Search results for "neural net"

showing 10 items of 1388 documents

Reduced Reference Mesh Visual Quality Assessment Based on Convolutional Neural Network

2018

3D meshes are usually affected by various visual distortions during their transmission and geometric processing. In this paper we propose a reduced reference method for mesh visual quality assessment. The method compares features extracted from the distorted mesh and the original one using a convolutional neural network in order to estimate the visual quality score. The perceptual distance between two meshes is computed as the Kullback-Leibler divergence between the two sets of feature vectors. Experimental results from two subjective databases (LIRIS masking database and LIRIS/EPFL general purpose database) and comparisons with seven objective metrics cited in the state-of-the-art demonstr…

business.industryComputer science[INFO.INFO-TS] Computer Science [cs]/Signal and Image ProcessingFeature vectorFeature extractionPattern recognition02 engineering and technology01 natural sciencesConvolutional neural networkVisualization010309 optics[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing0103 physical sciencesQuality ScoreMetric (mathematics)0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingPolygon meshArtificial intelligenceDivergence (statistics)businessComputingMilieux_MISCELLANEOUS
researchProduct

Computer Programming Aptitude Test as a Tool for Reducing Student Attrition

2015

Submitted to the VTR conference to be held in Rezekne, June 2015

business.industryComputer sciencemedia_common.quotation_subjectdata analysisComputer programmingaptitude test; attrition rate; computer science education; data analysisaptitude testmedicine.diseaseField (computer science)Test (assessment)attrition rateAction planComputingMilieux_COMPUTERSANDEDUCATIONmedicineMathematics educationcomputer science educationAttritionAptitudebusinessDropout (neural networks)media_commonEnvironment. Technology. Resources. Proceedings of the International Scientific and Practical Conference
researchProduct

Hybrid 3D-ResNet Deep Learning Model for Automatic Segmentation of Thoracic Organs at Risk in CT Images

2020

In image radiation therapy, accurate segmentation of organs at risk (OARs) is a very essential task and has clinical applications in cancer treatment. The segmentation of organs close to lung, breast, or esophageal cancer is a routine and time-consuming process. The automatic segmentation of organs at risk would be an essential part of treatment planning for patients suffering radiotherapy. The position and shape variation, morphology inherent and low soft tissue contrast between neighboring organs across each patient’s scans is the challenging task for automatic segmentation of OARs in Computed Tomography (CT) images. The objective of this paper is to use automatic segmentation of the orga…

business.industryComputer sciencemedicine.medical_treatmentDeep learningVolumetric segmentationPattern recognition02 engineering and technologyResidual neural network030218 nuclear medicine & medical imagingRadiation therapy03 medical and health sciences0302 clinical medicine0202 electrical engineering electronic engineering information engineeringmedicineAutomatic segmentation020201 artificial intelligence & image processingSegmentationPyramid (image processing)Artificial intelligencebusinessRadiation treatment planning2020 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM)
researchProduct

Dynamics of Vertebral Column Observed by Stereovision and Recurrent Neural Network Model

2005

A new non-invasive method for investigation of movement of selected points on the vertebral column is presented. The registration of position of points marked on patient's body is performed by 4 infrared cameras. This experiment enables to reconstruct 3-dimensional trajectories of displacement of marked points. We introduce recurrent neural networks as formal nonlinear dynamical models of each point trajectory. These models are based only on experimental data and are set up of minimal number of parameters. Therefore they are suitable for pattern recognition problems.

business.industryDynamics (mechanics)Displacement (vector)Set (abstract data type)Nonlinear systemRecurrent neural networkmedicine.anatomical_structurePosition (vector)Pattern recognition (psychology)medicineComputer visionArtificial intelligencebusinessVertebral columnMathematics
researchProduct

Deep learning model deploying on embedded skin cancer diagnostic device

2020

The number of research papers, where neural networks are applied in medical image analysis is growing. There is a proof that Convolutional Neural Networks (CNN) are able to differentiate skin cancer from nevi with greater accuracy than experienced specialists on average (sensitivity 82% and 73% accordingly).1 Team's latest research2 allows achieving even greater accuracy, by using specific narrow-band illumination. Nevertheless, the overall probability of early skin cancer detection depends on the availability of diagnostic tools. If screening tools will be available to a high number of general practices, the chance of disease detection will increase. The previous research3 shows that scala…

business.product_categoryArtificial neural networkComputer sciencebusiness.industryDeep learningReal-time computingProcess (computing)Cloud computingConvolutional neural networkScalabilityInternet accessSensitivity (control systems)Artificial intelligencebusinessBiophotonics—Riga 2020
researchProduct

Using a neural network for qualitative and quantitative predictions of weld integrity in solid bonding dominated processes

2014

Solid-state bonding occurs in several manufacturing processes, as Friction Stir Welding, Porthole Die Extrusion and Roll Bonding. Proper conditions of pressure, temperature, strain and strain rate are needed in order to get effective bonding in the final component. In the paper, a neural network is set up, trained and used to predict the bonding occurrence starting from the results of specific numerical models developed for each process. The Plata-Piwnik criterion was used in order to define a quantitative parameter taking into account the effectiveness of the bonding. Excellent predictive capability of the network is obtained for each process.

business.product_categoryMaterials scienceArtificial neural networkMechanical EngineeringMetallurgyFriction Stir WeldingProcess (computing)Mechanical engineeringWeldingStrain rateNeural networkAluminum alloysComputer Science Applicationslaw.inventionRoll bondinglawModeling and SimulationDie (manufacturing)Friction stir weldingGeneral Materials ScienceExtrusionBonding criterionbusinessCivil and Structural EngineeringComputers & Structures
researchProduct

Monte Carlo simulation of the glass transition in polymeric systems: Recent developments

1995

Abstract The bond fluctuation model on square and s.c. lattices is used as a coarse-grained model for flexible polymers in dense melts. Using an energy that favours long bonds, a conflict is created between the tendency of the bonds to stretch at low temperatures and packing constraints. This simple concept of ‘geometric frustration’ leads to glass transition. Both static and dynamic properties of this model are investigated by Monte Carlo simulations, paying attention to effects found by varying the cooling rate and the chain length N of the polymers. In two and three spatial dimensions an effective (cooling-rate dependent) glass transition temperature T g can be defined, where the system …

chemistry.chemical_classificationChemistryGeneral Chemical Engineeringmedia_common.quotation_subjectMonte Carlo methodGeneral Physics and AstronomyThermodynamicsFrustrationPolymerCondensed Matter::Disordered Systems and Neural NetworksSquare (algebra)Chain lengthCooling rateDiffusion (business)Glass transitionmedia_commonPhilosophical Magazine B
researchProduct

Polymer Films in the Normal-Liquid and Supercooled State: A Review of Recent Monte Carlo Simulation Results

2000

This paper reviews recent Monte Carlo simulation studies of the glassy behavior in thin polymer films. The simulations employ a version of the bond-fluctuation lattice model, in which the glass transition is driven by the competition between a stiffening of the polymers and their dense packing in the melt. The melt is geometrically confined between two impenetrable walls separated by distances ranging from once to about fifteen times the bulk radius of gyration. The confinement influences static and dynamic properties of the films: Chains close to the wall preferentially orient parallel to it. This orientation tendency propagates through the film and leads to a layer structure at low temper…

chemistry.chemical_classificationLattice model (finance)Materials scienceCondensed matter physicsMonte Carlo methodRelaxation (NMR)FOS: Physical sciencesGyration tensorSurfaces and InterfacesPolymerDisordered Systems and Neural Networks (cond-mat.dis-nn)Condensed Matter - Soft Condensed MatterCondensed Matter - Disordered Systems and Neural NetworksCondensed Matter::Soft Condensed MatterColloid and Surface ChemistrychemistryRadius of gyrationSoft Condensed Matter (cond-mat.soft)Physical and Theoretical ChemistryGlass transitionSupercooling
researchProduct

Disorder Classification of the Vibrational Spectra of Modern Glasses

2021

Using the coherent-potential approximation in heterogeneous-elasticity theory with a log-normal distribution of elastic constants for the description of the Raman spectrum and the temperature dependence of the specifi?c heat, we are able to reconstruct the vibrational density of states and characteristic descriptors of the elastic heterogeneity of a wide range of glassy materials. These descriptors are the non-affi?ne contribution to the shear modulus, the mean-square fluctuation of the local elasticity, and its correlation length. They enable a physical classification scheme for disorder in modern, industrially relevant glass materials. We apply our procedure to a broad range of real-world…

chemistry.chemical_classificationMaterials scienceCondensed matter physicsChalcogenidePolymerElasticity (physics)Condensed Matter::Disordered Systems and Neural NetworksPoisson's ratioShear modulussymbols.namesakechemistry.chemical_compoundFragilitychemistryPosition (vector)symbolsRaman spectroscopy
researchProduct

Effect of physical aging on the low-frequency vibrational density of states of a glassy polymer

2003

The effects of the physical aging on the vibrational density of states (VDOS) of a polymeric glass is studied. The VDOS of a poly(methyl methacrylate) glass at low-energy (<15 meV), was determined from inelastic neutron scattering at low-temperature for two different physical thermodynamical states. One sample was annealed during a long time at temperature lower than Tg, and another was quenched from a temperature higher than Tg. It was found that the VDOS around the boson peak, relatively to the one at higher energy, decreases with the annealing at lower temperature than Tg, i.e., with the physical aging.

chemistry.chemical_classificationMaterials sciencePhysical agingAnnealing (metallurgy)FOS: Physical sciencesGeneral Physics and AstronomyThermodynamicsDisordered Systems and Neural Networks (cond-mat.dis-nn)PolymerCondensed Matter - Disordered Systems and Neural NetworksLow frequency01 natural sciencesLower temperatureInelastic neutron scattering010305 fluids & plasmaschemistry.chemical_compoundVibrational density of stateschemistry0103 physical sciences[PHYS.COND.CM-MS]Physics [physics]/Condensed Matter [cond-mat]/Materials Science [cond-mat.mtrl-sci]Methyl methacrylate010306 general physicsEurophysics Letters (EPL)
researchProduct