Search results for " Vision"

showing 10 items of 2709 documents

A novel pilot study of automatic identification of EMF radiation effect on brain using computer vision and machine learning

2020

Abstract Electromagnetic field (EMF) radiations from mobile phones and cell tower affect brain of humans and other organisms in many ways. Exposure to EMF could lead to neurological changes causing morphological or chemical changes in the brain and other internal organs. Cellular level analysis to measure and identify the effect of mobile radiations is an expensive and long process as it requires preparing the cell suspension for the analysis. This paper presents a novel pilot study to identify changes in brain morphology under EMF exposure considering drosophila melanogaster as a specimen. The brain is automatically segmented, obtaining microscopic images from which discriminatory geometri…

animal structuresComputer science0206 medical engineeringBiomedical EngineeringHealth InformaticsImage processingFeature selection02 engineering and technologyMachine learningcomputer.software_genre03 medical and health sciencesNaive Bayes classifier0302 clinical medicineComputer visionTime complexityArtificial neural networkbusiness.industryBrain morphometry020601 biomedical engineeringRandom forestSupport vector machineSignal ProcessingArtificial intelligencebusinesscomputer030217 neurology & neurosurgeryBiomedical Signal Processing and Control
researchProduct

Orientation Adaptive Minimal Learning Machine for Directions of Atomic Forces

2021

Machine learning (ML) force fields are one of the most common applications of ML in nanoscience. However, commonly these methods are trained on potential energies of atomic systems and force vectors are omitted. Here we present a ML framework, which tackles the greatest difficulty on using forces in ML: accurate prediction of force direction. We use the idea of Minimal Learning Machine to device a method which can adapt to the orientation of an atomic environment to estimate the directions of force vectors. The method was tested with linear alkane molecules. peerReviewed

atomsComputer sciencebusiness.industryforce directionsmolekyylitOrientation (graph theory)nanotieteetatomitmachine learningkoneoppiminenMinimal learning machineComputer visionmoleculesArtificial intelligencebusiness
researchProduct

SHREC'12 Track: 3D mesh segmentation

2012

International audience; 3D mesh segmentation is a fundamental process in many applications such as shape retrieval, compression, deformation, etc. The objective of this track is to evaluate the performance of recent segmentation methods using a ground-truth corpus and an accurate similarity metric. The ground-truth corpus is composed of 28 watertight models, grouped in five classes (animal, furniture, hand, human and bust) and each associated with 4 ground-truth segmentations done by human subjects. 3 research groups have participated to this track, the accuracy of their segmentation algorithms have been evaluated and compared with 4 other state-of-the-art methods.

benchmarkcontestSHRECI.3.5 I2.103D-meshsegmentation[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV][ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
researchProduct

Less Data Same Information for Event-Based Sensors: A Bioinspired Filtering and Data Reduction Algorithm

2018

Sensors provide data which need to be processed after acquisition to remove noise and extract relevant information. When the sensor is a network node and acquired data are to be transmitted to other nodes (e.g., through Ethernet), the amount of generated data from multiple nodes can overload the communication channel. The reduction of generated data implies the possibility of lower hardware requirements and less power consumption for the hardware devices. This work proposes a filtering algorithm (LDSI&mdash

bioinspired event filteringComputer sciencedynamic vision sensor02 engineering and technologylcsh:Chemical technology01 natural sciencesBiochemistryArticleAnalytical ChemistryReduction (complexity)0202 electrical engineering electronic engineering information engineeringneuromorphic systemslcsh:TP1-1185Electrical and Electronic EngineeringEnginyeria DissenyInstrumentationEnginyeria elèctricaEvent (computing)Noise (signal processing)010401 analytical chemistryFilter (signal processing)Atomic and Molecular Physics and Optics0104 chemical sciencesevent data reductionFPGA implementationspike-basedLookup table020201 artificial intelligence & image processingevent-based sensorsAlgorithmData reductionSensors
researchProduct

The central control of oriented locomotion in insects - towards a neurobiological model

2010

A neurobiological model for the higher control of oriented locomotion in insects is developed here. It is based on studies in a genetic model insect, the fruit fly Drosophila melangaster. Reference is made to other insects, where respective functions are not yet studied in Drosophila. Flies can walk swiftly with up to 16 steps per second, each leg, on almost any substrate and in any orientation to the gravity vector. To bring about this astounding maneuverability and agility the central complex within the insect brain derives directional commands for the leg coordination centers in the thoracic nervous system. Neuroanatomical information is taken into account with regard to the general flow…

biologyComputer scienceOrientation (computer vision)media_common.quotation_subjectfungiInsectNeurophysiologybiology.organism_classificationMotion controlGenetic modelRobotProjection (set theory)Control (linguistics)DrosophilaNeurosciencemedia_commonThe 2010 International Joint Conference on Neural Networks (IJCNN)
researchProduct

Trichromatic color vision in the salamander (Salamandra salamandra)

1995

Spectral sensitivity functions were measured between 334 nm and 683 nm in Salamandra salamandra by utilizing two behavioral reactions: the negative phototactic response, and the prey catching behavior elicited by a moving worm dummy. The action spectrum of the negative phototactic response revealed 3 pronounced maxima: at 360–400 nm, at 520–540 nm, and at 600–640 nm. In the range around 450 nm, there was a “reaction gap” where sensitivity could not be measured. The action spectrum of the prey catching behavior was entirely different: maximal sensitivity was found at 500 nm and at 570 nm. Between 500 nm and 334 nm sensitivity decreased continuously for about 1 log unit (Fig. 6).

biologyPhysiologybusiness.industryColor visionTrichromacybiology.organism_classificationBehavioral NeuroscienceOpticsSpectral sensitivitybiology.animalPhototaxisSalamanderAnimal Science and ZoologySalamandrabusinessEcology Evolution Behavior and SystematicsAction spectrumJournal of Comparative Physiology A
researchProduct

Convergence Analysis of Distributed Set-Valued Information Systems

2016

This paper focuses on the convergence of information in distributed systems of agents communicating over a network. The information on which the convergence is sought is not rep- resented by real numbers, as often in the literature, rather by sets. The dynamics of the evolution of information across the net- work is accordingly described by set-valued iterative maps. While the study of convergence of set-valued iterative maps is highly complex in general, this paper focuses on Boolean maps, which are comprised of arbitrary combinations of unions, intersections, and complements of sets. For these important class of systems, we provide tools to study both global and local convergence. A distr…

boolean dynamic systems0209 industrial biotechnologyClass (set theory)Geographic information systemTheoretical computer scienceBinary encoding boolean dynamic systems con- sensus algorithms convergence cooperative systems distributed information systems set-valued dynamic maps.consensus algorithms02 engineering and technologyBoolean algebraSet (abstract data type)symbols.namesakecooperative systems020901 industrial engineering & automationSettore ING-INF/04 - AutomaticaConvergence (routing)0202 electrical engineering electronic engineering information engineeringInformation systemElectrical and Electronic EngineeringMathematicsReal numberconvergencebusiness.industryset-valued dynamic mapsComputer Science Applications1707 Computer Vision and Pattern Recognitiondistributed information systemsComputer Science ApplicationsLocal convergenceControl and Systems EngineeringsymbolsBinary encoding; boolean dynamic systems; consensus algorithms; convergence; cooperative systems; distributed information systems; set-valued dynamic maps; Electrical and Electronic Engineering; Control and Systems Engineering; Computer Science Applications1707 Computer Vision and Pattern RecognitionBinary encoding020201 artificial intelligence & image processingbusinessIEEE Transactions on Automatic Control
researchProduct

Learning-based multiresolution transforms with application to image compression

2013

In Harten's framework, multiresolution transforms are defined by predicting finer resolution levels of information from coarser ones using an operator, called prediction operator, and defining details (or wavelet coefficients) that are the difference between the exact and predicted values. In this paper we use tools of statistical learning in order to design a more accurate prediction operator in this framework based on a training sample, resulting in multiresolution decompositions with enhanced sparsity. In the case of images, we incorporate edge detection techniques in the design of the prediction operator in order to avoid Gibbs phenomenon. Numerical tests are presented showing that the …

business.industry020206 networking & telecommunicationsPattern recognition02 engineering and technologySample (graphics)Edge detectionGibbs phenomenonsymbols.namesakeWaveletOperator (computer programming)Control and Systems EngineeringCompression (functional analysis)Statistical learning theorySignal Processing0202 electrical engineering electronic engineering information engineeringsymbols020201 artificial intelligence & image processingComputer Vision and Pattern RecognitionArtificial intelligenceElectrical and Electronic EngineeringbusinessSoftwareImage compressionMathematicsSignal Processing
researchProduct

A LDR image expansion method for displaying on HDR screen

2013

International audience

business.industry020207 software engineering02 engineering and technologyTone mappingImage (mathematics)[INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV]Computer graphics (images)[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV][ INFO.INFO-TI ] Computer Science [cs]/Image Processing0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingComputer visionArtificial intelligencebusinessComputingMilieux_MISCELLANEOUSMathematics
researchProduct

Sport Spectators’ Segmentation

2015

International audience

business.industry0502 economics and business05 social sciences050211 marketingSegmentationComputer vision[SHS] Humanities and Social SciencesArtificial intelligenceSociologybusinessComputingMilieux_MISCELLANEOUS050212 sport leisure & tourism[SHS]Humanities and Social Sciences
researchProduct