLCANIC ERUPTIONSphreatomagmatic eruptionsCrater lakePhreatomagmatic eruptionphreatic eruptionGEOLOGYPOAS VOLCANO NATIONAL PARK (COSTA RICA)geographyeruption triggeringgeography.geographical_feature_categorygeophysicGEOLOGÍADroneGas monitoringPhreatic eruptioncrater lakeGeophysicsVolcanoVOLCANESERUPCIONES VOLCANICASGeneral Earth and Planetary SciencesGeology
researchProduct

BVLOS UAS Operations in Highly-Turbulent Volcanic Plumes.

2020

Long-range, high-altitude Unoccupied Aerial System (UAS) operations now enable in-situ measurements of volcanic gas chemistry at globally-significant active volcanoes. However, the extreme environments encountered within volcanic plumes present significant challenges for both air frame development and in-flight control. As part of a multi-disciplinary field deployment in May 2019, we flew fixed wing UAS Beyond Visual Line of Sight (BVLOS) over Manam volcano, Papua New Guinea, to measure real-time gas concentrations within the volcanic plume. By integrating aerial gas measurements with ground- and satellite-based sensors, our aim was to collect data that would constrain the emission rate of …

gas sensingMeteorologyFlight operationslcsh:Mechanical engineering and machineryUAVBVLOSlcsh:QA75.5-76.95Volcanic GasesArtificial Intelligenceeventlcsh:TJ1-1570Original Researchevent.disaster_typeRobotics and AIgeographygeography.geographical_feature_categoryplumeTurbulenceaerial roboticManamNew guineaComputer Science ApplicationsPlumeaerial robotic Volcanic degassing aerial robotic gas sensing Manam plume UAV unmanned aircraft system (UAS) volcanovolcanoVolcanoVolcanic plumeSoftware deploymentEnvironmental scienceunmanned aircraft system (UAS)lcsh:Electronic computers. Computer scienceFrontiers in robotics and AI
researchProduct