Search results for "Convolution"

showing 10 items of 334 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

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

Mathematical Models for Restoration of Baroque Paintings

2006

In this paper we adapt different techniques for image deconvolution, to the actual restoration of works of arts (mainly paintings and sculptures) from the baroque period. We use the special characteristics of these works in order to both restrict the strategies and benefit from those properties. We propose an algorithm which presents good results in the pieces we have worked. Due to the diversity of the period and the amount of artists who made it possible, the algorithms are too general even in this context. This is a first approach to the problem, in which we have assumed very common and shared features for the works of art. The flexibility of the algorithm, and the freedom to choose some…

Flexibility (engineering)Blind deconvolutionPaintingComputer sciencerestrictbusiness.industryImage processingContext (language use)Artificial intelligencebusinessThe artsPeriod (music)
researchProduct

Robustness, Stability, and Fidelity of Explanations for a Deep Skin Cancer Classification Model

2022

Skin cancer is one of the most prevalent of all cancers. Because of its being widespread and externally observable, there is a potential that machine learning models integrated into artificial intelligence systems will allow self-screening and automatic analysis in the future. Especially, the recent success of various deep machine learning models shows promise that, in the future, patients could self-analyse their external signs of skin cancer by uploading pictures of these signs to an artificial intelligence system, which runs such a deep learning model and returns the classification results. However, both patients and dermatologists, who might use such a system to aid their work, need to …

Fluid Flow and Transfer Processesexplainable artificial intelligenceskin cancerProcess Chemistry and TechnologyGeneral Engineeringconvolutional neural networkdeep learningsyväoppimineninterpretable machine learningpäätöksentukijärjestelmätneuroverkotdiagnostiikkaComputer Science Applicationsihosyöpälocal model-agnostic explanationskoneoppiminenGeneral Materials ScienceInstrumentationexplainable artificial intelligence; interpretable machine learning; skin cancer; convolutional neural network; deep learning; integrated gradients; local model-agnostic explanationsintegrated gradientsApplied Sciences
researchProduct

Semi-automated and interactive segmentation of contrast-enhancing masses on breast DCE-MRI using spatial fuzzy clustering

2022

Abstract Multiparametric Magnetic Resonance Imaging (MRI) is the most sensitive imaging modality for breast cancer detection and is increasingly playing a key role in lesion characterization. In this context, accurate and reliable quantification of the shape and extent of breast cancer is crucial in clinical research environments. Since conventional lesion delineation procedures are still mostly manual, automated segmentation approaches can improve this time-consuming and operator-dependent task by annotating the regions of interest in a reproducible manner. In this work, a semi-automated and interactive approach based on the spatial Fuzzy C-Means (sFCM) algorithm is proposed, used to segme…

Fuzzy clusteringUnsupervised fuzzy clusteringbusiness.industryComputer scienceBiomedical EngineeringHealth InformaticsPattern recognitionImage processingContext (language use)Image segmentationComputer-assisted lesion detectionMagnetic Resonance ImagingThresholdingConvolutional neural networkBreast cancer; Computer-assisted lesion detection; Magnetic Resonance Imaging; Semi-automated segmentation; Spatial information; Unsupervised fuzzy clusteringBreast cancerSignal ProcessingSemi-automated segmentationSpatial informationSegmentationArtificial intelligencebusinessMultiparametric Magnetic Resonance ImagingBiomedical Signal Processing and Control
researchProduct

Separate regression modelling of the Gaussian and Exponential components of an EMG response from respiratory physiology.

2014

If Y1 \sim N(\mu ;\sigma^2) and Y2 \sim Exp(\nu), with Y1 independent of Y2, then their sum Y = Y1 +Y2 follows an Exponentially Modified Gaussian (EMG) distribution. In many applications it is of interest to model the two components separately, in order to investigate their (possibly) different important predictors. We show how this can be done through a GAMLSS with EMG response, and apply this separate regression modelling strategy to a dataset on lung function variables from the SAPALDIA cohort study.

GAMLSSExponentially Modified Gaussian distributionDeconvolutionSettore SECS-S/01 - Statistica
researchProduct

FCA-Net: Adversarial Learning for Skin Lesion Segmentation Based on Multi-Scale Features and Factorized Channel Attention

2019

International audience; Skin lesion segmentation in dermoscopic images is still a challenge due to the low contrast and fuzzy boundaries of lesions. Moreover, lesions have high similarity with the healthy regions in terms of appearance. In this paper, we propose an accurate skin lesion segmentation model based on a modified conditional generative adversarial network (cGAN). We introduce a new block in the encoder of cGAN called factorized channel attention (FCA), which exploits both channel attention mechanism and residual 1-D kernel factorized convolution. The channel attention mechanism increases the discriminability between the lesion and non-lesion features by taking feature channel int…

General Computer ScienceComputer science02 engineering and technologyResidualFuzzy logic030218 nuclear medicine & medical imagingConvolutionconditional generative adversarial network03 medical and health sciencesSkin lesion0302 clinical medicineGradient vector flow0202 electrical engineering electronic engineering information engineeringGeneral Materials ScienceSegmentation[INFO]Computer Science [cs]channel attentionbusiness.industryresidual convolutionGeneral EngineeringPattern recognitionKernel (image processing)factorized kernel020201 artificial intelligence & image processingArtificial intelligencelcsh:Electrical engineering. Electronics. Nuclear engineeringbusinessEncoderlcsh:TK1-9971Dermoscopy images
researchProduct

Bartlett formalism generating functions and Z-transforms in fluctuation and noise theory

1983

Abstract “La theorie des fonctions generatrices s'adapte elle meme et avec la plus grande generalite aux questions des probabilite les plus difficiles.” (Laplace, 1812) “An important part of probability theory consists of the derivation of the probability distribution of the sum of n random variables, each of which obeys a given probability law, and the development of asymptotic forms of these distributions valid for increasing n. Probability generating functions owe their dominant position to the simplification they permit to both problems. Their employment to obtain the successive moments of a probability distribution and to solve the difference equations of probability theory is ancillar…

Generating FunctionPopulation DynamicBartlett formalismMoment-generating functionNoise TheoryConvolution of probability distributionsAlgebra of random variablesStochastic ProceNuclear Energy and EngineeringProbability theoryJoint probability distributionCalculusApplied mathematicsProbability distributionRandom variableSettore ING-IND/19 - Impianti NucleariLaw of the unconscious statisticianMathematicsAnnals of Nuclear Energy
researchProduct

Domain Adaptation of Landsat-8 and Proba-V Data Using Generative Adversarial Networks for Cloud Detection

2019

Training machine learning algorithms for new satellites requires collecting new data. This is a critical drawback for most remote sensing applications and specially for cloud detection. A sensible strategy to mitigate this problem is to exploit available data from a similar sensor, which involves transforming this data to resemble the new sensor data. However, even taking into account the technical characteristics of both sensors to transform the images, statistical differences between data distributions still remain. This results in a poor performance of the methods trained on one sensor and applied to the new one. In this this work, we propose to use the generative adversarial networks (G…

Ground truth010504 meteorology & atmospheric sciencesComputer scienceRemote sensing application0211 other engineering and technologies02 engineering and technologycomputer.software_genre01 natural sciencesConvolutional neural networkData miningAdaptation (computer science)computerGenerative grammar021101 geological & geomatics engineering0105 earth and related environmental sciencesIGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium
researchProduct