Grenoble Institute of Technology

About: Grenoble Institute of Technology is a education organization based out in Grenoble, France. It is known for research contribution in the topics: Hyperspectral imaging & Geology. The organization has 3427 authors who have published 5345 publications receiving 137158 citations. The organization is also known as: Grenoble INP.

Design of Chipless RFID Tags Printed on Paper by Flexography

Abstract: In this paper, we demonstrate for the first time that a 19-bit chipless tag based on a paper substrate can be realized using the flexography technique, which is an industrial high-speed printing process. The chipless tag is able to operate within the ultra-wide band (UWB) and has a reasonable size ( 7×3 cm 2) compared to state-of-the-art versions. Thus, it is possible to use this design for various identification applications that require a low unit cost of tags. Both the simulation and measurement results are shown, and performance comparisons are provided between several realization processes, such as classical chemical etching, flexography printing, and catalyst inkjet printing.

Pansharpening Based on Semiblind Deconvolution

Abstract: Many powerful pansharpening approaches exploit the functional relation between the fusion of PANchromatic (PAN) and MultiSpectral (MS) images. To this purpose, the modulation transfer function of the MS sensor is typically used, being easily approximated as a Gaussian filter whose analytic expression is fully specified by the sensor gain at the Nyquist frequency. However, this characterization is often inadequate in practice. In this paper, we develop an algorithm for estimating the relation between PAN and MS images directly from the available data through an efficient optimization procedure. The effectiveness of the approach is validated both on a reduced scale data set generated by degrading images acquired by the IKONOS sensor and on full-scale data consisting of images collected by the QuickBird sensor. In the first case, the proposed method achieves performances very similar to that of the algorithm that relies upon the full knowledge of the degrading filter. In the second, it is shown to outperform several very credited state-of-the-art approaches for the extraction of the details used in the current literature.

Pore-Scale Modeling of Viscous Flow and Induced Forces in Dense Sphere Packings

Abstract: We propose a method for effectively upscaling incompressible viscous flow in large random polydispersed sphere packings: the emphasis of this method is on the determination of the forces applied on the solid particles by the fluid. Pore bodies and their connections are defined locally through a regular Delaunay triangulation of the packings. Viscous flow equations are upscaled at the pore level, and approximated with a finite volume numerical scheme. We compare numerical simulations of the proposed method to detailed finite element simulations of the Stokes equations for assemblies of 8–200 spheres. A good agreement is found both in terms of forces exerted on the solid particles and effective permeability coefficients.

On Short-Term Load Forecasting Using Machine Learning Techniques and a Novel Parallel Deep LSTM-CNN Approach

Abstract: Since electricity plays a crucial role in countries’ industrial infrastructures, power companies are trying to monitor and control infrastructures to improve energy management and scheduling. Accurate forecasting is a critical task for a stable and efficient energy supply, where load and supply are matched. This article discusses various algorithms and a new hybrid deep learning model which combines long short-term memory networks (LSTM) and convolutional neural network (CNN) model to analyze their performance for short-term load forecasting. The proposed model is called parallel LSTM-CNN Network or PLCNet. Two real-world data sets, namely “hourly load consumption of Malaysia ” as well as “daily power electric consumption of Germany”, are used to test and compare the presented models. To evaluate the tested models’ performance, root mean squared error (RMSE), mean absolute percentage error (MAPE), and R-squared were used. In total, this article is divided into two parts. In the first part, different machine learning models, including the PLCNet, predict the next time step load. In the second part, the model’s performance, which has shown the most accurate results in the first part, is discussed in different time horizons. The results show that deep neural networks models, especially PLCNet, are good candidates for being used as short-term prediction tools. PLCNet improved the accuracy from 83.17% to 91.18% for the German data and achieved 98.23% accuracy in Malaysian data, which is an excellent result in load forecasting.