Search results for " electronics"

showing 10 items of 580 documents

On the use of Deep Reinforcement Learning for Visual Tracking: a Survey

2021

This paper aims at highlighting cutting-edge research results in the field of visual tracking by deep reinforcement learning. Deep reinforcement learning (DRL) is an emerging area combining recent progress in deep and reinforcement learning. It is showing interesting results in the computer vision field and, recently, it has been applied to the visual tracking problem yielding to the rapid development of novel tracking strategies. After providing an introduction to reinforcement learning, this paper compares recent visual tracking approaches based on deep reinforcement learning. Analysis of the state-of-the-art suggests that reinforcement learning allows modeling varying parts of the tracki…

General Computer ScienceComputer scienceFeature extractionMachine learningcomputer.software_genreField (computer science)video-surveillanceMinimum bounding boxReinforcement learningGeneral Materials ScienceSettore ING-INF/05 - Sistemi Di Elaborazione Delle Informazionideep reinforcement learningComputer vision machine learning video-surveillance deep reinforcement learning visual tracking.business.industryGeneral EngineeringTracking systemvisual trackingVisualizationActive appearance modelTK1-9971machine learningEye trackingComputer visionArtificial intelligenceElectrical engineering. Electronics. Nuclear engineeringbusinesscomputer
researchProduct

WiWeHAR: Multimodal Human Activity Recognition Using Wi-Fi and Wearable Sensing Modalities

2020

Robust and accurate human activity recognition (HAR) systems are essential to many human-centric services within active assisted living and healthcare facilities. Traditional HAR systems mostly leverage a single sensing modality (e.g., either wearable, vision, or radio frequency sensing) combined with machine learning techniques to recognize human activities. Such unimodal HAR systems do not cope well with real-time changes in the environment. To overcome this limitation, new HAR systems that incorporate multiple sensing modalities are needed. Multiple diverse sensors can provide more accurate and complete information resulting in better recognition of the performed activities. This article…

General Computer ScienceComputer scienceFeature extractionPrincipal component analysisComputació centrada en humansWearable computer02 engineering and technologyDoppler EfecteAccelerometerRadio frequency sensinglaw.inventionActivity recognitionlawInertial measurement unitMachine learning0202 electrical engineering electronic engineering information engineeringfeature fusionGeneral Materials ScienceComputer visionReconeixement de formes (Informàtica)VDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550Feature fusionModality (human–computer interaction)business.industryfeature extractionSupervised learningGeneral Engineering:Enginyeria de la telecomunicació::Processament del senyal::Reconeixement de formes [Àrees temàtiques de la UPC]020206 networking & telecommunicationsGyroscopemicro-Doppler signatureDoppler effectWearable sensingmachine learningHuman-centered computingActivity recognitionFeature extractionMicro-Doppler signature020201 artificial intelligence & image processing:Informàtica::Intel·ligència artificial [Àrees temàtiques de la UPC]Artificial intelligencelcsh:Electrical engineering. Electronics. Nuclear engineeringHuman activity recognitionbusinesslcsh:TK1-9971
researchProduct

A Machine Learning Approach for Fall Detection Based on the Instantaneous Doppler Frequency

2019

Modern societies are facing an ageing problem that is accompanied by increasing healthcare costs. A major share of this ever-increasing cost is due to fall-related injuries, which urges the development of fall detection systems. In this context, this paper paves the way for the development of radio-frequency-based fall detection systems, which do not require the user to wear any device and can detect falls without compromising the user's privacy. For the design of such systems, we present an activity simulator that generates the complex path gain of indoor channels in the presence of one person performing three different activities: slow fall, fast fall, and walking. We have developed a mac…

General Computer ScienceComputer scienceFeature vectorFeature extractionDecision tree02 engineering and technologyMachine learningcomputer.software_genreActivity recognitioncomplex path gainFall detection0202 electrical engineering electronic engineering information engineeringGeneral Materials Scienceactivity recognitionVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550instantaneous Doppler frequencyArtificial neural networkbusiness.industryfeature extractionGeneral Engineering020206 networking & telecommunicationsSupport vector machineStatistical classificationmachine learning020201 artificial intelligence & image processinglcsh:Electrical engineering. Electronics. Nuclear engineeringArtificial intelligencebusinesslcsh:TK1-9971computerClassifier (UML)IEEE Access
researchProduct

On the Assessment of Fitness to Drive: Steering and Brake Operative Forces

2021

[EN] The Directive (EU) 2015/653 aimed at facilitating that the maximum force that any disabled driver could make on the vehicle's primary controls could be adjusted to their needs. The technical adjustment in the vehicle's design requires a measurement of the operational forces applied by the driver on the steering and brake controls, in order to determine its functional capacity during the execution of driving maneuvers. The objective of this paper is to define the steering and braking operative forces used for driving current market M1 motor vehicles for the ¿fitness to drive assessment of drivers with physical disabilities. A total of 200 trials were performed with 17 different vehicles…

General Computer ScienceComputer scienceINGENIERIA MECANICAGeneral EngineeringFitness to driveVehiclesDirectiveINGENIERIA DE SISTEMAS Y AUTOMATICAAutomotive engineeringTK1-9971Braking forcesFitness to driveSteering operative forcesOrder (business)BrakeCode (cryptography)General Materials ScienceElectrical engineering. Electronics. Nuclear engineeringDriving assessmentElectrical and Electronic Engineering
researchProduct

Face Inpainting via Nested Generative Adversarial Networks

2019

Face inpainting aims to repaired damaged images caused by occlusion or cover. In recent years, deep learning based approaches have shown promising results for the challenging task of image inpainting. However, there are still limitation in reconstructing reasonable structures because of over-smoothed and/or blurred results. The distorted structures or blurred textures are inconsistent with surrounding areas and require further post-processing to blend the results. In this paper, we present a novel generative model-based approach, which consisted by nested two Generative Adversarial Networks (GAN), the sub-confrontation GAN in generator and parent-confrontation GAN. The sub-confrontation GAN…

General Computer ScienceComputer scienceInpaintingComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technologyFace inpainting010501 environmental sciencesResidual01 natural sciencesImage (mathematics)0202 electrical engineering electronic engineering information engineeringGeneral Materials ScienceVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 5500105 earth and related environmental sciencesbusiness.industryDeep learningGeneral Engineeringdeep neural networkPattern recognitionGenerative modelFace (geometry)020201 artificial intelligence & image processingArtificial intelligencenested GANlcsh:Electrical engineering. Electronics. Nuclear engineeringbusinesslcsh:TK1-9971Generator (mathematics)
researchProduct

A Language and Platform Independent Co-Simulation Framework Based on the Functional Mock-Up Interface

2019

The main goal of the Functional Mock-up Interface (FMI) standard is to allow the sharing of simulation models across tools. To accomplish this, FMI relies on a combination of XML-files and compiled C-code packaged in a zip archive. This archive is called a Functional Mock-up Unit (FMU). In theory, an FMU can support multiple platforms, but not necessarily in practice. Furthermore, software libraries for interacting with FMUs may not be available in a particular language or platform. Another issue is related to the protection of intellectual property (IP). While an FMU is free to only provide the C-code in its binary form, other resources within the FMU may be unprotected. Distributing model…

General Computer ScienceComputer scienceInterface (Java)distributed simulation020101 civil engineering02 engineering and technologyCo-simulation01 natural sciences010305 fluids & plasmas0201 civil engineeringmodel exchangeSoftware0103 physical sciencesCode (cryptography)General Materials ScienceElectrical and Electronic EngineeringArchitectureVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550FMIFMUbusiness.industryGeneral EngineeringVDP::Teknologi: 500Remote procedure callFunctional Mock-up InterfaceRPClcsh:Electrical engineering. Electronics. Nuclear engineeringCo-simulationCommunications protocolSoftware engineeringbusinesslcsh:TK1-9971
researchProduct

Interference Cancellation for LoRa Gateways and Impact on Network Capacity

2021

In this paper we propose LoRaSyNc (LoRa receiver with SyNchronization and Cancellation), a second generation LoRa receiver that implements Successive Interference Cancellation (SIC) and time synchronization to improve the performance of LoRa gateways. Indeed, the chirp spread spectrum modulation employed in LoRa experiences very high capture probability, and cancelling the strongest signal in case of collisions can significantly improve the cell capacity. An important feature of LoRaSyNc is the ability to track the frequency and clock drifts between the transmitter and receiver, during the whole demodulation of the interfered frame. Due to the use of low-cost oscillators on end-devices, a s…

General Computer ScienceComputer scienceInternet of ThingsinterferenceChirp spread spectrumSilicon carbideSignalReceiversSettore ING-INF/01 - ElettronicaLoRaSynchronizationLPWANElectronic engineeringDemodulationGeneral Materials ScienceComputer architecturesynchronized signalsscalabilityClocksFrame (networking)TransmitterGeneral Engineeringinterference cancellationLogic gatesLoRaWANTK1-9971Single antenna interference cancellationModulationspreading factorElectrical engineering. Electronics. Nuclear engineeringCapture effectIEEE Access
researchProduct

Four-Level Three-Phase Inverter With Reduced Component Count for Low and Medium Voltage Applications

2021

This paper proposes a novel three-phase topology with a reduced component count for low- and medium-voltage systems. It requires three bidirectional switches and twelve unidirectional switches for producing four-level voltages without using flying capacitors or clamping diodes, reducing the size, cost, and losses. Removing flying capacitors and clamping diodes allows it to simplify control algorithms and increase the reliability, efficiency, and lifetime. A modified low-frequency modulation (LFM) scheme is developed and implemented on the proposed topology to produce a staircase voltage with four steps. Further, a level-shifted pulse width modulation (LSPWM) is used to reduce the filter siz…

General Computer ScienceComputer scienceTopology (electrical circuits)02 engineering and technology01 natural scienceslaw.inventionlawthree-phase inverters0103 physical sciences0202 electrical engineering electronic engineering information engineeringElectronic engineeringGeneral Materials Sciencemultilevel invertersDiode010302 applied physics020208 electrical & electronic engineeringGeneral EngineeringDC-AC convertersClampingControllabilityCapacitorVDP::Teknologi: 500low and medium voltage applicationsFilter (video)lcsh:Electrical engineering. Electronics. Nuclear engineeringfour-level inverterslcsh:TK1-9971Pulse-width modulationVoltage
researchProduct

An Indoor and Outdoor Navigation System for Visually Impaired People

2019

In this paper, we present a system that allows visually impaired people to autonomously navigate in an unknown indoor and outdoor environment. The system, explicitly designed for low vision people, can be generalized to other users in an easy way. We assume that special landmarks are posed for helping the users in the localization of pre-defined paths. Our novel approach exploits the use of both the inertial sensors and the camera integrated into the smartphone as sensors. Such a navigation system can also provide direction estimates to the tracking system to the users. The success of out approach is proved both through experimental tests performed in controlled indoor environments and in r…

General Computer ScienceComputer scienceVisually impairedComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technologydead reckoning01 natural sciencescomputer visionInertial measurement unitDead reckoning0202 electrical engineering electronic engineering information engineeringGeneral Materials ScienceComputer visionbusiness.industryDeep learning010401 analytical chemistryGeneral EngineeringNavigation system020206 networking & telecommunicationsTracking systemKalman filterNavigation0104 chemical sciencesvisually impairedArtificial intelligencelcsh:Electrical engineering. Electronics. Nuclear engineeringbusinessKalman filteringlcsh:TK1-9971IEEE Access
researchProduct

Human Heart-Related Indexes Behavior Study for Aircraft Pilots Allowable Workload Level Assessment

2022

This study aimed to evaluate workload by detecting Heart Rate Variability (HRV) indexes in a sample of 34 pilots (with a mean age of 33 years) while performing simulated flight exercises. A one-way ANOVA with repeated measures was performed to assess the changes of the physiological measures in five standard maneuvers associated with different workload levels. The results show that all the indexes, but the Low Frequency to High Frequency ratio index (LF/HF), have a well-defined trend between the baseline and the en-route phase and with the three phases takeoff, steady turn, and landing. This study, as main findings, provides evidence of a differentiation among low, medium, and high workload…

General Computer ScienceGeneral Engineeringheart rate variabilityGeneral Materials ScienceElectrical engineering. Electronics. Nuclear engineeringworkload assessmentPilot performance monitoringTK1-9971IEEE Access
researchProduct