Search results for "Random forest"

showing 10 items of 121 documents

EFFICIENT MACHINE LEARNING FRAMEWORK FOR COMPUTER-AIDED DETECTION OF CEREBRAL MICROBLEEDS USING THE RADON TRANSFORM

2014

International audience; Recent developments of susceptibility weighted MR techniques have improved visualization of venous vasculature and underlying pathologies such as cerebral microbleed (CMB). CMBs are small round hypointense lesions on MRI images that are emerging as a potential biomarker for cerebrovascular disease. CMB manual rating has limited reliability, is time-consuming and is prone to errors as small CMBs can be easily missed or mistaken for venous crosssections. This paper presents a computer-aided detection technique that utilizes a novel cascade of random forest classifiers which are trained on robust Radon-based features with an unbalanced sample distribution. The training …

Radon transformbusiness.industryBlob detection030218 nuclear medicine & medical imagingVisualizationRandom forest03 medical and health sciences0302 clinical medicineSampling distribution[INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV]Minimum bounding box[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]Susceptibility weighted imaging[ INFO.INFO-TI ] Computer Science [cs]/Image ProcessingComputer visionArtificial intelligenceSensitivity (control systems)business030217 neurology & neurosurgeryMathematics
researchProduct

Random forest analysis: a new approach for classication of Beta Thalassemia

2020

In recent years, Thalassemia care providers started classifying patients as transfusion- dependent-Thalassemia (TDT) or non-transfusion-dependent-Thalassemia (NTDT) owing to the established role of transfusion therapy in dening the clinical complication prole, although this classication was also based on expert opinion and is limited by reliance on patients'current transfusion status. Starting from a vast set of variables indicating severity phenotype, through the use of both classication and clustering techniques we want to explore the presence of two (TDT vs NTDT) or more clusters, in order to approaching to a new denition for the classication of Beta-Thalassemia in Thalassemia Syndromes …

Random forest Unsupervised classication Clustering Thalassemia
researchProduct

Assessment of Classifiers and Remote Sensing Features of Hyperspectral Imagery and Stereo-Photogrammetric Point Clouds for Recognition of Tree Specie…

2018

Recognition of tree species and geospatial information on tree species composition is essential for forest management. In this study, tree species recognition was examined using hyperspectral imagery from visible to near-infrared (VNIR) and short-wave infrared (SWIR) camera sensors in combination with a 3D photogrammetric canopy surface model based on RGB camera stereo-imagery. An arboretum with a diverse selection of 26 tree species from 14 genera was used as a test area. Aerial hyperspectral imagery and high spatial resolution photogrammetric color imagery were acquired from the test area using unmanned aerial vehicle (UAV) borne sensors. Hyperspectral imagery was processed to calibrated …

Reflectance calibration010504 meteorology & atmospheric sciencesInfraredComputer sciencegeneettiset algoritmitUAVta1171Point clouddense point cloud01 natural scienceshyperspectral imagery; tree species recognition; photogrammetry; dense point cloud; reflectance calibration; UAV; random forest; genetic algorithm; machine learningilmakuvakartoitusMachine learninggenetic algorithmImage sensorfotogrammetria0105 earth and related environmental sciencesRemote sensingta113040101 forestryta213tree species recognitionspektrikuvausSpecies diversityHyperspectral imaging04 agricultural and veterinary sciencesOtaNanoreflectance calibrationDense point cloudVNIRRandom forestTree (data structure)hyperspectral imagerykoneoppiminenPhotogrammetryGenetic algorithmHyperspectral imageryPhotogrammetryTree species recognitionlajinmääritys0401 agriculture forestry and fisheriesGeneral Earth and Planetary SciencesRGB color modelkaukokartoituspuustorandom forestRandom forestRemote Sensing; Volume 10; Issue 5; Pages: 714
researchProduct

Relative evaluation of regression tools for urban area electrical energy demand forecasting

2019

Abstract Load forecasting is the most fundamental application in Smart-Grid, which provides essential input to Demand Response, Topology Optimization and Abnormally Detection, facilitating the integration of intermittent clean energy sources. In this work, several regression tools are analyzed using larger datasets for urban area electrical load forecasting. The regression tools which are used are Random Forest Regressor, k-Nearest Neighbour Regressor and Linear Regressor. This work explores the use of regression tool for regional electric load forecasting by correlating lower distinctive categorical level (season, day of the week) and weather parameters. The regression analysis has been do…

Renewable Energy Sustainability and the Environment020209 energyStrategy and Management05 social sciencesRegression analysisSample (statistics)02 engineering and technologyDemand forecastingIndustrial and Manufacturing EngineeringRegressionRandom forestDemand responseMean absolute percentage errorStatistics050501 criminology0202 electrical engineering electronic engineering information engineeringCategorical variable0505 lawGeneral Environmental ScienceMathematicsJournal of Cleaner Production
researchProduct

Deep learning for agricultural land use classification from Sentinel-2

2020

[ES] En el campo de la teledetección se ha producido recientemente un incremento del uso de técnicas de aprendizaje profundo (deep learning). Estos algoritmos se utilizan con éxito principalmente en la estimación de parámetros y en la clasificación de imágenes. Sin embargo, se han realizado pocos esfuerzos encaminados a su comprensión, lo que lleva a ejecutarlos como si fueran “cajas negras”. Este trabajo pretende evaluar el rendimiento y acercarnos al entendimiento de un algoritmo de aprendizaje profundo, basado en una red recurrente bidireccional de memoria corta a largo plazo (2-BiLSTM), a través de un ejemplo de clasificación de usos de suelo agrícola de la Comunidad Valenciana dentro d…

Series temporalesTime series010504 meteorology & atmospheric sciencesComputer scienceRemote sensing applicationGeography Planning and Development0211 other engineering and technologiesDecision treelcsh:G1-92202 engineering and technologyClasificaciónMachine learningcomputer.software_genre01 natural sciencesBiLSTMClassifier (linguistics)Earth and Planetary Sciences (miscellaneous)Spatial analysis021101 geological & geomatics engineering0105 earth and related environmental sciencesArtificial neural networkbusiness.industryDeep learningDeep learningClassificationRandom forestSupport vector machineArtificial intelligenceSentinel-2businesscomputerlcsh:Geography (General)
researchProduct

Application of SNP reduction approaches and random forest for the identification of population informative markers in cosmopolitan and local cattle b…

2017

In livestock, single nucleotide polymorphism genotyping arrays have been used to differentiate breeds and populations for several downstream applications, including breed allocation of individuals, breeds of origin of crossbred animals, authentication of mono breed products, comparative analyses of selection signatures among several other uses. We already tested a combination of principal component analysis (PCA), used as preselection method, and random forest (RF) used as classification method to assign cosmopolitan Italian breeds with no or very low error rate. In this work, we increased the number of breeds and approaches, to have a more comprehensive view of the strategies available and…

Settore AGR/17 - Zootecnica Generale E Miglioramento GeneticoSNPs random forest cattle breeds
researchProduct

Modeling Macroalgal Forest Distribution at Mediterranean Scale: Present Status, Drivers of Changes and Insights for Conservation and Management

2020

Macroalgal forests are one of the most productive and valuable marine ecosystems, but yet strongly exposed to fragmentation and loss. Detailed large-scale information on their distribution is largely lacking, hindering conservation initiatives. In this study, a systematic effort to combine spatial data on Cystoseira C. Agardh canopies (Fucales, Phaeophyta) was carried out to develop a Habitat Suitability Model (HSM) at Mediterranean scale, providing critical tools to improve site prioritization for their management, restoration and protection. A georeferenced database on the occurrence of 20 Cystoseira species was produced collecting all the available information from published and grey lit…

Settore BIO/07 - EcologiaCystoseira canopies; Habitat suitability model; Mediterranean Sea; Random Forest; Species distribution0106 biological scienceslcsh:QH1-199.5Settore BIO/07Distribution (economics)Ocean Engineeringlcsh:General. Including nature conservation geographical distributionAquatic ScienceCystoseira canopieOceanography010603 evolutionary biology01 natural sciencesMediterranean scaleBrown algae -- Mediterranean seeAlgues brunes -- Distribució geogràficaMediterranean seaMarine resources -- Management -- Mediterranean SeaMediterranean Seamedia_common.cataloged_instance14. Life underwaterEuropean unionlcsh:ScienceAlgues brunes -- Mediterrània MarSpecies distributionWater Science and Technologymedia_commonGlobal and Planetary ChangeRandom ForestMarine ecology -- Mediterranean Seabusiness.industrySettore BIO/02 - Botanica Sistematica010604 marine biology & hydrobiologyEnvironmental resource managementMarine habitats -- Mediterranean Sea15. Life on landHabitat suitability model (HSM)Geography13. Climate actionSettore BIO/03 - Botanica Ambientale E Applicatalcsh:QCystoseira canopies habitat suitability model Mediterranean Sea Random Forest species distributionCystoseira canopiesbusinessHabitat suitability modelMarine algae -- Mediterranean SeaBrown algae -- Geographical distributionFrontiers in Marine Science
researchProduct

A Novel Recruitment Policy to Defend against Sybils in Vehicular Crowdsourcing

2021

Vehicular Social Networks (VSNs) is an emerging communication paradigm, derived by merging the concepts of Online Social Networks (OSNs) and Vehicular Ad-hoc Networks (VANETs). Due to the lack of robust authentication mechanisms, social-based vehicular applications are vulnerable to numerous attacks including the generation of sybil entities in the networks. We address this important issue in vehicular crowdsourcing campaigns where sybils are usually employed to increase their influence and worsen the functioning of the system. In particular, we propose a novel User Recruitment Policy (URP) that, after extracting the participants within the event radius of a crowdsourcing campaign, detects …

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniAuthenticationEvent (computing)business.industryComputer sciencecomputer.internet_protocolComputerSystemsOrganization_COMPUTER-COMMUNICATIONNETWORKSCrowdsourcingComputer securitycomputer.software_genreDomain (software engineering)Random forestCrowdsourcing; Proximity Graph; Sybil detection; Trust and Truthfulness; Vehicular Social NetworkCrowdsourcing Proximity Graph Sybil detection Trust and Truthfulness Vehicular Social NetworkGraph (abstract data type)RADIUSbusinesscomputer
researchProduct

Automatic differentiation of melanoma from dysplastic nevi.

2015

International audience; Malignant melanoma causes the majority of deaths related to skin cancer. Nevertheless, it is the most treatable one, depending on its early diagnosis. The early prognosis is a challenging task for both clinicians and dermatologist, due to the characteristic similarities of melanoma with other skin lesions such as dysplastic nevi. In the past decades, several computerized lesion analysis algorithms have been proposed by the research community for detection of melanoma. These algorithms mostly focus on differentiating melanoma from benign lesions and few have considered the case of melanoma against dysplastic nevi. In this paper, we consider the most challenging task a…

Shape featuresSkin Neoplasms[SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/ImagingDysplastic02 engineering and technology[ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]030218 nuclear medicine & medical imagingColourPattern Recognition Automated0302 clinical medicine0202 electrical engineering electronic engineering information engineeringMelanoma[ SDV.IB.IMA ] Life Sciences [q-bio]/Bioengineering/ImagingRadiological and Ultrasound Technology[ INFO.INFO-IM ] Computer Science [cs]/Medical ImagingMelanomaClassificationComputer Graphics and Computer-Aided DesignDermoscopy imaging3. Good healthRandom forest020201 artificial intelligence & image processingComputer Vision and Pattern RecognitionAlgorithmsmedicine.medical_specialtyAutomatic differentiationFeature extractionHealth InformaticsDermoscopySensitivity and SpecificityDiagnosis Differential03 medical and health sciencesLesion analysisMachine learningImage Interpretation Computer-Assistedmedicine[INFO.INFO-IM]Computer Science [cs]/Medical ImagingHumansRadiology Nuclear Medicine and imagingTextureneoplasmsbusiness.industry[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]medicine.diseaseDermatologySupport vector machineBag-of-words modelSkin cancerbusinessDysplastic Nevus SyndromeComputerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
researchProduct

Nonlinear Distribution Regression for Remote Sensing Applications

2020

In many remote sensing applications, one wants to estimate variables or parameters of interest from observations. When the target variable is available at a resolution that matches the remote sensing observations, standard algorithms, such as neural networks, random forests, or the Gaussian processes, are readily available to relate the two. However, we often encounter situations where the target variable is only available at the group level, i.e., collectively associated with a number of remotely sensed observations. This problem setting is known in statistics and machine learning as multiple instance learning (MIL) or distribution regression (DR). This article introduces a nonlinear (kern…

Signal Processing (eess.SP)FOS: Computer and information sciencesComputer Science - Machine LearningArtificial neural networkRemote sensing applicationComputer science0211 other engineering and technologies02 engineering and technologyLeast squaresRandom forestMachine Learning (cs.LG)Kernel (linear algebra)symbols.namesakeKernel (statistics)symbolsFOS: Electrical engineering electronic engineering information engineeringGeneral Earth and Planetary SciencesElectrical Engineering and Systems Science - Signal ProcessingElectrical and Electronic EngineeringGaussian processAlgorithm021101 geological & geomatics engineeringCurse of dimensionalityIEEE Transactions on Geoscience and Remote Sensing
researchProduct