Search results for " Pattern recognition"

showing 10 items of 1050 documents

Large-scale nonlinear dimensionality reduction for network intrusion detection

2017

International audience; Network intrusion detection (NID) is a complex classification problem. In this paper, we combine classification with recent and scalable nonlinear dimensionality reduction (NLDR) methods. Classification and DR are not necessarily adversarial, provided adequate cluster magnification occurring in NLDR methods like $t$-SNE: DR mitigates the curse of dimensionality, while cluster magnification can maintain class separability. We demonstrate experimentally the effectiveness of the approach by analyzing and comparing results on the big KDD99 dataset, using both NLDR quality assessment and classification rate for SVMs and random forests. Since data involves features of mixe…

intrusion detection[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV][ SPI.SIGNAL ] Engineering Sciences [physics]/Signal and Image processing[INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG][ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV][ INFO.INFO-LG ] Computer Science [cs]/Machine Learning [cs.LG][STAT.ML] Statistics [stat]/Machine Learning [stat.ML][INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]ComputingMethodologies_PATTERNRECOGNITION[STAT.ML]Statistics [stat]/Machine Learning [stat.ML][INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]Gower[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing[ STAT.ML ] Statistics [stat]/Machine Learning [stat.ML][SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processingdimensionality reduction
researchProduct

A study of the relationship between regulatory systems, assessment e locomotion, and online learning groups

2011

The present paper examines the relationship between assessment, locomotion and attitudes and learning outcomes in a Computer-supported collaborative learning (CSCL) framework. Results showed that regulatory mode predicted exam marks, numbers of tasks completed, messages sent and attitudes towards the course and the ingroup. The theoretical implications and some reflections about CSCL and Regulatory-mode Theory (RMT) are presented.

lcsh:Theory and practice of educationCSCL3304CSCL Regulatory-mode theory higher education assessment locomotion.higher educationassessmentlocomotion.Computer Science Applications1707 Computer Vision and Pattern RecognitionRegulatory-mode theorySettore M-PSI/05 - Psicologia SocialeLocomotionlcsh:LB5-3640
researchProduct

Efficient contour-based annotation by iterative deep learning for organ segmentation from volumetric medical images

2022

Abstract Purpose Training deep neural networks usually require a large number of human-annotated data. For organ segmentation from volumetric medical images, human annotation is tedious and inefficient. To save human labour and to accelerate the training process, the strategy of annotation by iterative deep learning recently becomes popular in the research community. However, due to the lack of domain knowledge or efficient human-interaction tools, the current AID methods still suffer from long training time and high annotation burden. Methods We develop a contour-based annotation by iterative deep learning (AID) algorithm which uses boundary representation instead of voxel labels to incorp…

lääketieteellinen tekniikkaorgan segmentationBiomedical Engineeringdeep learningsyväoppimineninteractive segmentationHealth InformaticsGeneral MedicineComputer Graphics and Computer-Aided Designmedical image annotationComputer Science ApplicationsalgoritmitRadiology Nuclear Medicine and imagingSurgeryComputer Vision and Pattern RecognitionInternational Journal of Computer Assisted Radiology and Surgery
researchProduct

E-Fairs: a Cyber-Physical System for Aggregation and Economy of Scale in e-Commerce

2018

In recent years, the e-commerce arena has deeply changed because of the advent of new business models and the growing weight of huge global actors like Amazon. Some business models create competition between users, and the product price tends to rise (e.g., online auctions); other models, including group-buying, make users cooperate, and the price tends to go down. The present study extends the group-buying model and proposes a cyber-physical system called e-fair, in which both sellers and buyers are grouped to negotiate on a specific product or service. E-fairs minimize the global purchase price and the shipping resources respectively with the aggregation of demand and supply as well as or…

media_common.quotation_subjectEnergy Engineering and Power TechnologyE-commerceBusiness modelIndustrial and Manufacturing Engineeringe-fairSupply and demandCompetition (economics)aggregation; e-fair; group buying; the blockchainArtificial Intelligencegroup buyingCommon value auctionInstrumentationIndustrial organizationmedia_commonSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniGroup buyingRenewable Energy Sustainability and the Environmentbusiness.industryaggregationComputer Science Applications1707 Computer Vision and Pattern RecognitionProduct (business)Computer Networks and CommunicationService (economics)the blockchainbusiness2018 IEEE 4th International Forum on Research and Technology for Society and Industry (RTSI)
researchProduct

Automated approach for indirect immunofluorescence images classification based on unsupervised clustering method

2018

Autoimmune diseases (ADs) are a collection of many complex disorders of unknown aetiology resulting in immune responses to self-antigens and are thought to result from interactions between genetic and environmental factors. ADs collectively are amongst the most prevalent diseases in the U.S., affecting at least 7% of the population. The diagnosis of ADs is very complex, the standard screening methods provides seeking and recognizing of Antinuclear Antibodies (ANA) by Indirect ImmunoFluorescence (IIF) based on HEp-2 cells. In this paper an automatic system able to identify and classify the Centromere pattern is presented. The method is based on the grouping of centromeres present on the cell…

medical disorderComputer sciencePopulationFeature extraction02 engineering and technologybiomedical optical imagingmedical image processing030218 nuclear medicine & medical imaging03 medical and health sciences0302 clinical medicineImage textureblood0202 electrical engineering electronic engineering information engineeringSegmentationimage texturecellular biophysicsCluster analysiseducationimage segmentationdiseaseeducation.field_of_studyIndirect immunofluorescenceContextual image classificationbusiness.industryfeature extractionPattern recognitionImage segmentationSettore FIS/07 - Fisica Applicata(Beni Culturali Ambientali Biol.e Medicin)020201 artificial intelligence & image processingfluorescenceComputer Vision and Pattern RecognitionArtificial intelligencebusinessSoftwareimage classificationIET Computer Vision
researchProduct

Ocular counterrolling. Some practical considerations of a new evaluation method for diagnostic purposes.

1986

Ocular counterrolling (OCR) data taken from the literature (12 publications) were used to test the best fit (least-square fit) of these measurements with respect to three mathematical models: a sine relation between OCR and the lateral tilt stimulus, a complex cosine-square relation, and a logarithmic relation between OCR gain and tilt. The latter proved to be the best fitting function. On the basis of this model, we attempted to define a physiological transfer function between OCR gain and tilt, which could serve as a reference of normal population, assuming healthy subjects for the investigations applied. Comparison of this physiological range with pathological data demonstrated marked di…

medicine.medical_specialtyBest fittingMathematical modelLogarithmEye MovementsComputer sciencebusiness.industryNormal populationPattern recognitionGeneral MedicineVestibular Function TestsTransfer functionModels BiologicalSurgeryOtolithic MembraneOtorhinolaryngologyComputer Science::Computer Vision and Pattern RecognitionEvaluation methodsmedicineCurve fittingHumansArtificial intelligencebusinessOcular counterrollingActa oto-laryngologica
researchProduct

Primary ciliary dyskinesia assessment by means of optical flow analysis of phase-contrast microscopy images

2014

Primary ciliary dyskinesia implies cilia with defective or total absence of motility, which may result in sinusitis, chronic bronchitis, bronchiectasis and male infertility. Diagnosis can be difficult and is based on an abnormal ciliary beat frequency (CBF) and beat pattern. In this paper, we present a method to determine CBF of isolated cells through the analysis of phase-contrast microscopy images, estimating cilia motion by means of an optical flow algorithm. After having analyzed 28 image sequences (14 with a normal beat pattern and 14 with a dyskinetic pattern), the normal group presented a CBF of 5.2 +/- 1.6 Hz, while the dyskinetic patients presented a 1.9 +/- 0.9 Hz CBF. The cutoff …

medicine.medical_specialtyChronic bronchitisPhase contrast microscopyOptical flowBeat (acoustics)Health InformaticsSensitivity and SpecificityPattern Recognition Automatedlaw.inventionTECNOLOGIA ELECTRONICAPrimary ciliary dyskinesialawOphthalmologyImage Interpretation Computer-AssistedMicroscopymedicineHumansMicroscopy Phase-ContrastRadiology Nuclear Medicine and imagingPrimary ciliary dyskinesiaMicroscopy VideoBronchiectasisRadiological and Ultrasound Technologybusiness.industryCiliumOptical flowActive contoursReproducibility of ResultsAnatomyImage Enhancementmedicine.diseaseComputer Graphics and Computer-Aided DesignCell TrackingSubtraction TechniqueFISICA APLICADABeat frequencyComputer Vision and Pattern RecognitionbusinessMATEMATICA APLICADAAlgorithmsFourier-Mellin transformCiliary Motility Disorders
researchProduct

Laser illumination designs for snapshot multi-spectral-line imaging

2019

For multi-spectral imaging, both acquisition time of the spectral image set and the spectral bandwidth of each image have to be minimized. Ultimate performance can be achieved if the set of monochromatic (single-wavelength) spectral images is obtained with a single snapshot — a technique provisionally called "snapshot multi-spectral-line imaging" or SMSLI. Using contemporary RGB colour cameras, up to three spectral line images can be extracted from a snapshot image data cube at specific illumination that comprises only three spectral lines, each of them positioned within one of the detection bands (R, G or B) [1]. Techniques able to provide more spectral line images are under development, a…

medicine.medical_specialtyComputer sciencebusiness.industryData_MISCELLANEOUSMultispectral imageComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONLaser01 natural sciencesSpectral linelaw.inventionSpectral imaging010309 opticsData cubeOpticslawComputer Science::Computer Vision and Pattern Recognition0103 physical sciencesmedicineRGB color modelSnapshot (computer storage)Monochromatic colorbusiness
researchProduct

Single snapshot RGB multispectral imaging at fixed wavelengths: proof of concept

2014

A concept of single snapshot multispectral imaging by standard RGB image sensors under spectrally-specific illumination comprising a fixed number of narrow spectral lines is discussed and experimentally validated. The limiting conditions, RGB band spectral crosstalk corrections and potential applications for parametric mapping of skin are regarded, along with the preliminary results of the proof-of-concept measurements.

medicine.medical_specialtyComputer sciencebusiness.industryMultispectral imageSpectral lineSpectral imagingWavelengthOpticsProof of conceptComputer Science::Computer Vision and Pattern RecognitionmedicineRGB color modelSnapshot (computer storage)businessParametric statisticsSPIE Proceedings
researchProduct

HDR Imaging Pipeline for Spectral Filter Array Cameras

2017

Multispectral single shot imaging systems can benefit computer vision applications in needs of a compact and affordable imaging system. Spectral filter arrays technology meets the requirement, but can lead to artifacts due to inhomogeneous intensity levels between spectral channels due to filter manufacturing constraints, illumination and object properties. One solution to solve this problem is to use high dynamic range imaging techniques on these sensors. We define a spectral imaging pipeline that incorporates high dynamic range, demosaicing and color image visualization. Qualitative evaluation is based on real images captured with a prototype of spectral filter array sensor in the visible…

medicine.medical_specialtyDemosaicingColor imageComputer sciencebusiness.industryMultispectral imageComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION020206 networking & telecommunications02 engineering and technologyReal imageSpectral imagingHigh-dynamic-range imagingFilter (video)Computer Science::Computer Vision and Pattern Recognition0202 electrical engineering electronic engineering information engineeringmedicine020201 artificial intelligence & image processingComputer visionArtificial intelligencebusinessHigh dynamic range
researchProduct