Search results for "Convolution"

showing 10 items of 334 documents

Deep learning strategies for automatic fault diagnosis in photovoltaic systems by thermographic images

2021

Abstract Losses of electricity production in photovoltaic systems are mainly caused by the presence of faults that affect the efficiency of the systems. The identification of any overheating in a photovoltaic module, through the thermographic non-destructive test, may be essential to maintain the correct functioning of the photovoltaic system quickly and cost-effectively, without interrupting its normal operation. This work proposes a system for the automatic classification of thermographic images using a convolutional neural network, developed via open-source libraries. To reduce image noise, various pre-processing strategies were evaluated, including normalization and homogenization of pi…

Artificial neural networkContextual image classificationRenewable Energy Sustainability and the EnvironmentComputer sciencebusiness.industry020209 energyDeep learningEnergy Engineering and Power TechnologyPattern recognitionSobel operatorAutomatic Fault recognition Convolutional Neural Network Photovoltaics TensorFlow Infrared Thermography02 engineering and technologyPerceptronConvolutional neural networkThresholdingThermographic inspectionFuel Technology020401 chemical engineeringNuclear Energy and Engineering0202 electrical engineering electronic engineering information engineeringArtificial intelligence0204 chemical engineeringbusinessEnergy Conversion and Management
researchProduct

The Use of Artificial Intelligence in Disaster Management - A Systematic Literature Review

2019

Whenever a disaster occurs, users in social media, sensors, cameras, satellites, and the like generate vast amounts of data. Emergency responders and victims use this data for situational awareness, decision-making, and safe evacuations. However, making sense of the generated information under time-bound situations is a challenging task as the amount of data can be significant, and there is a need for intelligent systems to analyze, process, and visualize it. With recent advancements in Artificial Intelligence (AI), numerous researchers have begun exploring AI, machine learning (ML), and deep learning (DL) techniques for big data analytics in managing disasters efficiently. This paper adopt…

Artificial neural networkbusiness.industryComputer scienceDeep learningBig dataIntelligent decision support system020206 networking & telecommunications02 engineering and technologyLatent Dirichlet allocationConvolutional neural networkSupport vector machinesymbols.namesakeNaive Bayes classifierComputingMethodologies_PATTERNRECOGNITION0202 electrical engineering electronic engineering information engineeringsymbols020201 artificial intelligence & image processingArtificial intelligencebusiness2019 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)
researchProduct

ConvLSTM Neural Networks for seismic event prediction in Chile

2021

Predicting seismic risk is a challenging task in order to avoid catastrophic effects. In this work, two models based on Convolutional Network (CNN) and Long Short Term Memory (LSTM) networks are proposed to predict the seismic risk in Chile. In particular, a ConvLSTM and a Multi-column ConvLSTM network are used for the prediction of the average number of seismic events greater than 2,8 magnitude on the Richter scale, in the Chilean regions of Coquimbo and Araucania between the years 2010 and 2017. For this model, the values of the intensity function estimated through an ETAS model and the accumulated displacement prior to a the seismic events are used as inputs. In particular, given the spa…

Artificial neural networkbusiness.industryDeep learningMagnitude (mathematics)Convolutional neural networkDisplacement (vector)law.inventionRichter magnitude scalelawArtificial intelligenceSeismic riskbusinessSeismologyGeologyEvent (probability theory)2021 IEEE XXVIII International Conference on Electronics, Electrical Engineering and Computing (INTERCON)
researchProduct

An Encrypted Traffic Classification Framework Based on Convolutional Neural Networks and Stacked Autoencoders

2020

In recent years, deep learning-based encrypted traffic classification has proven to be effective; especially, using neural networks to extract features from raw traffic to classify encrypted traffic. However, most of the neural networks need a fixed-sized input, so that the raw traffic need to be trimmed. This will cause the loss of some information; for example, we do not know the number of packets in a session. To solve these problems, a framework, which implements both a convolutional neural network (CNN) and a stacked autoencoder (SAE), is proposed in this paper. This framework uses a CNN to extract high-level features from raw network traffic and uses an SAE to encode the 26 statistica…

Artificial neural networkbusiness.industryNetwork packetComputer scienceDeep learningFeature extraction020206 networking & telecommunicationsPattern recognition02 engineering and technologyEncryptionAutoencoderConvolutional neural networkTraffic classification0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingArtificial intelligencebusiness2020 IEEE 6th International Conference on Computer and Communications (ICCC)
researchProduct

Deconvolution procedure of the UV-vis spectra. A powerful tool for the estimation of the binding of a model drug to specific solubilisation loci of b…

2015

UV-vis-spectra evolution of Nile Red loaded into Tween 20 micelles with pH and [Tween 20] have been analysed in a non-conventional manner by exploiting the deconvolution method. The number of buried sub-bands has been found to depend on both pH and bio-surfactant concentration, whose positions have been associated to Nile Red confined in aqueous solution and in the three micellar solubilisation sites. For the first time, by using an extended classical two-pseudo-phases-model, the robust treatment of the spectrophotometric data allows the estimation of Nile Red binding constant to the available loci. Hosting capability towards Nile Red is exalted by the pH enhancement. Comparison between bin…

Atomic and Molecular Physics and OpticOxazineAnalytical chemistrySpecific solubilisation lociTween 20PolysorbatesDeconvolutionNile RedMicelleSpectral lineUV-vis spectraAnalytical ChemistrySurface-Active Agentchemistry.chemical_compoundSurface-Active AgentsUltraviolet visible spectroscopycmc; Deconvolution; Nile Red; Specific solubilisation loci; Tween 20; UV-vis spectra; Binding Sites; Oxazines; Polysorbates; Solubility; Spectrophotometry Ultraviolet; Surface-Active Agents; Micelles; Instrumentation; Atomic and Molecular Physics and Optics; Analytical Chemistry; Spectroscopy; Medicine (all)Pulmonary surfactantOxazinesInstrumentationSpectroscopyMicellesAqueous solutionBinding SitesChemistryMedicine (all)Nile redBinding SiteBinding constantAtomic and Molecular Physics and OpticsPolysorbateSolubilitycmcSpectrophotometry UltravioletDeconvolutionMicelle
researchProduct

Enabling Real-Time Computation of Psycho-Acoustic Parameters in Acoustic Sensors Using Convolutional Neural Networks

2020

Sensor networks have become an extremely useful tool for monitoring and analysing many aspects of our daily lives. Noise pollution levels are very important today, especially in cities where the number of inhabitants and disturbing sounds are constantly increasing. Psycho-acoustic parameters are a fundamental tool for assessing the degree of discomfort produced by different sounds and, combined with wireless acoustic sensor networks (WASNs), could enable, for example, the efficient implementation of acoustic discomfort maps within smart cities. However, the continuous monitoring of psycho-acoustic parameters to create time-dependent discomfort maps requires a high computational demand that …

Audio signalComputer scienceNoise pollutionbusiness.industryComputation010401 analytical chemistryReal-time computing01 natural sciencesConvolutional neural network0104 chemical sciencesWirelessElectrical and Electronic EngineeringbusinessInstrumentationWireless sensor networkIEEE Sensors Journal
researchProduct

Improving accuracy of FIR filters for computing convolution transforms for smooth non-bandlimited signals

2019

We propose to improve the accuracy of FIR filters for computing convolution transforms for smooth non-bandlimited (NBL) signals by designing filters by the identification method with using a pair of bandlimited portions of the chosen NBL input and output signals related with each other by the given transform. A design example of type IV linear phase differentiator is presented, where filter coefficients are calculated from the bandlimited portions of the Cauchy pulse and its derivative. The performance of the designed differentiator is evaluated by comparing the accuracy of computed derivatives for several smooth NBL test signals, such as the Cauchy pulse, the Hilbert transform of Cauchy pu…

Bandlimiting020303 mechanical engineering & transports0203 mechanical engineeringFinite impulse responseComputer sciencelcsh:TA1-2040021105 building & construction0211 other engineering and technologies02 engineering and technologylcsh:Engineering (General). Civil engineering (General)AlgorithmConvolutionMATEC Web of Conferences
researchProduct

Quantitative comparison of motion history image variants for video-based depression assessment

2017

Abstract Depression is the most prevalent mood disorder and a leading cause of disability worldwide. Automated video-based analyses may afford objective measures to support clinical judgments. In the present paper, categorical depression assessment is addressed by proposing a novel variant of the Motion History Image (MHI) which considers Gabor-inhibited filtered data instead of the original image. Classification results obtained with this method on the AVEC’14 dataset are compared to those derived using (a) an earlier MHI variant, the Landmark Motion History Image (LMHI), and (b) the original MHI. The different motion representations were tested in several combinations of appearance-based …

BiometricsComputer scienceSpeech recognitionlcsh:TK7800-836002 engineering and technologyConvolutional neural networkMotion (physics)[SPI]Engineering Sciences [physics]Image processingMachine learning0502 economics and business[ SPI ] Engineering Sciences [physics]0202 electrical engineering electronic engineering information engineeringElectrical and Electronic EngineeringCategorical variableComputingMilieux_MISCELLANEOUSLandmarkbusiness.industrylcsh:Electronics05 social sciencesAffective computingFacial image analysisPattern recognitionMotion history imageMoodSignal ProcessingPattern recognition (psychology)Depression assessment020201 artificial intelligence & image processingArtificial intelligenceF1 scorebusiness050203 business & managementInformation SystemsEURASIP Journal on Image and Video Processing
researchProduct

Blind deconvolution using TV regularization and Bregman iteration

2005

In this paper we formulate a new time dependent model for blind deconvolution based on a constrained variational model that uses the sum of the total variation norms of the signal and the kernel as a regularizing functional. We incorporate mass conservation and the nonnegativity of the kernel and the signal as additional constraints. We apply the idea of Bregman iterative regularization, first used for image restoration by Osher and colleagues [S.J. Osher, M. Burger, D. Goldfarb, J.J. Xu, and W. Yin, An iterated regularization method for total variation based on image restoration, UCLA CAM Report, 04-13, (2004)]. to recover finer scales. We also present an analytical study of the model disc…

Blind deconvolutionDeblurringMathematical optimizationBregman divergenceTotal variation denoisingRegularization (mathematics)Electronic Optical and Magnetic MaterialsKernel (image processing)Iterated functionApplied mathematicsComputer Vision and Pattern RecognitionElectrical and Electronic EngineeringSoftwareImage restorationMathematicsInternational Journal of Imaging Systems and Technology
researchProduct

Free-depths reconstruction with synthetic impulse response in integral imaging

2015

Integral Imaging provides spatial and angular information of three-dimensional (3D) objects, which can be used both for 3D display and for computational post-processing purposes. In order to recover the depth information from an integral image, several algorithms have been developed. In this paper, we propose a new free depth synthesis and reconstruction method based on the two-dimensional (2D) deconvolution between the integral image and a simplified version of the periodic impulse response function (IRF) of the system. The period of the IRF depends directly on the axial position within the object space. Then, we can retrieve the depth information by performing the deconvolution with compu…

Blind deconvolutionIntegral imagingComputer scienceImage qualitybusiness.industryFast Fourier transformImage processingImpulse (physics)Atomic and Molecular Physics and OpticsOpticsDigital image processingDeconvolutionbusinessImpulse responseOptics Express
researchProduct