Search results for "EURA"

showing 10 items of 3336 documents

Machine learning techniques demonstrating individual movement patterns of the vertebral column: the fingerprint of spinal motion

2022

Surface topography systems enable the capture of spinal dynamic movement; however, it is unclear whether vertebral dynamics are unique enough to identify individuals. Therefore, in this study, we investigated whether the identification of individuals is possible based on dynamic spinal data. Three different data representations were compared (automated extracted features using contrastive loss and triplet loss functions, as well as simple descriptive statistics). High accuracies indicated the possible existence of a personal spinal 'fingerprint', therefore enabling subject recognition. The present work forms the basis for an objective comparison of subjects and the transfer of the method to…

Computer scienceMovementBiomedical EngineeringBioengineeringMotion (physics)Machine LearningMotionTriplet lossmedicineHumansDescriptive statisticsMovement (music)business.industryWork (physics)Fingerprint (computing)Pattern recognitionGeneral MedicineSpineComputer Science ApplicationsHuman-Computer InteractionIdentification (information)medicine.anatomical_structureNeural Networks ComputerArtificial intelligencebusinessVertebral column
researchProduct

Burst analysis tool for developing neuronal networks exhibiting highly varying action potential dynamics

2012

In this paper we propose a firing statistics based neuronal network burst detection algorithm for neuronal networks exhibiting highly variable action potential dynamics. Electrical activity of neuronal networks is generally analyzed by the occurrences of spikes and bursts both in time and space. Commonly accepted analysis tools employ burst detection algorithms based on predefined criteria. However, maturing neuronal networks, such as those originating from human embryonic stem cells (hESC), exhibit highly variable network structure and time-varying dynamics. To explore the developing burst/spike activities of such networks, we propose a burst detection algorithm which utilizes the firing s…

Computer scienceNeuroscience (miscellaneous)Interval (mathematics)ta3112lcsh:RC321-57103 medical and health sciencesCellular and Molecular Neuroscience0302 clinical medicineMoving averageHistogramBiological neural networkMethods Articleburst analysislcsh:Neurosciences. Biological psychiatry. Neuropsychiatry030304 developmental biology0303 health sciencesspike trainsQuantitative Biology::Neurons and Cognitionmicroelectrode arrayMEAaction potential burstsdeveloping neuronal networksMultielectrode arrayhuman embryonic stem cellsPower (physics)nervous systemSkewnesshESCsSpike (software development)Biological systemNeuroscience030217 neurology & neurosurgeryNeuroscienceFrontiers in Computational Neuroscience
researchProduct

Deep Learning-Based Real-Time Object Detection in Inland Navigation

2019

International audience; Semi-autonomous and fully-autonomous systems must have knowledge about the objects in their environment to ensure a safe navigation. Modern approaches implement deep learning techniques to train a neural network for object detection. This project will study the effectiveness of using several promising algorithms such as Faster R-CNN, SSD, and different versions of YOLO, to detect, classify, and track objects in near real-time fluvial domain. Since no dataset is available for this purpose in literature, we first started by annotating a dataset of 2488 images with almost 35 400 annotations for training the convolutional neural network architectures. We made this data s…

Computer scienceObject detection02 engineering and technologyMachine learningcomputer.software_genreConvolutional neural networkDomain (software engineering)[SPI]Engineering Sciences [physics]0502 economics and businessMachine learning0202 electrical engineering electronic engineering information engineeringTrainingInland navigationAdaptation (computer science)050210 logistics & transportationArtificial neural networkbusiness.industryDeep learning05 social sciencesData modelsObject detectionNavigationRoadsData set020201 artificial intelligence & image processingArtificial intelligencebusinesscomputerNeural networks
researchProduct

Emulation of 2D Hydrodynamic Flood Simulations at Catchment Scale Using ANN and SVR

2021

Two-dimensional (2D) hydrodynamic models are one of the most widely used tools for flood modeling practices and risk estimation. The 2D models provide accurate results

Computer scienceProcess (engineering)Geography Planning and DevelopmentAquatic ScienceMachine learningcomputer.software_genreBiochemistrysupport vector regressionTD201-500Uncertainty analysisWater Science and TechnologyEmulationArtificial neural networkFlood mythWater supply for domestic and industrial purposesbusiness.industryDimensionality reductionHydraulic engineeringSupport vector machineemulatorsVDP::Teknologi: 500Sample size determinationerror structureArtificial intelligencetraining set sizebusinessTC1-978computerartificial neural networkWater
researchProduct

On-line Coordination in Complex Goal-directed Movements: a Matter of Interactions between Several Loops.

2012

International audience; Motor flexibility is the ability to rapidly modify behavior when unexpected perturbations occur. In goal directed movements, this process may be involved during the motor execution itself, by using on-line motor corrections, or off-line, on a trial-by-trial basis. A consensus has emerged to describe and unify these two dependant processes within the framework of the internal models theory in which the cerebellum is involved in error processing. However, this general framework may be incomplete to describe on-line motor corrections when complex motor coordination is involved in the task. In particular, interaction torques existing between different effectors limit the…

Computer scienceProcess (engineering)Movement050105 experimental psychology[SPI.AUTO]Engineering Sciences [physics]/Automatic03 medical and health sciences0302 clinical medicineControl theory[ SPI.AUTO ] Engineering Sciences [physics]/AutomaticNeural PathwaysReaction TimeAnimalsHumans0501 psychology and cognitive sciencesCerebral CortexFlexibility (engineering)Communicationbusiness.industryGeneral Neuroscience[SCCO.NEUR]Cognitive science/Neuroscience05 social sciences[SCCO.NEUR] Cognitive science/NeuroscienceMotor controlEfference copy16. Peace & justiceMotor coordinationDegrees of freedom problem[SPI.AUTO] Engineering Sciences [physics]/Automatic[ SCCO.NEUR ] Cognitive science/NeuroscienceNerve NetMotor learningbusinessGoalsMotor goalPsychomotor Performance030217 neurology & neurosurgery
researchProduct

A blind mesh visual quality assessment method based on convolutional neural network

2018

International audience

Computer scienceQuality assessmentbusiness.industry[INFO.INFO-TS] Computer Science [cs]/Signal and Image ProcessingPattern recognition02 engineering and technology01 natural sciencesConvolutional neural network[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing0103 physical sciences0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingArtificial intelligence010306 general physicsbusinessComputingMilieux_MISCELLANEOUS
researchProduct

Computational Offloading in Mobile Edge with Comprehensive and Energy Efficient Cost Function: A Deep Learning Approach

2021

In mobile edge computing (MEC), partial computational offloading can be intelligently investigated to reduce the energy consumption and service delay of user equipment (UE) by dividing a single task into different components. Some of the components execute locally on the UE while the remaining are offloaded to a mobile edge server (MES). In this paper, we investigate the partial offloading technique in MEC using a supervised deep learning approach. The proposed technique, comprehensive and energy efficient deep learning-based offloading technique (CEDOT), intelligently selects the partial offloading policy and also the size of each component of a task to reduce the service delay and energy …

Computer scienceReal-time computingTP1-118502 engineering and technologyBiochemistryVDP::Teknologi: 500::Elektrotekniske fag: 540ArticleAnalytical Chemistry0202 electrical engineering electronic engineering information engineeringcomputational offloadingElectrical and Electronic EngineeringInstrumentationenergy efficiencyMobile edge computingArtificial neural networkbusiness.industryChemical technologyDeep learningdeep learning020206 networking & telecommunicationsEnergy consumptionAtomic and Molecular Physics and OpticsTask (computing)cost functionUser equipment020201 artificial intelligence & image processingmobile edge computingArtificial intelligenceEnhanced Data Rates for GSM Evolutionremote executionbusinessEfficient energy useSensors
researchProduct

Deep Convolutional Neural Network for HEp-2 fluorescence intensity classification

2019

Indirect ImmunoFluorescence (IIF) assays are recommended as the gold standard method for detection of antinuclear antibodies (ANAs), which are of considerable importance in the diagnosis of autoimmune diseases. Fluorescence intensity analysis is very often complex, and depending on the capabilities of the operator, the association with incorrect classes is statistically easy. In this paper, we present a Convolutional Neural Network (CNN) system to classify positive/negative fluorescence intensity of HEp-2 IIF images, which is important for autoimmune diseases diagnosis. The method uses the best known pre-trained CNNs to extract features and a support vector machine (SVM) classifier for the …

Computer scienceSVM02 engineering and technologyConvolutional neural networklcsh:TechnologyIIF image030218 nuclear medicine & medical imaginglcsh:Chemistry03 medical and health sciences0302 clinical medicineClassifier (linguistics)Autoimmune disease0202 electrical engineering electronic engineering information engineeringGeneral Materials Scienceautoimmune diseasesReceiver operating characteristic (ROC) curveInstrumentationlcsh:QH301-705.5AccuracyIIF imagesFluid Flow and Transfer ProcessesIndirect immunofluorescencebusiness.industrylcsh:TProcess Chemistry and TechnologyGeneral EngineeringPattern recognitionIIfGold standard (test)Convolutional Neural Network (CNN)lcsh:QC1-999Computer Science ApplicationsIntensity (physics)Support vector machineFluorescence intensitylcsh:Biology (General)lcsh:QD1-999lcsh:TA1-2040020201 artificial intelligence & image processingArtificial intelligencebusinesslcsh:Engineering (General). Civil engineering (General)lcsh:Physics
researchProduct

The role of network connectivity on epileptiform activity.

2021

AbstractA number of potentially important mechanisms have been identified as key players to generate epileptiform activity, such as genetic mutations, activity-dependent alteration of synaptic functions, and functional network reorganization at the macroscopic level. Here we study how network connectivity at cellular level can affect the onset of epileptiform activity, using computational model networks with different wiring properties. The model suggests that networks connected as in real brain circuits are more resistant to generate seizure-like activity. The results suggest new experimentally testable predictions on the cellular network connectivity in epileptic individuals, and highligh…

Computer scienceScienceAction PotentialsCellular levelArticleFunctional networksComputational biophysicsSeizuresNeural Pathwayscomputational model networkHumansThe role of network connectivity on epileptiform activityComputational modelMultidisciplinaryNetwork modelsEpilepsycellular network connectivitySettore INF/01 - InformaticaQRBrainElectroencephalographyNetwork connectivityApplied mathematicsepileptiform activitywiring propertieCellular networkKey (cryptography)MedicineNerve NetNeuroscienceScientific reports
researchProduct

Live demonstration: multiplexing AER asynchronous channels over LVDS Links with Flow-Control and Clock-Correction for Scalable Neuromorphic Systems

2017

Paper presented at the 2017 IEEE International Symposium on Circuits and Systems (ISCAS), held in Baltimore, MD, USA, on 28-31 May 2017.

Computer scienceSerial communicationGabor filters02 engineering and technologyMultiplexingMultiplexing0202 electrical engineering electronic engineering information engineeringComputerSystemsOrganization_SPECIAL-PURPOSEANDAPPLICATION-BASEDSYSTEMSField-programmable gate arrayComputer Science::Operating SystemsMassively parallelNeuromorphicsReal-time systemsSpiking neural networkQuantitative Biology::Neurons and CognitionArtificial neural networkbusiness.industry020208 electrical & electronic engineeringField programmable gate arraysNeuromorphic engineeringAsynchronous communicationEmbedded systemVoltage controlbusinessComputer hardwareNeural networksHardware_LOGICDESIGN
researchProduct