Search results for "METHODOLOGIE"

showing 10 items of 2141 documents

Semi-supervised Hyperspectral Image Classification with Graphs

2006

This paper presents a semi-supervised graph-based method for the classification of hyperspectral images. The method is designed to exploit the spatial/contextual information in the im- ages through composite kernels. The proposed method produces smoother classifications with respect to the intrinsic structure collectively revealed by known labeled and unlabeled points. Good accuracy in high dimensional spaces and low number of labeled samples (ill-posed situations) are produced as compared to standard inductive support vector machines.

Structured support vector machineContextual image classificationbusiness.industryHyperspectral imagingPattern recognitionGraphRelevance vector machineSupport vector machineComputingMethodologies_PATTERNRECOGNITIONKernel (image processing)Artificial intelligencebusinessCluster analysisMathematics2006 IEEE International Symposium on Geoscience and Remote Sensing
researchProduct

The Development of the Dealing with Challenging Interaction (DCI) Method to Evaluate Teachers’ Social Interaction Skills

2012

The Dealing with Challenging Interaction (DCI) method was developed to measure social interaction skills of teacher study groups. The participants were 70 teachers from three schools. The inter-rater agreement, Cohen’s kappa, varied between 0.57- 1.00. The discriminant validity was supported by a cluster analysis differentiating between the skilful and less skilful teachers. The results of the supplementary instrument were equivalent to the cluster analysis maintaining criterion oriented validity of the method developed. The DCI appeared to be a reliable and valid tool for measuring teachers’ social interaction skills. Peer reviewed

Study groupsevaluation methodologies515 Psychologymedia_common.quotation_subjectsupporting autonomychallenging interactionteacher trainingevaluation method03 medical and health sciences0302 clinical medicineSocial interaction skillsEvaluation methodsSocial emotional learningMathematics educationTeacher Effectiveness TrainingDealing with Challenging InteractionGeneral Materials Sciencevuorovaikutuksen tutkimus030212 general & internal medicineautonomyopettajankoulutusta515media_common4. Education05 social sciencesteacher study groupDiscriminant validity050301 educationsocial interactionglobal ratingsocial and emotional learningSocial relationGlobal Rating516 Educational sciencesPsychology0503 educationSocial psychologyAutonomyProcedia - Social and Behavioral Sciences
researchProduct

A deep semantic segmentation-based algorithm to segment crops and weeds in agronomic color images

2022

Abstract In precision agriculture, the accurate segmentation of crops and weeds in agronomic images has always been the center of attention. Many methods have been proposed but still the clean and sharp segmentation of crops and weeds is a challenging issue for the images with a high presence of weeds. This work proposes a segmentation method based on the combination of semantic segmentation and K-means algorithms for the segmentation of crops and weeds in color images. Agronomic images of two different databases were used for the segmentation algorithms. Using the thresholding technique, everything except plants was removed from the images. Afterward, semantic segmentation was applied usin…

Subtractive colorComputer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONConfusion matrixForestryAquatic ScienceThresholdingAccurate segmentationComputer Science ApplicationsClassification rateAnimal Science and ZoologySegmentationPrecision agricultureCluster analysisAgronomy and Crop ScienceAlgorithmInformation Processing in Agriculture
researchProduct

La Valle dei Templi in epoca medioevale. Caratterizzazione antropologica e paleopatologica delle sepolture antistanti in Tempio della Concordia

2021

Riassunto ― Il lavoro presenta i risultati delle analisi bio-archeologiche effettuate su resti scheletrici umani rinvenuti in quattordici sepolture di epoca medioevale rinvenute nel Parco Archeologico della Valle dei Templi di Agrigento (Sicilia). L’obiettivo è stato l’acquisizione delle informazioni necessarie per la ricostruzione del profilo biologico di ciascun individuo, al fine di determinarne il sesso, la stima dell’età biologica alla morte, la stima della statura e la valutazione delle patologie e degli indicatori di stress occupazionale mediante le correnti metodologie e tecniche diagnostiche di tipo antropologico. Sebbene il cattivo stato di conservazione di alcuni individui non ne…

Summary ― The work presents the results of the bio-archaeological analyzes carried out on human skeletal remains found in fourteen burials of Medieval chronology at the Archaeological Park of Valle dei Templi in Agrigentum (Sicily). The aim of the work was the acquisition of the information necessary for the reconstruction of the biological profile of each individual throught the determination of sex the estimate of the biological age at death the estimate of height and the evaluation of pathologies and markers of occupational stress through current anthropological diagnostic methodologies and techniques. Althought the poor state of conservation of some individuals has not allowed their whole anthropological characterization the investigations have highlighted the heterogeneity relating to the age groups and have allowed us to ascertain the presence of pathological alterations in subjects of mature age sometimes of unknown etiology such as DISH (Diffuse Idiopathic Hyperostosis). The sample size is not representative of the entire population but subsequent insights will provide a better understanding of the population dynamics of Medieval Agrigentum.Settore BIO/08 - Antropologia
researchProduct

Mixed Fault Classification of Sensorless PMSM Drive in Dynamic Operations Based on External Stray Flux Sensors

2022

This paper aims to classify local demagnetisation and inter-turn short-circuit (ITSC) on position sensorless permanent magnet synchronous motors (PMSM) in transient states based on external stray flux and learning classifier. Within the framework, four supervised machine learning tools were tested: ensemble decision tree (EDT), k-nearest neighbours (KNN), support vector machine (SVM), and feedforward neural network (FNN). All algorithms are trained on datasets from one operational profile but tested on other different operation profiles. Their input features or spectrograms are computed from resampled time-series data based on the estimated position of the rotor from one stray flux sensor t…

Support Vector Machinedemagnetisationinter-turn short circuitChemical technologydemagnetisation; inter-turn short circuit; machine learning; permanent magnet synchronous motor; variable speed; variable loadTP1-1185BiochemistryAtomic and Molecular Physics and OpticsAnalytical ChemistryComputingMethodologies_PATTERNRECOGNITIONmachine learningpermanent magnet synchronous motorvariable speedVDP::Teknologi: 500::Maskinfag: 570Magnetsvariable loadNeural Networks ComputerSupervised Machine LearningElectrical and Electronic EngineeringInstrumentationAlgorithmsSensors (Basel, Switzerland)
researchProduct

Classification of SD-OCT volumes with multi pyramids, LBP and HOG descriptors: application to DME detections.

2016

This paper deals with the automated detection of Diabetic Macular Edema (DME) on Optical Coherence Tomography (OCT) volumes. Our method considers a generic classification pipeline with preprocessing for noise removal and flattening of each B-Scan. Features such as Histogram of Oriented Gradients (HOG) and Local Binary Patterns (LBP) are extracted and combined to create a set of different feature vectors which are fed to a linear-Support Vector Machines (SVM) Classifier. Experimental results show a promising sensitivity/specificity of 0.75/0.87 on a challenging dataset.

Support Vector Machinegenetic structuresDatabases FactualComputer science[INFO.INFO-IM] Computer Science [cs]/Medical Imaging02 engineering and technology[ SPI.SIGNAL ] Engineering Sciences [physics]/Signal and Image processing[ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]01 natural sciences[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]0202 electrical engineering electronic engineering information engineeringImage Processing Computer-AssistedSegmentationComputer visionmedicine.diagnostic_test[ INFO.INFO-IM ] Computer Science [cs]/Medical ImagingDiabetic retinopathyHistogram of oriented gradientsmedicine.anatomical_structure020201 artificial intelligence & image processing[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processingTomography Optical CoherenceLocal binary patternsFeature vectorDiabetic macular edemaFeature extractionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONImage processingSensitivity and SpecificityMacular Edema010309 opticsOptical coherence tomographyHistogram0103 physical sciencesmedicine[INFO.INFO-IM]Computer Science [cs]/Medical ImagingHumansMacular edema[SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processingRetinaDiabetic Retinopathybusiness.industry[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Pattern recognitionImage segmentationmedicine.diseaseeye diseasesSupport vector machineComputingMethodologies_PATTERNRECOGNITIONsense organsArtificial intelligencebusinessAnnual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
researchProduct

Deep learning approach for prediction of impact peak appearance at ground reaction force signal of running activity

2020

Protruding impact peak is one of the features of vertical ground reaction force (GRF) that is related to injury risk while running. The present research is dedicated to predicting GRF impact peak appearance by setting a binary classification problem. Kinematic data, namely a number of raw signals in the sagittal plane, collected by the Vicon motion capture system (Oxford Metrics Group, UK) were employed as predictors. Therefore, the input data for the predictive model are presented as a multi-channel time series. Deep learning techniques, namely five convolutional neural network (CNN) models were applied to the binary classification analysis, based on a Multi-Layer Perceptron (MLP) classifi…

Support Vector MachinerasitusvammatComputer science02 engineering and technologyneuroverkotliikkeenkaappausConvolutional neural networkRunning0302 clinical medicineCluster Analysis315 Sport and fitness sciencesbinary classificationrisk assessmentSignal Processing Computer-AssistedGeneral MedicineComputer Science ApplicationsRandom forestkoneoppiminenBinary classificationRUNNERSbiomekaniikkaAlgorithmsCNNforce platform0206 medical engineeringBiomedical EngineeringBioengineeringjuoksu03 medical and health sciencesDeep LearningClassifier (linguistics)HumansliikeanalyysiGround reaction forcerunning gait analysisbusiness.industryDeep learningPattern recognition030229 sport sciencesPerceptron113 Computer and information sciences020601 biomedical engineeringHuman-Computer InteractionSupport vector machineLogistic ModelsComputingMethodologies_PATTERNRECOGNITIONINJURIESArtificial intelligenceNeural Networks Computerbusiness
researchProduct

An AI Walk from Pharmacokinetics to Marketing

2009

This work is intended for providing a review of reallife practical applications of Artificial Intelligence (AI) methods. We focus on the use of Machine Learning (ML) methods applied to rather real problems than synthetic problems with standard and controlled environment. In particular, we will describe the following problems in next sections: • Optimization of Erythropoietin (EPO) dosages in anaemic patients undergoing Chronic Renal Failure (CRF). • Optimization of a recommender system for citizen web portal users. • Optimization of a marketing campaign. The choice of these problems is due to their relevance and their heterogeneity. This heterogeneity shows the capabilities and versatility …

Support vector machineEngineeringComputingMethodologies_PATTERNRECOGNITIONAdaptive resonance theoryArtificial neural networkbusiness.industryMultilayer perceptronReinforcement learningArtificial intelligencebusinessCluster analysisFuzzy logicHierarchical clustering
researchProduct

HD-RTI: an adaptive multi-light imaging approach for the quality assessment of manufactured surfaces

2021

International audience; Reflectance Transformation Imaging (RTI) is a technique for estimating surface local angular reflectance from a set of stereo-photometric images captured with variable lighting directions. The digitization of this information fully fits into the industry 4.0 approach and makes it possible to characterize the visual properties of a surface. The proposed method, namely HD-RTI, is based on the coupling of RTI and HDR imaging techniques. This coupling is carried out adaptively according to the response at each angle of illumination. The proposed method is applied to five industrial samples which have high local variations of reflectivity because of their heterogeneity of…

Surface (mathematics)0209 industrial biotechnologyGeneral Computer ScienceComputer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technologyMachine visionSet (abstract data type)020901 industrial engineering & automationQuality (physics)[INFO.INFO-TS]Computer Science [cs]/Signal and Image ProcessingRobustness (computer science)0202 electrical engineering electronic engineering information engineeringComputer visionComputingMethodologies_COMPUTERGRAPHICSCouplingbusiness.industryQuality assessmentGeneral Engineering[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Variable (computer science)Quality inspection020201 artificial intelligence & image processingArtificial intelligenceMaterial AppearancebusinessPolynomial texture mapping
researchProduct

Two View Line-Based Motion and Structure Estimation for Planar Scenes

2012

We present an algorithm for reconstruction of piece-wise planar scenes from only two views and based on minimum line correspondences. We first recover camera rotation by matching vanishing points based on the methods already exist in the literature and then recover the camera translation by searching among a family of hypothesized planes passing through one line. Unlike algorithms based on line segments, the presented algorithm does not require an overlap between two line segments or more that one line correspon- dence across more than two views to recover the translation and achieves the goal by exploiting photometric constraints of the surface around the line. Experimental results on real…

Surface (mathematics)Computer engineering. Computer hardwareMatching (graph theory)Line correspondenceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technologyVideo AnalysisTranslation (geometry)[ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]TK7885-7895Motion[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Line segment0202 electrical engineering electronic engineering information engineeringComputer visionVanishing pointComputingMilieux_MISCELLANEOUSMathematicsTwo viewsbusiness.industryTracking[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]020207 software engineeringKeywordsQA75.5-76.953D and StereoReal imageElectronic computers. Computer scienceLine (geometry)Piece-wise planar scene020201 artificial intelligence & image processingComputer Vision and Pattern RecognitionArtificial intelligencebusinessStructure and MotionRotation (mathematics)Software
researchProduct