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…
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…
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…
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…
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…
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 …
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…
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 …
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…
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…