Search results for "NEURAL NETWORK"

showing 10 items of 1385 documents

Neural Networks in ECG Classification

2011

In this chapter, we review the vast field of application of artificial neural networks in cardiac pathology discrimination based on electrocardiographic signals. We discuss advantages and drawbacks of neural and adaptive systems in cardiovascular medicine and catch a glimpse of forthcoming developments in machine learning models for the real clinical environment. Some problems are identified in the learning tasks of beat detection, feature selection/extraction, and classification, and some proposals and suggestions are given to alleviate the problems of interpretability, overfitting, and adaptation. These have become important problems in recent years and will surely constitute the basis of…

Physical neural networkComputingMethodologies_PATTERNRECOGNITIONArtificial neural networkbusiness.industryComputer scienceTime delay neural networkAdaptive systemArtificial intelligenceTypes of artificial neural networksbusiness
researchProduct

Design environment for hardware generation of SLFF neural network topologies with ELM training capability

2015

Extreme Learning Machine (ELM) is a noniterative training method suited for Single Layer Feed Forward Neural Networks (SLFF-NN). Typically, a hardware neural network is trained before implementation in order to avoid additional on-chip occupation, delay and performance degradation. However, ELM provides fixed-time learning capability and simplifies the process of re-training a neural network once implemented in hardware. This is an important issue in many applications where input data are continuously changing and a new training process must be launched very often, providing self-adaptation. This work describes a general SLFF-NN design environment to assist in the definition of neural netwo…

Physical neural networkHardware architectureArtificial neural networkTime delay neural networkbusiness.industryComputer scienceDesign flowSoftware designbusinessNetwork topologyComputer hardwareExtreme learning machine2015 IEEE 13th International Conference on Industrial Informatics (INDIN)
researchProduct

Ab initioquality neural-network potential for sodium

2010

An interatomic potential for high-pressure high-temperature (HPHT) crystalline and liquid phases of sodium is created using a neural-network (NN) representation of the ab initio potential energy surface. It is demonstrated that the NN potential provides an ab initio quality description of multiple properties of liquid sodium and bcc, fcc, cI16 crystal phases in the P-T region up to 120 GPa and 1200 K. The unique combination of computational efficiency of the NN potential and its ability to reproduce quantitatively experimental properties of sodium in the wide P-T range enables molecular dynamics simulations of physicochemical processes in HPHT sodium of unprecedented quality.

Physicochemical ProcessesCondensed Matter - Materials ScienceMaterials scienceStatistical Mechanics (cond-mat.stat-mech)Artificial neural networkSodiumAb initioMaterials Science (cond-mat.mtrl-sci)FOS: Physical sciencesThermodynamicschemistry.chemical_elementInteratomic potentialCondensed Matter PhysicsElectronic Optical and Magnetic MaterialsCrystalQuality (physics)chemistryCondensed Matter - Statistical MechanicsPhysical Review B
researchProduct

The ALICE Transition Radiation Detector: Construction, operation, and performance

2018

The Transition Radiation Detector (TRD) was designed and built to enhance the capabilities of the ALICE detector at the Large Hadron Collider (LHC). While aimed at providing electron identification and triggering, the TRD also contributes significantly to the track reconstruction and calibration in the central barrel of ALICE. In this paper the design, construction, operation, and performance of this detector are discussed. A pion rejection factor of up to 410 is achieved at a momentum of 1 GeV/$c$ in p-Pb collisions and the resolution at high transverse momentum improves by about 40% when including the TRD information in track reconstruction. The triggering capability is demonstrated both …

Physics - Instrumentation and Detectors:Kjerne- og elementærpartikkelfysikk: 431 [VDP]TRPhysics::Instrumentation and DetectorsCOLLIDING BEAM EXPERIMENT; ELECTRON IDENTIFICATION; DRIFT CHAMBERS; TRD PROTOTYPES; ENERGY-LOSS; GEV/C; COLLISIONS; PIONSparticle identification [electron]Ionisation energy loTracking (particle physics)Transition radiation detector ; Multi-wire proportional drift chamber ; Fibre/foam sandwich radiator ; Xenon-based gas mixture ; Tracking ; Ionisation energy loss ; dE/dx ; TR ; Electron-pion identification ; Neural network ; Trigger01 natural sciencesParticle identificationdesign [detector]ALICEDetectors and Experimental Techniquesmomentum resolutionNuclear Experimentphysics.ins-detInstrumentationPhysicsPROTOTYPESLarge Hadron Collidertransition radiation detector; multi-wire proportional drift chamber;; fibre/foam sandwich radiator; Xenon-based gas mixture; tracking;; Ionisation energy loss; dE/dx; TR; electron-pion identification; Neural; network; trigger; COLLIDING BEAM EXPERIMENT; ELECTRON IDENTIFICATION; DRIFT CHAMBERS; TRD; PROTOTYPES; ENERGY-LOSS; GEV/C; COLLISIONS; PIONStrack data analysisTrackingPIONSDetectorVDP::Kjerne- og elementærpartikkelfysikk: 431Instrumentation and Detectors (physics.ins-det)trackingtransition radiation detector:Mathematics and natural scienses: 400::Physics: 430::Nuclear and elementary particle physics: 431 [VDP]ddc:PRIRODNE ZNANOSTI. Fizika.Xenon-based gas mixtureTransition radiation detector:Nuclear and elementary particle physics: 431 [VDP]VDP::Nuclear and elementary particle physics: 431GEV/Cmulti-wire proportional drift chamberperformanceParticle physicsNuclear and High Energy PhysicsCOLLISIONSelectron-pion identificationneural networkInstrumentationFOS: Physical sciencesTransition radiation detector; Multi-wire proportional drift chamber; Fibre/foam sandwich radiator; Xenon-based gas mixture; Tracking; Ionisation energy loss; dE/dx; TR; Electron-pion identification; Neural network; Trigger114 Physical sciencesMomentumNuclear physicsionisation energy loss0103 physical sciencesdE/dxDRIFT CHAMBERSdE/dx Electron-pion identification Fibre/foam sandwich radiator Ionisation energy loss Multi-wire proportional drift chamber Neural network TR Tracking Transition radiation detector Trigger Xenon-based gas mixture Nuclear and High Energy Physics Instrumentation.ddc:530[PHYS.PHYS.PHYS-INS-DET]Physics [physics]/Physics [physics]/Instrumentation and Detectors [physics.ins-det]seuranta010306 general physicsdetector: designNuclear and High Energy PhysicNeuralCOLLIDING BEAM EXPERIMENTTRD PROTOTYPESelectron: particle identificationta114010308 nuclear & particles physics:Matematikk og naturvitenskap: 400::Fysikk: 430::Kjerne- og elementærpartikkelfysikk: 431 [VDP]fibre/foam sandwich radiatortriggercalibrationNATURAL SCIENCES. Physics.Neural networkdE/dx; Electron-pion identification; Fibre/foam sandwich radiator; Ionisation energy loss; Multi-wire proportional drift chamber; Neural network; TR; Tracking; Transition radiation detector; Trigger; Xenon-based gas mixtureTriggerdE/dx; Electron-pion identification; Fibre/foam sandwich radiator; Ionisation energy loss; Multi-wire proportional drift chamber; Neural network; TR; Tracking; Transition radiation detector; Trigger; Xenon-based gas mixture; Nuclear and High Energy Physics; InstrumentationnetworkELECTRON IDENTIFICATIONTRDHigh Energy Physics::ExperimentALICE (propellant)ENERGY-LOSSNuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment
researchProduct

A tool for filtering information in complex systems

2005

We introduce a technique to filter out complex data-sets by extracting a subgraph of representative links. Such a filtering can be tuned up to any desired level by controlling the genus of the resulting graph. We show that this technique is especially suitable for correlation based graphs giving filtered graphs which preserve the hierarchical organization of the minimum spanning tree but containing a larger amount of information in their internal structure. In particular in the case of planar filtered graphs (genus equal to 0) triangular loops and 4 element cliques are formed. The application of this filtering procedure to 100 stocks in the USA equity markets shows that such loops and cliqu…

Physics - Physics and SocietyComputer scienceComplex systemFOS: Physical sciencesPhysics and Society (physics.soc-ph)Minimum spanning treecomputer.software_genrePlanarHierarchical organizationINTERNETCondensed Matter - Statistical MechanicsComplex data typeMultidisciplinarySmall-world networkStatistical Mechanics (cond-mat.stat-mech)SMALL-WORLD NETWORKSFilter (signal processing)Disordered Systems and Neural Networks (cond-mat.dis-nn)Condensed Matter - Disordered Systems and Neural NetworksComplex networkWEBDYNAMIC ASSET TREESPhysical SciencesGRAPHData miningAlgorithmcomputerMathematicsofComputing_DISCRETEMATHEMATICS
researchProduct

Mean Escape Time in a System with Stochastic Volatility

2007

We study the mean escape time in a market model with stochastic volatility. The process followed by the volatility is the Cox Ingersoll and Ross process which is widely used to model stock price fluctuations. The market model can be considered as a generalization of the Heston model, where the geometric Brownian motion is replaced by a random walk in the presence of a cubic nonlinearity. We investigate the statistical properties of the escape time of the returns, from a given interval, as a function of the three parameters of the model. We find that the noise can have a stabilizing effect on the system, as long as the global noise is not too high with respect to the effective potential barr…

Physics - Physics and SocietyMean escape timeFOS: Physical sciencesPhysics and Society (physics.soc-ph)Heston modelFOS: Economics and businessEconometricsEconophysics; Mean escape time; Heston model; Stochastic modelStatistical physicsCondensed Matter - Statistical MechanicsMathematicsGeometric Brownian motionStatistical Finance (q-fin.ST)Statistical Mechanics (cond-mat.stat-mech)Stochastic volatilityStochastic processEconophysicQuantitative Finance - Statistical FinanceDisordered Systems and Neural Networks (cond-mat.dis-nn)Brownian excursionCondensed Matter - Disordered Systems and Neural NetworksSettore FIS/07 - Fisica Applicata(Beni Culturali Ambientali Biol.e Medicin)Heston modelStochastic modelReflected Brownian motionVolatility (finance)Rendleman–Bartter model
researchProduct

Non-Markovian dynamics from band edge effects and static disorder

2017

It was recently shown [S. Lorenzo et al., Sci. Rep. 7, 42729 (2017)] that the presence of static disorder in a bosonic bath - whose normal modes thus become all Anderson-localised - leads to non-Markovianity in the emission of an atom weakly coupled to it (a process which in absence of disorder is fully Markovian). Here, we extend the above analysis beyond the weak-coupling regime for a finite-band bath so as to account for band edge effects. We study the interplay of these with static disorder in the emergence of non-Markovian behaviour in terms of a suitable non-Markovianity measure.

Physics and Astronomy (miscellaneous)Anderson localizactionMarkov processNon-MarkovianityFOS: Physical sciencesEdge (geometry)01 natural sciencesMeasure (mathematics)Static disorderCondensed Matter::Disordered Systems and Neural NetworksSettore FIS/03 - Fisica Della Materia010305 fluids & plasmassymbols.namesakeNormal modeQuantum mechanicsAtom (measure theory)0103 physical sciencesband edge mode010306 general physicsband edge modesPhysicsQuantum PhysicsDynamics (mechanics)disordersymbolsQuantum Physics (quant-ph)Anderson localizaction; band edge modes; disorder; Non-Markovianity; Physics and Astronomy (miscellaneous)
researchProduct

Fingerprint classification based on deep learning approaches: Experimental findings and comparisons

2021

Biometric classification plays a key role in fingerprint characterization, especially in the identification process. In fact, reducing the number of comparisons in biometric recognition systems is essential when dealing with large-scale databases. The classification of fingerprints aims to achieve this target by splitting fingerprints into different categories. The general approach of fingerprint classification requires pre-processing techniques that are usually computationally expensive. Deep Learning is emerging as the leading field that has been successfully applied to many areas, such as image processing. This work shows the performance of pre-trained Convolutional Neural Networks (CNNs…

Physics and Astronomy (miscellaneous)BiometricsComputer scienceGeneral Mathematicsfingerprint featuresfingerprint classification; deep learning; convolutional neural networks; fingerprint featuresConvolutional neural networks Deep learning Fingerprint classification Fingerprint featuresImage processing02 engineering and technologyConvolutional neural networkField (computer science)fingerprint classification020204 information systemsconvolutional neural networksQA1-9390202 electrical engineering electronic engineering information engineeringComputer Science (miscellaneous)Reliability (statistics)business.industryDeep learningFingerprint (computing)deep learningPattern recognitionIdentification (information)Chemistry (miscellaneous)Convolutional neural networks; Deep learning; Fingerprint classification; Fingerprint features020201 artificial intelligence & image processingArtificial intelligencebusinessMathematics
researchProduct

Recent advances in intelligent-based structural health monitoring of civil structures

2018

This survey paper deals with the structural health monitoring systems on the basis of methodologies involving intelligent techniques. The intelligent techniques are the most popular tools for damage identification in terms of high accuracy, reliable nature and the involvement of low cost. In this critical survey, a thorough analysis of various intelligent techniques is carried out considering the cases involved in civil structures. The importance and utilization of various intelligent tools to be mention as the concept of fuzzy logic, the technique of genetic algorithm, the methodology of neural network techniques, as well as the approaches of hybrid methods for the monitoring of the struct…

Physics and Astronomy (miscellaneous)Computer science020101 civil engineering02 engineering and technologyMachine learningcomputer.software_genreFuzzy logiclcsh:Technology0201 civil engineering0203 mechanical engineeringManagement of Technology and InnovationGenetic algorithmlcsh:ScienceEngineering (miscellaneous)Basis (linear algebra)Artificial neural networkbusiness.industrylcsh:TIdentification (information)020303 mechanical engineering & transportsCritical surveylcsh:QArtificial intelligenceStructural health monitoringbusinesscomputer
researchProduct

Stringlike Cooperative Motion in a Supercooled Liquid

1998

Extensive molecular dynamics simulations are performed on a glass-forming Lennard-Jones mixture to determine the nature of the cooperative motions occurring in this model fragile liquid. We observe stringlike cooperative molecular motion (``strings'') at temperatures well above the glass transition. The mean length of the strings increases upon cooling, and the string length distribution is found to be nearly exponential.

Physics010304 chemical physicsCondensed matter physicsMathematical modelGeneral Physics and AstronomyCondensed Matter::Disordered Systems and Neural Networks01 natural sciences3. Good healthExponential functionCondensed Matter::Soft Condensed MatterMolecular dynamics0103 physical sciencesQuasiparticleRelaxation (physics)Dynamical heterogeneity010306 general physicsGlass transitionSupercoolingPhysical Review Letters
researchProduct