Search results for "RECOGNITION"

showing 10 items of 3607 documents

On the pattern recognition and classification of stochastically episodic events

2012

Published version of a chapter published in the book: Transactions on Compuational Collective Intelligence VI. Also available from the publisher at: http://dx.doi.org/10.1007/978-3-642-29356-6_1 Researchers in the field of Pattern Recognition (PR) have traditionally presumed the availability of a representative set of data drawn from the classes of interest, say ω 1 and ω 2 in a 2-class problem. These samples are typically utilized in the development of the system’s discriminant function. It is, however, widely recognized that there exists a particularly challenging class of PR problems for which a representative set is not available for the second class, which has motivated a great deal of…

VDP::Mathematics and natural science: 400::Information and communication science: 420::Knowledge based systems: 425stochastic eventsPattern Recognitionerroneous datarare events
researchProduct

Methodology for the estimation of the increase in time loss due to future increase in tropical cyclone intensity in Japan

2009

Published version of an article from the journal: Climatic Change. The original publication is available at Spingerlink. http://dx.doi.org/10.1007/s10584-009-9725-9 The present paper develops a methodology for estimating the risks and consequences of possible future increases in tropical cyclone intensities that would allow policy makers to relatively quickly evaluate the cost of different mitigation strategies. The methodology simulates future tropical cyclones by modifying the intensity of historical tropical cyclones between the years 1978 and 2007. It then uses a Monte Carlo Simulation to obtain the expected number of hours that a certain area can expect to be affected by winds of a giv…

VDP::Mathematics and natural science: 400::Mathematics: 410::Applied mathematics: 413Atmospheric ScienceGlobal and Planetary ChangeDowntimeVDP::Mathematics and natural science: 400::Geosciences: 450::Meteorology: 453Severe weatherMeteorologybusiness.industryGlobal warmingVDP::Social science: 200::Urbanism and physical planning: 230::Spatial territorial planning: 238Climate changeStormComputingMethodologies_PATTERNRECOGNITIONEnvironmental scienceEconomic impact analysisTropical cyclonebusinessRisk management
researchProduct

Mathematical modeling of a vehicle crash test based on elasto-plastic unloading scenarios of spring-mass models

2011

Published version of an article in the journal: The International Journal of Advanced Manufacturing Technology. Also available from the publisher on SpringerLink: htp://dx.doi.org/10.1007/s00170-010-3056-x This paper investigates the usability of spring which exhibit nonlinear force-deflection characteristic in the area of mathematical modeling of vehicle crash. We present a method which allows us to obtain parameters of the spring-mass model basing on the full-scale experimental data analysis. Since vehicle collision is a dynamic event, it involves such phenomena as rebound and energy dissipation. Three different spring unloading scenarios (elastic, plastic, and elasto-plastic) are covered…

VDP::Mathematics and natural science: 400::Mathematics: 410::Applied mathematics: 413EngineeringTotal crash energyVehicle crashKinematicsIndustrial and Manufacturing EngineeringCoefficient of restitution; Spring-mass model; Total crash energy; Unloading stiffness; Vehicle crash; Control and Systems Engineering; Software; Mechanical Engineering; Computer Science Applications1707 Computer Vision and Pattern Recognition; Industrial and Manufacturing EngineeringSimulationEvent (probability theory)Coefficient of restitutionbusiness.industrySpring-mass modelMechanical EngineeringVDP::Technology: 500::Mechanical engineering: 570UsabilityComputer Science Applications1707 Computer Vision and Pattern RecognitionStructural engineeringDissipationCollisionComputer Science ApplicationsNonlinear systemUnloading stiffnessSpring (device)Control and Systems EngineeringCoefficient of restitutionbusinessSoftware
researchProduct

A novel active contour model for unsupervised low-key image segmentation

2013

Published version of an article in the journal: Central European Journal of Engineering. Also available from the publisher at: http://dx.doi.org/10.2478/s13531-012-0050-0 Unsupervised image segmentation is greatly useful in many vision-based applications. In this paper, we aim at the unsupervised low-key image segmentation. In low-key images, dark tone dominates the background, and gray level distribution of the foreground is heterogeneous. They widely exist in the areas of space exploration, machine vision, medical imaging, etc. In our algorithm, a novel active contour model with the probability density function of gamma distribution is proposed. The flexible gamma distribution gives a bet…

VDP::Mathematics and natural science: 400::Mathematics: 410::Applied mathematics: 413Environmental EngineeringComputer scienceMachine visionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONAerospace EngineeringInitializationScale-space segmentationProbability density functionGamma distributionGeneral Materials ScienceComputer visionactive contour modelElectrical and Electronic Engineeringimage segmentationCivil and Structural EngineeringActive contour modellow-key imageSegmentation-based object categorizationbusiness.industryMechanical EngineeringVDP::Technology: 500::Mechanical engineering: 570Pattern recognitionImage segmentationEngineering (General). Civil engineering (General)Computer Science::Computer Vision and Pattern RecognitionArtificial intelligenceTA1-2040businessOpen Engineering
researchProduct

Investigation of vehicle crash modeling techniques: theory and application

2013

Published version of an article in the journal: The International Journal of Advanced Manufacturing Technology. Also available from the publisher at: http://dx.doi.org/10.1007/s00170-013-5320-3 Creating a mathematical model of a vehicle crash is a task which involves considerations and analysis of different areas which need to be addressed because of the mathematical complexity of a crash event representation. Therefore, to simplify the analysis and enhance the modeling process, in this work, a brief overview of different vehicle crash modeling methodologies is proposed. The acceleration of a colliding vehicle is measured in its center of gravity—this crash pulse contains detailed informati…

VDP::Mathematics and natural science: 400::Mathematics: 410::Applied mathematics: 413Feedforward neural network; Lumped parameter models; Multiresolution analysis; Vehicle crash modeling; Control and Systems Engineering; Software; Mechanical Engineering; Computer Science Applications1707 Computer Vision and Pattern Recognition; Industrial and Manufacturing EngineeringEvent (computing)Computer scienceReliability (computer networking)Mechanical Engineeringvehicle crash modelingVDP::Technology: 500::Mechanical engineering: 570lumped parameter modelsCrashControl engineeringComputer Science Applications1707 Computer Vision and Pattern RecognitionCollisionIndustrial and Manufacturing EngineeringComputer Science Applicationsmultiresolution analysisAutoregressive modelControl and Systems Engineeringfeedforward neural networkRepresentation (mathematics)SimulationSoftwareMotor vehicle crash
researchProduct

Multi-class pairwise linear dimensionality reduction using heteroscedastic schemes

2010

Accepted version of an article published in the journal: Pattern Recognition. Published version on Sciverse: http://dx.doi.org/10.1016/j.patcog.2010.01.018 Linear dimensionality reduction (LDR) techniques have been increasingly important in pattern recognition (PR) due to the fact that they permit a relatively simple mapping of the problem onto a lower-dimensional subspace, leading to simple and computationally efficient classification strategies. Although the field has been well developed for the two-class problem, the corresponding issues encountered when dealing with multiple classes are far from trivial. In this paper, we argue that, as opposed to the traditional LDR multi-class schemes…

VDP::Mathematics and natural science: 400::Mathematics: 410::Applied mathematics: 413business.industryVDP::Mathematics and natural science: 400::Information and communication science: 420::Algorithms and computability theory: 422Dimensionality reductionDecision treePattern recognitionBayes classifierLinear discriminant analysisLinear subspaceWeightingArtificial IntelligenceSignal ProcessingPairwise comparisonComputer Vision and Pattern RecognitionArtificial intelligencebusinessAlgorithmSoftwareSubspace topologyMathematics
researchProduct

Mixed l-/l1 fault detection observer design for positive switched systems with time-varying delay via delta operator approach

2014

Published version of an article in the journal: International Journal of Control, Automation and Systems. Also available from the publisher at: http://dx.doi.org/10.1007/s12555-013-0466-1 This paper investigates the problem of fault detection observer design for positive switched systems with time-varying delay via delta operator approach. A new fault sensitivity measure, called l-index, is proposed. The l- fault detection observer design and multi-objective l -/l1 fault detection observer design problems are addressed. Based on the average dwell time approach and the piecewise copositive type Lyapunov-Krasovskii functional method in delta domain, sufficient conditions for the existence of …

VDP::Technology: 500::Mechanical engineering: 570Computer Science Applications1707 Computer Vision and Pattern RecognitionDelta operatorMechatronicsfault sensitivityFault (power engineering)positive switched systemsMeasure (mathematics)VDP::Mathematics and natural science: 400::Mathematics: 410::Analysis: 411Fault detection and isolationfault detectionComputer Science Applicationsdelta operatorDwell timeControl theoryControl and Systems EngineeringPiecewiseAverage dwell time; delta operator; fault detection; fault sensitivity; positive switched systems; Control and Systems Engineering; Computer Science Applications1707 Computer Vision and Pattern RecognitionSensitivity (control systems)Average dwell timeMathematics
researchProduct

Spectral adaptation of hyperspectral flight lines using VHR contextual information

2014

Abstract: Due to technological constraints, hyperspectral earth observation imagery are often a mosaic of overlapping flight lines collected in different passes over the area of interest. This causes variations in aqcuisition conditions such that the reflected spectrum can vary significantly between these flight lines. Partly, this problem is solved by atmospherical correction, but residual spectral differences often remain. A probabilistic domain adaptation framework based on graph matching using Hidden Markov Random Fields was recently proposed for transforming hyperspectral data from one image to better correspond to the other. This paper investigates the use of scale and angle invariant…

VHR imageryHyperspectral imaginggraph matchingComputer sciencebusiness.industrydomain adaptationPhysicsHyperspectral imagingPattern recognitionFilter (signal processing)Rendering (computer graphics)Computer Science::Computer Vision and Pattern RecognitionFull spectral imagingtextural featuresComputer visionArtificial intelligenceHidden Markov random fieldHidden Markov modelbusiness
researchProduct

Evaluación multicriterio de políticas de uso y gestión de recursos naturales

2014

The purpose of this work is show the characteristics of different environmental economic assessment methodologies, and exposes a case study where possible alternatives addressed to reduce the contamination of a bay with multicriteria approach are evaluated. The results obtained show the effectiveness of multicriteria analysis to evaluate the alternatives for solution of contamination problem in a bay. Economic evaluation of the contamination effects integrated to the environmental, social and economic dimensions through multicriteria techniques allows an alternative planning to solve the environmental problem studied, providing the right decision.

Valorização Econômica Ambiental; Métodos Multicritério; Recursos Naturais; Meio Ambiente.ComputingMethodologies_PATTERNRECOGNITIONValoración Económica Ambiental; Métodos Multicriterio; Recursos Naturales; Medio Ambiente.GeneticsAnimal Science and ZoologyEnvironmental Economic Valuation; Multicriteria Methods; Natural Resources; Environment.Revista Eletrônica de Estratégia & Negócios
researchProduct

A Multiple Case Study of Artificial Intelligent System Development in Industry

2020

There is a rapidly increasing amount of Artificial Intelligence (AI) systems developed in recent years, with much expectation on its capacity of innovation and business value generation. However, the promised value of AI systems in specific business contexts might not be understood, and further integrated into the development processes. We wanted to understand how software engineering processes and practices can be applied to develop AI systems in a fast-faced, business-driven manner. As the first step, we explored contextual factors of AI development and the connections between AI developments to business opportunities. We conducted 12 semi-structured interviews in seven companies in Brazi…

Value (ethics)AI business patternComputer scienceBusiness opportunityohjelmistotuotanto02 engineering and technologytekoälyGeneralLiterature_MISCELLANEOUSSoutheast asia020204 information systems0202 electrical engineering electronic engineering information engineeringSystem developmentbusiness.industrySEMATSoftware developmentartificial intelligent system020207 software engineeringBusiness valueComputingMethodologies_PATTERNRECOGNITIONbusiness opportunitysoftware developmentMultiple caseArtificial intelligenceohjelmistoliiketoimintabusinessohjelmistokehitysPivotAi systemssoftware engineering
researchProduct