Search results for "Pattern recognition"

showing 10 items of 2301 documents

Robustness of PET Radiomics Features: Impact of Co-Registration with MRI

2021

Radiomics holds great promise in the field of cancer management. However, the clinical application of radiomics has been hampered by uncertainty about the robustness of the features extracted from the images. Previous studies have reported that radiomics features are sensitive to changes in voxel size resampling and interpolation, image perturbation, or slice thickness. This study aims to observe the variability of positron emission tomography (PET) radiomics features under the impact of co-registration with magnetic resonance imaging (MRI) using the difference percentage coefficient, and the Spearman’s correlation coefficient for three groups of images: (i) original PET, (ii) PET after co-…

TechnologyTomografía de emisión de positronesNeoplasias encefálicasCorrelation coefficientImagen por resonancia magnética:Phenomena and Processes::Mathematical Concepts::Probability::Uncertainty [Medical Subject Headings]QH301-705.5Computer scienceQC1-999:Diseases::Neoplasms::Neoplasms by Site::Nervous System Neoplasms::Central Nervous System Neoplasms::Brain Neoplasms [Medical Subject Headings]:Analytical Diagnostic and Therapeutic Techniques and Equipment::Diagnosis::Diagnostic Techniques and Procedures::Diagnostic Imaging::Magnetic Resonance Imaging [Medical Subject Headings]Co registrationFluid-attenuated inversion recovery:Organisms::Eukaryota::Animals::Chordata::Vertebrates::Mammals::Primates::Haplorhini::Catarrhini::Hominidae::Humans [Medical Subject Headings]Magnetic resonance imagingRadiomicsRobustness (computer science):Analytical Diagnostic and Therapeutic Techniques and Equipment::Diagnosis::Diagnostic Techniques and Procedures::Diagnostic Techniques Radioisotope::Radionuclide Imaging::Tomography Emission-Computed::Positron-Emission Tomography [Medical Subject Headings]Resamplingradiomics feature robustness; imaging quantification; [11C]-methionine positron emission tomography; PET/MRI co-registration Appl.medicineGeneral Materials ScienceBiology (General)QD1-999InstrumentationSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniFluid Flow and Transfer Processesmedicine.diagnostic_testbusiness.industryTPhysicsProcess Chemistry and TechnologyRadiomics feature robustnessGeneral EngineeringPET/MRI co-registrationMagnetic resonance imagingPattern recognitionEngineering (General). Civil engineering (General)Imaging quantificationComputer Science ApplicationsChemistry:Chemicals and Drugs::Amino Acids Peptides and Proteins::Amino Acids::Amino Acids Essential::Methionine [Medical Subject Headings]Positron emission tomography[11C]-methionine positron emission tomography:Analytical Diagnostic and Therapeutic Techniques and Equipment::Diagnosis::Prognosis [Medical Subject Headings]Artificial intelligenceTA1-2040businessApplied Sciences
researchProduct

Learning non-linear time-scales with kernel -filters

2009

A family of kernel methods, based on the @c-filter structure, is presented for non-linear system identification and time series prediction. The kernel trick allows us to develop the natural non-linear extension of the (linear) support vector machine (SVM) @c-filter [G. Camps-Valls, M. Martinez-Ramon, J.L. Rojo-Alvarez, E. Soria-Olivas, Robust @c-filter using support vector machines, Neurocomput. J. 62(12) (2004) 493-499.], but this approach yields a rigid system model without non-linear cross relation between time-scales. Several functional analysis properties allow us to develop a full, principled family of kernel @c-filters. The improved performance in several application examples suggest…

TelecomunicacionesSupport vector machinesbusiness.industryCognitive NeuroscienceNonlinear System IdentificationPattern recognitionKernel principal component analysisComputer Science ApplicationsKernel methodMercer's KernelArtificial IntelligenceVariable kernel density estimationString kernelKernel embedding of distributionsPolynomial kernelRadial basis function kernelGamma-FiltersArtificial intelligenceTree kernelbusinessMathematicsNeurocomputing
researchProduct

Robust γ-filter using support vector machines

2009

This Letter presents a new approach to time-series modelling using the support vector machines (SVM). Although the g-filter can provide stability in several time-series models, the SVM is proposed here to provide robustness in the estimation of the g-filter coefficients. Examples in chaotic time-series prediction and channel equalization show the advantages of the joint SVM g-filter. Teoría de la Señal y Comunicaciones

Telecomunicacionesbusiness.industryComputer scienceCognitive NeuroscienceChaoticPattern recognitionComputer Science ApplicationsSupport vector machineFilter designArtificial IntelligenceRobustness (computer science)3325 Tecnología de las TelecomunicacionesArtificial intelligencebusinessNeurocomputing
researchProduct

A Simple Fusion Method for Image Time Series Based on the Estimation of Image Temporal Validity

2015

High-spatial-resolution satellites usually have the constraint of a low temporal frequency, which leads to long periods without information in cloudy areas. Furthermore, low-spatial-resolution satellites have higher revisit cycles. Combining information from high- and low- spatial-resolution satellites is thought a key factor for studies that require dense time series of high-resolution images, e.g., crop monitoring. There are several fusion methods in the bibliography, but they are time-consuming and complicated to implement. Moreover, the local evaluation of the fused images is rarely analyzed. In this paper, we present a simple and fast fusion method based on a weighted average of two in…

TeledeteccióComputer scienceforêt tropicalehttp://aims.fao.org/aos/agrovoc/c_714remote sensingSimple (abstract algebra)K01 - Foresterie - Considérations généralesBiomassehttp://aims.fao.org/aos/agrovoc/c_6498validationUtilisation des terresEucalyptusFusionQhttp://aims.fao.org/aos/agrovoc/c_14093http://aims.fao.org/aos/agrovoc/c_9000094Plantation forestièreséquestration du carbonehttp://aims.fao.org/aos/agrovoc/c_926http://aims.fao.org/aos/agrovoc/c_1070http://aims.fao.org/aos/agrovoc/c_25409http://aims.fao.org/aos/agrovoc/c_4182P01 - Conservation de la nature et ressources foncièresSpectrométriePhénologiehttp://aims.fao.org/aos/agrovoc/c_2683TélédétectionScienceImage (mathematics)Cartographie de l'occupation du solhttp://aims.fao.org/aos/agrovoc/c_24904TermodinàmicaCouverture végétalehttp://aims.fao.org/aos/agrovoc/c_7283http://aims.fao.org/aos/agrovoc/c_1666http://aims.fao.org/aos/agrovoc/c_8176http://aims.fao.org/aos/agrovoc/c_3048MODIS; Landsat; validation; remote sensingRemote sensingChangement climatiqueSeries (mathematics)business.industryCiències de la terraPattern recognitionVégétationhttp://aims.fao.org/aos/agrovoc/c_331583Constraint (information theory)http://aims.fao.org/aos/agrovoc/c_5774SpectroradiometerMODISSatelliteGeneral Earth and Planetary SciencesArtificial intelligenceU30 - Méthodes de recherchebusinessLandsatRemote Sensing; Volume 7; Issue 1; Pages: 704-724
researchProduct

Análisis de métodos de validación cruzada para la obtención robusta de parámetros biofísicos

2015

[EN] Non-parametric regression methods are powerful statistical methods to retrieve biophysical parameters from remote sensing measurements. However, their performance can be affected by what has been presented during the training phase. To ensure robust retrievals, various cross-validation sub-sampling methods are often used, which allow to evaluate the model with subsets of the field dataset. Here, two types of cross-validation techniques were analyzed in the development of non-parametric regression models: hold-out and k-fold. Selected non-parametric linear regression methods were least squares Linear Regression (LR) and Partial Least Squares Regression (PLSR), and nonlinear methods were…

TeledeteccióGeography Planning and Developmentlcsh:G1-922Least squaresCross-validationValidación cruzadaProcesos gausianosHold-outAnàlisi de regressióLinear regressionStatisticsPartial least squares regressionEarth and Planetary Sciences (miscellaneous)MLRAbusiness.industryCross-validationRegression analysisPattern recognitionRegresión de Kernel RidgeAprendizaje automáticoRegressionK-foldHold-OutGeographyk-foldPrincipal component regressionArtificial intelligencebusinessKernel Ridge regressionNonlinear regressionGaussian process regressionlcsh:Geography (General)Revista de Teledetección
researchProduct

Metodo di Template Matching per l'Analisi di Immagini

2012

La presente invenzione si riferisce ad un metodo di Template Matching per l’analisi di immagini da ImmunoFluorescenza Indiretta (IFI) per la rivelazione e classificazione automatica di pattern autoanticorpali. L’invenzione qui presentata generalizza il metodo del Template Matching operando innovativamente il mapping del contenuto visuale dell’immagine con particolari funzioni discrete qui denominate “mappatori”; inoltre, utilizzando le informazioni provenienti dalla sovrapposizione dei vari mappatori con un metodo di confronto funzionale, realizza una funzione di correlazione originale. La metodologia descritta nel seguito presenta una flessibilità tale da renderla applicabile a qualsiasi p…

Template Matchingpattern recognitionImmunofluorescenza indirettabioimmaginiSettore FIS/07 - Fisica Applicata(Beni Culturali Ambientali Biol.e Medicin)
researchProduct

Segmentation d'images robuste appliqué à l'imagerie par résonance magnétique et l'échographie de la prostate

2012

Prostate segmentation in trans rectal ultrasound (TRUS) and magnetic resonanceimages (MRI) facilitates volume estimation, multi-modal image registration, surgicalplaning and image guided prostate biopsies. The objective of this thesis is to developshape and region prior deformable models for accurate, robust and computationallyefficient prostate segmentation in TRUS and MRI images. Primary contributionof this thesis is in adopting a probabilistic learning approach to achieve soft classificationof the prostate for automatic initialization and evolution of a shape andregion prior deformable models for prostate segmentation in TRUS images. Twodeformable models are developed for the purpose. An…

Tesis i dissertacions acadèmiques616.6[INFO.INFO-OH]Computer Science [cs]/Other [cs.OH]Physics::Medical PhysicsProstate segmentation68Segmentación de la próstataNo english key word[ SDV.MHEP ] Life Sciences [q-bio]/Human health and pathologySegmentació de la próstata616.6 - Patologia del sistema genitourinariImagen de ultrasonidoPas de mots-clés en français[SDV.MHEP] Life Sciences [q-bio]/Human health and pathologyProstate cancerImatge d'ultrasóComputer Science::Other[INFO.INFO-OH] Computer Science [cs]/Other [cs.OH]68 - Indústries oficis i comerç d'articles acabats. Tecnologia cibernètica i automàticaCancer de próstataImatges mèdiquesComputer Science::Computer Vision and Pattern RecognitionImágenes médicasImatge de ressonància magnèticaMRI imagingUS imaging[ INFO.INFO-OH ] Computer Science [cs]/Other [cs.OH]Imagen de resonancia magnéticaMedical imaging[SDV.MHEP]Life Sciences [q-bio]/Human health and pathology
researchProduct

Development of an Automatic Pollen Classification System Using Shape, Texture and Aperture Features

2015

International audience; Automatic detection and classification of pollen species has value for use inside of palynologic allergen studies. Traditional labeling of different pollen species requires an expert biologist to classify particles by sight, and is therefore time-consuming and expensive. Here, an automatic process is developed which segments the particle contour and uses the extracted features for the classification process. We consider shape features, texture features and aperture features and analyze which are useful. The texture features analyzed include: Gabor Filters, Fast Fourier Transform, Local Binary Patterns, Histogram of Oriented Gradients, and Haralick features. We have s…

Texture classification[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Image processingMachine learningComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONPollen[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
researchProduct

A solution to the stochastic point location problem in metalevel nonstationary environments.

2008

This paper reports the first known solution to the stochastic point location (SPL) problem when the environment is nonstationary. The SPL problem involves a general learning problem in which the learning mechanism (which could be a robot, a learning automaton, or, in general, an algorithm) attempts to learn a "parameter," for example, lambda*, within a closed interval. However, unlike the earlier reported results, we consider the scenario when the learning is to be done in a nonstationary setting. For each guess, the environment essentially informs the mechanism, possibly erroneously (i.e., with probability p), which way it should move to reach the unknown point. Unlike the results availabl…

Theoretical computer scienceAutomatic controlDiscretizationComputer scienceInformation Storage and RetrievalDecision Support TechniquesPattern Recognition AutomatedArtificial IntelligenceComputer SimulationElectrical and Electronic EngineeringStochastic ProcessesModels StatisticalLearning automatabusiness.industryStochastic processSignal Processing Computer-AssistedGeneral MedicineRandom walkComputer Science ApplicationsAutomatonHuman-Computer InteractionControl and Systems EngineeringPoint locationArtificial intelligencebusinessSoftwareAlgorithmsInformation SystemsIEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society
researchProduct

Increasing the Inference and Learning Speed of Tsetlin Machines with Clause Indexing

2020

The Tsetlin Machine (TM) is a machine learning algorithm founded on the classical Tsetlin Automaton (TA) and game theory. It further leverages frequent pattern mining and resource allocation principles to extract common patterns in the data, rather than relying on minimizing output error, which is prone to overfitting. Unlike the intertwined nature of pattern representation in neural networks, a TM decomposes problems into self-contained patterns, represented as conjunctive clauses. The clause outputs, in turn, are combined into a classification decision through summation and thresholding, akin to a logistic regression function, however, with binary weights and a unit step output function. …

Theoretical computer scienceContextual image classificationArtificial neural networkLearning automataComputer scienceSentiment analysisSearch engine indexingPattern recognition (psychology)OverfittingMNIST database
researchProduct