Search results for " Neural Networks"

showing 10 items of 390 documents

Estimation of brain connectivity through Artificial Neural Networks

2019

Among different methods available for estimating brain connectivity from electroencephalographic signals (EEG), those based on MVAR models have proved to be flexible and accurate. They rely on the solution of linear equations that can be pursued through artificial neural networks (ANNs) used as MVAR model. However, when few data samples are available, there is a lack of accuracy in estimating MVAR parameters due to the collinearity between regressors. Moreover, the assessment procedure is also affected by the lack of data points. The mathematical solution to these problems is represented by penalized regression methods based on l 1 norm, that can reduce collinearity by means of variable sel…

Computer scienceFeature selection02 engineering and technologyConnectivity measurements03 medical and health sciences0302 clinical medicine0202 electrical engineering electronic engineering information engineeringArtificial neural networkbusiness.industryProcess (computing)BrainPattern recognitionElectroencephalographyCollinearityCausalityData pointCausality; Connectivity measurements; Physiological systems modeling - Multivariate signal processingNorm (mathematics)Physiological systems modeling - Multivariate signal processingRegression Analysis020201 artificial intelligence & image processingAnalysis of varianceArtificial intelligenceNeural Networks ComputerbusinessAlgorithms Brain Electroencephalography Regression Analysis Neural Networks Computer030217 neurology & neurosurgeryLinear equationAlgorithms
researchProduct

Robust Resolution-Enhanced Prostate Segmentation in Magnetic Resonance and Ultrasound Images through Convolutional Neural Networks

2021

[EN] Prostate segmentations are required for an ever-increasing number of medical applications, such as image-based lesion detection, fusion-guided biopsy and focal therapies. However, obtaining accurate segmentations is laborious, requires expertise and, even then, the inter-observer variability remains high. In this paper, a robust, accurate and generalizable model for Magnetic Resonance (MR) and three-dimensional (3D) Ultrasound (US) prostate image segmentation is proposed. It uses a densenet-resnet-based Convolutional Neural Network (CNN) combined with techniques such as deep supervision, checkpoint ensembling and Neural Resolution Enhancement. The MR prostate segmentation model was tra…

Computer scienceMR prostate imagingUS prostate imagingINGENIERIA MECANICAconvolutional neural networklcsh:TechnologyConvolutional neural network030218 nuclear medicine & medical imaginglcsh:Chemistry03 medical and health sciences0302 clinical medicinemedicineGeneral Materials Sciencelcsh:QH301-705.5Instrumentation030304 developmental biologyFluid Flow and Transfer Processes0303 health sciencesmedicine.diagnostic_testlcsh:Tbusiness.industryProcess Chemistry and TechnologyConvolutional Neural NetworksUltrasoundResolution (electron density)General EngineeringMagnetic resonance imagingPattern recognitionProstate Segmentationlcsh:QC1-999Computer Science ApplicationsNeural resolution enhancementlcsh:Biology (General)lcsh:QD1-999lcsh:TA1-2040Christian ministryArtificial intelligencelcsh:Engineering (General). Civil engineering (General)Magnetic Resonance and Ultrasound Imagesbusinesslcsh:PhysicsProstate segmentationApplied Sciences
researchProduct

Investigating the cooling rate dependence of amorphous silica: A computer simulation study

1996

We use molecular dynamics computer simulations to study the dependence of the properties of amorphous silica on the cooling rate with which the glass has been produced. In particular we show that the density, the glass transition temperature, the radial distribution function and the distribution of the size of the rings depend on the cooling rate.

Computer simulationDistribution (number theory)ChemistryGeneral Chemical EngineeringThermodynamicsComputer experimentRadial distribution functionCondensed Matter::Disordered Systems and Neural NetworksCondensed Matter::Soft Condensed MatterMolecular dynamicsCooling ratePhysical chemistryAmorphous silicaGlass transitionBerichte der Bunsengesellschaft für physikalische Chemie
researchProduct

Concepts, proto-concepts, and shades of reasoning in neural networks

2019

One of the most important functions of concepts is that of producing classifications; and since there are at least two different types of such things, we better give a preliminary short description of them both. The first kind of classification is based on the existence of a property common to all the things that fall under a concept. The second, instead, relies on similarities between the objects belonging to a certain class A and certain elements of a subclass AS of A, the so-called ‘stereotypes.’ In what follows, we are going to call ‘proto-concepts’ all those concepts whose power of classification depends on stereotypes, leaving the term ‘concepts’ for all the others. The main aim of th…

Concepts proto-concepts stereotypes prototypes neural networks machine learningSettore M-FIL/02 - Logica E Filosofia Della Scienza
researchProduct

L\'evy flights confinement in a parabolic potential and fractional quantum oscillator

2018

We study L\'evy flights confined in a parabolic potential. This has to do with a fractional generalization of ordinary quantum-mechanical oscillator problem. To solve the spectral problem for the fractional quantum oscillator, we pass to the momentum space, where we apply the variational method. This permits to obtain approximate analytical expressions for eigenvalues and eigenfunctions with very good accuracy. Latter fact has been checked by numerical solution of the problem. We point to the realistic physical systems ranging from multiferroics and oxide heterostructures to quantum chaotic excitons, where obtained results can be used.

Condensed Matter - Disordered Systems and Neural Networks
researchProduct

Stability of E' centers induced by 4.7eV laser radiation in SiO2

2007

The kinetics of E' centers (silicon dangling bonds) induced by 4.7eV pulsed laser irradiation in dry fused silica was investigated by in situ optical absorption spectroscopy. The stability of the defects, conditioned by reaction with mobile hydrogen of radiolytic origin, is discussed and compared to results of similar experiments performed on wet fused silica. A portion of E' and hydrogen are most likely generated by laser-induced breaking of Si-H precursors, while an additional fraction of the paramagnetic centers arise from another formation mechanism. Both typologies of E' participate to the reaction with H_2 leading to the post-irradiation decay of the defects. This annealing process is…

Condensed Matter - Materials ScienceAbsorption spectroscopyHydrogenAnnealing (metallurgy)Kineticschemistry.chemical_elementPhysics::OpticsMaterials Science (cond-mat.mtrl-sci)FOS: Physical sciencesDisordered Systems and Neural Networks (cond-mat.dis-nn)Condensed Matter - Disordered Systems and Neural NetworksCondensed Matter PhysicsPhotochemistryLaserElectronic Optical and Magnetic Materialslaw.inventionParamagnetismNuclear magnetic resonancechemistrylawRadiolysisMaterials ChemistryCeramics and CompositesElectron paramagnetic resonance
researchProduct

Bleaching of optical activity induced by UV Laser exposure in natural silica

2004

We report experimental data on two types of natural silica, differing for their OH content, irradiated with UV photons (4.66 eV) from a pulsed Nd:YAG laser. Irradiation induces a reduction of the absorption band at 5.12eV and of the associated emissions at 3.14eV and 4.28eV, ascribed to twofold coordinated Ge (=Ge'') centers pre-existing in our samples. The bleaching is mainly due to the post-irradiation conversion of =Ge'' into the paramagnetic H(II) center via trapping of a H atom. Comparison with literature data points out the peculiarities of silica with a low Ge concentration as regards UV induced transformations.

Condensed Matter - Materials ScienceChemistryAnalytical chemistryMaterials Science (cond-mat.mtrl-sci)FOS: Physical sciencesDisordered Systems and Neural Networks (cond-mat.dis-nn)TrappingCondensed Matter - Disordered Systems and Neural NetworksCondensed Matter PhysicsLaseroptical fibers radiation effects radiation-induced attenuationElectronic Optical and Magnetic Materialslaw.inventionParamagnetismlawAbsorption bandAtomMaterials ChemistryCeramics and CompositesUv laserIrradiationUltraviolet radiation
researchProduct

Structure and transport properties of amorphous aluminium silicates: computer simulation studies

2005

The structure and transport properties of SiO2-Al2O3 melts containing 13 mol% and 47 mol% Al2O3 are investigated by means of large scale molecular dynamics computer simulations. The interactions between the atoms are modelled by a pair potential which is a modified version of the one proposed by Kramer et al. [J. Am. Chem. Soc. 64, 6435 (1991)]. Fully equilibrated melts in the temperature range 6000 K >= T > 2000 K are considered as well as glass configurations, that were obtained by a rapid quench from the lowest melt temperatures. Each system is simulated at two different densities in order to study the effect of pressure on structural and dynamic properties. We find that the Al ato…

Condensed Matter - Materials ScienceDiffusionAb initioMaterials Science (cond-mat.mtrl-sci)FOS: Physical scienceschemistry.chemical_elementThermodynamicsGeologyDisordered Systems and Neural Networks (cond-mat.dis-nn)Atmospheric temperature rangeCondensed Matter - Disordered Systems and Neural NetworksAmorphous solidMolecular dynamicschemistryGeochemistry and PetrologyAluminiumAluminosilicatePhysical chemistryPair potential
researchProduct

Lattice-Boltzmann and finite difference simulations for the permeability of three-dimensional porous media

2002

Numerical micropermeametry is performed on three dimensional porous samples having a linear size of approximately 3 mm and a resolution of 7.5 $\mu$m. One of the samples is a microtomographic image of Fontainebleau sandstone. Two of the samples are stochastic reconstructions with the same porosity, specific surface area, and two-point correlation function as the Fontainebleau sample. The fourth sample is a physical model which mimics the processes of sedimentation, compaction and diagenesis of Fontainebleau sandstone. The permeabilities of these samples are determined by numerically solving at low Reynolds numbers the appropriate Stokes equations in the pore spaces of the samples. The physi…

Condensed Matter - Materials ScienceFinite differenceLattice Boltzmann methodsCompactionMaterials Science (cond-mat.mtrl-sci)FOS: Physical sciencesReynolds numberDisordered Systems and Neural Networks (cond-mat.dis-nn)MechanicsCondensed Matter - Disordered Systems and Neural NetworksGranular materialPhysics::GeophysicsPermeability (earth sciences)symbols.namesakesymbolsCalculusPorosityPorous mediumMathematics
researchProduct

Comparative classical and ab initio Molecular Dynamics study of molten and glassy germanium dioxide

2008

A Molecular Dynamics (MD) study of static and dynamic properties of molten and glassy germanium dioxide is presented. The interactions between the atoms are modelled by the classical pair potential proposed by Oeffner and Elliott (OE) [Oeffner R D and Elliott S R 1998, Phys. Rev. B, 58, 14791]. We compare our results to experiments and previous simulations. In addition, an ab initio method, the so-called Car-Parrinello Molecular Dynamics (CPMD), is applied to check the accuracy of the structural properties, as obtained by the classical MD simulations with the OE potential. As in a similar study for SiO2, the structure predicted by CPMD is only slightly softer than that resulting from the cl…

Condensed Matter - Materials ScienceGermanium dioxideCar–Parrinello molecular dynamicsMaterials scienceDynamic structure factorRelaxation (NMR)Ab initioMaterials Science (cond-mat.mtrl-sci)FOS: Physical sciencesThermodynamicsDisordered Systems and Neural Networks (cond-mat.dis-nn)Condensed Matter - Disordered Systems and Neural NetworksCondensed Matter Physicschemistry.chemical_compoundMolecular dynamicsgermaniamolecular dynamics simulationchemistryAb initio quantum chemistry methodsGeneral Materials SciencePair potential
researchProduct