Search results for "Pattern recognition"

showing 10 items of 2301 documents

Classification of Heart Sounds Using Convolutional Neural Network

2020

Heart sounds play an important role in the diagnosis of cardiac conditions. Due to the low signal-to-noise ratio (SNR), it is problematic and time-consuming for experts to discriminate different kinds of heart sounds. Thus, objective classification of heart sounds is essential. In this study, we combined a conventional feature engineering method with deep learning algorithms to automatically classify normal and abnormal heart sounds. First, 497 features were extracted from eight domains. Then, we fed these features into the designed convolutional neural network (CNN), in which the fully connected layers that are usually used before the classification layer were replaced with a global averag…

Feature engineeringComputer science0206 medical engineeringconvolutional neural networkneuroverkot02 engineering and technologyOverfittingConvolutional neural networklcsh:Technologylcsh:Chemistry0202 electrical engineering electronic engineering information engineeringFeature (machine learning)General Materials ScienceSensitivity (control systems)sydäntauditInstrumentationlcsh:QH301-705.5Fluid Flow and Transfer Processesbusiness.industrylcsh:TProcess Chemistry and TechnologyDeep learning020208 electrical & electronic engineeringGeneral EngineeringPattern recognitiondiagnostiikkaMatthews correlation coefficientautomatic heart sound classification020601 biomedical engineeringlcsh:QC1-999Computer Science Applicationsfeature engineeringkoneoppiminenlcsh:Biology (General)lcsh:QD1-999lcsh:TA1-2040Heart soundsArtificial intelligencetiedonlouhintabusinesslcsh:Engineering (General). Civil engineering (General)lcsh:PhysicsApplied Sciences
researchProduct

Combining feature extraction and expansion to improve classification based similarity learning

2017

Abstract Metric learning has been shown to outperform standard classification based similarity learning in a number of different contexts. In this paper, we show that the performance of classification similarity learning strongly depends on the data format used to learn the model. We then present an Enriched Classification Similarity Learning method that follows a hybrid approach that combines both feature extraction and feature expansion. In particular, we propose a data transformation and the use of a set of standard distances to supplement the information provided by the feature vectors of the training samples. The method is compared to state-of-the-art feature extraction and metric lear…

Feature extractionLinear classifier02 engineering and technologySemi-supervised learning010501 environmental sciencesMachine learningcomputer.software_genre01 natural sciencesk-nearest neighbors algorithmArtificial Intelligence0202 electrical engineering electronic engineering information engineering0105 earth and related environmental sciencesMathematicsbusiness.industryDimensionality reductionPattern recognitionStatistical classificationSignal Processing020201 artificial intelligence & image processingComputer Vision and Pattern RecognitionArtificial intelligencebusinessFeature learningcomputerSoftwareSimilarity learningPattern Recognition Letters
researchProduct

Local electrical characterisation of human atrial fibrillation

2002

The rate of success of radio-frequency catheter ablation in the treatment of atrial fibrillation may be significantly improved by evaluating the local electrical properties of the atrial tissue. The aim of this study is the development of an automatic procedure for the characterisation of the local electrical activity during atrial fibrillation and the comparison of its performance with the manual analysis. The adopted procedures were the semi-automatic measurement of the local fibrillation intervals (A-A intervals) and the manual electrogram classification following the criteria suggested by Wells (1978) or Konings (1997). Two methods have been used: Principal Component Analysis and Cluste…

Fibrillationmedicine.medical_specialtymedicine.diagnostic_testbusiness.industrymedicine.medical_treatmentComputer Science Applications1707 Computer Vision and Pattern RecognitionAtrial fibrillationCatheter ablationAtrial tissuemedicine.diseaseInternal medicineSettore ING-INF/06 - Bioingegneria Elettronica E InformaticaClinical valueCardiologyMedicinemedicine.symptomCardiology and Cardiovascular MedicinebusinessElectrocardiographyComputers in Cardiology 2000. Vol.27 (Cat. 00CH37163)
researchProduct

Testing the X-IFU calibration requirements: an example for quantum efficiency and energy resolution

2018

With its array of 3840 Transition Edge Sensors (TESs) operated at 90 mK, the X-Ray Integral Field Unit (X-IFU) on board the ESA L2 mission Athena will provide spatially resolved high-resolution spectroscopy (2.5 eV FWHM up to 7 keV) over the 0.2 to 12 keV bandpass. The in-flight performance of the X-IFU will be strongly affected by the calibration of the instrument. Uncertainties in the knowledge of the overall system, from the filter transmission to the energy scale, may introduce systematic errors in the data, which could potentially compromise science objectives - notably those involving line characterisation e.g. turbulence velocity measurements - if not properly accounted for. Defining…

Field (physics)FOS: Physical sciencesCondensed Matter Physic01 natural sciences7. Clean energyX-raySettore FIS/05 - Astronomia E AstrofisicaBand-pass filter0103 physical sciencesCalibrationAthenaElectrical and Electronic Engineering010306 general physics010303 astronomy & astrophysicsInstrumentation and Methods for Astrophysics (astro-ph.IM)ComputingMilieux_MISCELLANEOUSPhysicsX-IFU[SDU.ASTR]Sciences of the Universe [physics]/Astrophysics [astro-ph]Electronic Optical and Magnetic MaterialDetectorAstrophysics::Instrumentation and Methods for AstrophysicsComputer Science Applications1707 Computer Vision and Pattern RecognitionFilter (signal processing)Computational physicsApplied MathematicPerformance verificationTransmission (telecommunications)CalibrationQuantum efficiencyAstrophysics - Instrumentation and Methods for AstrophysicsEnergy (signal processing)
researchProduct

The performance of the ATHENA X-ray Integral Field Unit

2018

The X-ray Integral Field Unit (X-IFU) is a next generation microcalorimeter planned for launch onboard the Athena observatory. Operating a matrix of 3840 superconducting Transition Edge Sensors at 90 mK, it will provide unprecedented spectro-imaging capabilities (2.5 eV resolution, for a field of view of 5') in the soft X-ray band (0.2 up to 12 keV), enabling breakthrough science. The definition of the instrument evolved along the phase A study and we present here an overview of its predicted performances and their modeling, illustrating how the design of the X-IFU meets its top-level scientific requirements. This article notably covers the energy resolution, count-rate capability, quantum …

Field (physics)X-ray Integral Fiel UnitPhase (waves)Field of viewCondensed Matter Physicmicrocalorimeter01 natural sciencesX-rayMatrix (mathematics)Settore FIS/05 - Astronomia E AstrofisicaObservatory0103 physical sciencesAthenaAerospace engineeringElectrical and Electronic Engineering010306 general physicsPhysics010308 nuclear & particles physicsbusiness.industryElectronic Optical and Magnetic MaterialResolution (electron density)Computer Science Applications1707 Computer Vision and Pattern RecognitionApplied MathematicQuantum efficiencybusinessEnergy (signal processing)performance
researchProduct

A methodology for assessing the effect of correlations among muscle synergy activations on task-discriminating information

2013

Delis, Ioannis | Berret, Bastien | Pozzo, Thierry | Panzeri, Stefano; International audience; ''Muscle synergies have been hypothesized to be the building blocks used by the central nervous system to generate movement. According to this hypothesis, the accomplishment of various motor tasks relies on the ability of the motor system to recruit a small set of synergies on a single-trial basis and combine them in a task-dependent manner. It is conceivable that this requires a fine tuning of the trial-to-trial relationships between the synergy activations. Here we develop an analytical methodology to address the nature and functional role of trial-to-trial correlations between synergy activation…

Fine-tuningComputer scienceInformation TheoryNeuroscience (miscellaneous)COMMUNICATIONInformation theorylcsh:RC321-571NATURAL MOTOR BEHAVIORSTask (project management)MOVEMENT03 medical and health sciencesCellular and Molecular Neurosciencetask decoding0302 clinical medicinecorrelationsmuscle synergiesMATRIX FACTORIZATIONMotor systemSimilarity (psychology)NOISE CORRELATIONSOriginal Research ArticleSet (psychology)lcsh:Neurosciences. Biological psychiatry. Neuropsychiatry030304 developmental biologysingle-trial analysis0303 health sciencesINDEPENDENCEbusiness.industry[SCCO.NEUR]Cognitive science/NeuroscienceMATHEMATICAL-THEORYSIGNAL (programming language)CORTICAL-NEURONSINDEPENDENCE''Pattern recognitionNEURAL POPULATION[ SCCO.NEUR ] Cognitive science/Neuroscience''NATURAL MOTOR BEHAVIORSArtificial intelligenceNoise (video)SPINAL-CORDbusiness030217 neurology & neurosurgeryNeuroscience
researchProduct

Performance of Fine-Tuning Convolutional Neural Networks for HEp-2 Image Classification

2020

The search for anti-nucleus antibodies (ANA) represents a fundamental step in the diagnosis of autoimmune diseases. The test considered the gold standard for ANA research is indirect immunofluorescence (IIF). The best substrate for ANA detection is provided by Human Epithelial type 2 (HEp-2) cells. The first phase of HEp-2 type image analysis involves the classification of fluorescence intensity in the positive/negative classes. However, the analysis of IIF images is difficult to perform and particularly dependent on the experience of the immunologist. For this reason, the interest of the scientific community in finding relevant technological solutions to the problem has been high. Deep lea…

Fine-tuningComputer scienceautoimmune diseaseHEp-202 engineering and technologylcsh:TechnologyConvolutional neural network030218 nuclear medicine & medical imagingImage (mathematics)lcsh:Chemistry03 medical and health sciences0302 clinical medicine0202 electrical engineering electronic engineering information engineeringautoimmune diseasesGeneral Materials Sciencelcsh:QH301-705.5InstrumentationFluid Flow and Transfer ProcessesContextual image classificationReceiver operating characteristiclcsh:Tbusiness.industryProcess Chemistry and TechnologyDeep learningGeneral EngineeringCNNsdeep learningPattern recognitionGold standard (test)lcsh:QC1-999Settore FIS/07 - Fisica Applicata(Beni Culturali Ambientali Biol.e Medicin)IIF testComputer Science Applicationslcsh:Biology (General)lcsh:QD1-999lcsh:TA1-2040Feature (computer vision)020201 artificial intelligence & image processingArtificial intelligencelcsh:Engineering (General). Civil engineering (General)businessfine-tuninglcsh:PhysicsCNNfeatures extractorApplied Sciences
researchProduct

Deep Convolutional Neural Networks for Fire Detection in Images

2017

Detecting fire in images using image processing and computer vision techniques has gained a lot of attention from researchers during the past few years. Indeed, with sufficient accuracy, such systems may outperform traditional fire detection equipment. One of the most promising techniques used in this area is Convolutional Neural Networks (CNNs). However, the previous research on fire detection with CNNs has only been evaluated on balanced datasets, which may give misleading information on real-world performance, where fire is a rare event. Actually, as demonstrated in this paper, it turns out that a traditional CNN performs relatively poorly when evaluated on the more realistically balance…

Fine-tuningFire detectionComputer sciencebusiness.industryEvent (computing)Training time020101 civil engineeringImage processingPattern recognition02 engineering and technologyReplicateConvolutional neural network0201 civil engineering0202 electrical engineering electronic engineering information engineeringBenchmark (computing)020201 artificial intelligence & image processingArtificial intelligencebusiness
researchProduct

Foetal ECG recovery using dynamic neural networks

2002

Non-invasive electrocardiography has proven to be a very interesting method for obtaining information about the foetus state and thus to assure its well-being during pregnancy. One of the main applications in this field is foetal electrocardiogram (ECG) recovery by means of automatic methods. Evident problems found in the literature are the limited number of available registers, the lack of performance indicators, and the limited use of non-linear adaptive methods. In order to circumvent these problems, we first introduce the generation of synthetic registers and discuss the influence of different kinds of noise to the modelling. Second, a method which is based on numerical (correlation coe…

Finite impulse responseComputer scienceMedicine (miscellaneous)Machine learningcomputer.software_genreSensitivity and SpecificityLeast mean squares filterElectrocardiographyFetal HeartPredictive Value of TestsPregnancyArtificial IntelligenceRobustness (computer science)HumansActive noise controlArtificial neural networkbusiness.industryModels CardiovascularPattern recognitionAdaptive filterIdentification (information)NoiseFemaleNeural Networks ComputerArtificial intelligencebusinesscomputerArtificial Intelligence in Medicine
researchProduct

Ambiguity and complementation in recognizable two-dimensional languages

2008

The theory of one-dimensional (word) languages is well founded and investigated since fifties. From several years, the increasing interest for pattern recognition and image processing motivated the research on two-dimensional or picture languages, and nowadays this is a research field of great interest. A first attempt to formalize the concept of finite state recognizability for two-dimensional languages can be attributed to Blum and Hewitt ([7]) who started in 1967 the study of finite state devices that can define two-dimensional languages, with the aim to finding a counterpart of what regular languages are in one dimension. Since then, many approaches have been presented in the literature…

Finite-state machineTessellationCOMPLEXITYSettore INF/01 - Informaticamedia_common.quotation_subjectPicture LanguageAmbiguityPattern RecognitionPicture languageAlgebraRule-based machine translationRegular languageFormal LanguagePICTURE-LANGUAGES; NONDETERMINISM; COMPLEXITY; AUTOMATAFormal languageRegular expressionAUTOMATAArithmeticPICTURE-LANGUAGESmedia_commonMathematicsNONDETERMINISM
researchProduct