Search results for " Estimation"

Robust estimation of mean electricity consumption curves by sampling for small areas in presence of missing values

2017

In this thesis, we address the problem of robust estimation of mean or total electricity consumption curves by sampling in a finite population for the entire population and for small areas. We are also interested in estimating mean curves by sampling in presence of partially missing trajectories.Indeed, many studies carried out in the French electricity company EDF, for marketing or power grid management purposes, are based on the analysis of mean or total electricity consumption curves at a fine time scale, for different groups of clients sharing some common characteristics.Because of privacy issues and financial costs, it is not possible to measure the electricity consumption curve of eac…

Linearization and Sample Reuse in Variance Estimation

2004

Accounting for haplotype phase uncertainty in linkage disequilibrium estimation

2007

The characterization of linkage disequilibrium (LD) is applied in a variety of studies including the identification of molecular determinants of the local recombination rate, the migration and population history of populations, and the role of positive selection in adaptation. LD suffers from the phase uncertainty of the haplotypes used in its calculation, which reflects limitations of the algorithms used for haplotype estimation. We introduce a LD calculation method, which deals with phase uncertainty by weighting all possible haplotype pairs according to their estimated probabilities as evaluated by PHASE. In contrast to the expectation-maximization (EM) algorithm as implemented in the HA…

Generalized SCODEF Deformations on Subdivision Surfaces

2006

This paper proposes to define a generalized SCODEF deformation method on a subdivision surface. It combines an “easy-to-use” free-form deformation with a Loop subdivision algorithm. The deformation method processes only on vertices of an object and permits the satisfaction of geometrical constraints given by the user. The method controls the resulting shape, defining the range (i.e. the impact) of the deformation on an object before applying it. The deformation takes into account the Loop properties to follow the subdivision scheme, allowing the user to fix some constraints at the subdivision-level he works on and to render the final object at the level he wants to. We also propose an adapt…

Nonparametric estimation of quantile versions of the Lorenz curve

2018

Estimators of quantile versions of the Lorenz curve are proposed. The pointwise consistency and asymptotic normality of the estimators is proved. The efficiency of the estimators is also studied in simulations

Adaptive feedback linearizing control of linear induction motor considering the end-effects

2016

This paper proposes an input-output feedback linearization techniques for linear induction motors, taking into consideration the dynamic end-effects. As a main original content, this work proposes a new control law based on the on-line estimation of the induced-part time constant. The estimation law is obtained thanks to a Lyapunov based analysis and thus the stability of the entire control system, including the estimation algorithm, is intrinsically guaranteed. Moreover, with such an approach even the on-lihe variation of the induced-part time constant with the speed is retrieved, thus improving the behavior of previously developed approaches where such a variation vs. speed is considered …

A Nonlinear Observer for Rotor Flux Estimation of Induction Motor Considering the Estimated Magnetization Characteristic

2017

This paper proposes a nonlinear observer for induction machine drives based on space-vector dynamic model of induction machine, expressed in state form, which presents the peculiarity of taking into consideration the magnetic saturation of the iron core. This observer is particularly suitable in order to obtain high accuracy in rotor flux estimation, in both amplitude and phase position, during working conditions characterized by varying flux, among which the most important are those during electrical losses minimization. A Lyapunov-based convergence analysis is proposed in order to suitably compute the numerical observer gain guaranteeing the convergence of the estimation error. The propos…

Input-Output Feedback Linearization Control with On-Line Inductances Estimation of Synchronous Reluctance Motors

2021

This paper proposes an adaptive input-output Feedback Linearization (FL) techniques for Synchronous Reluctance Motor (SynRM) drives, taking into consideration the iron losses. As a main original content, this work proposes a control law based on a new dynamic model of the SynRM including iron losses as well as the on-line estimation of the static inductances. The on-line estimation of the SynRM static inductances permits to inherently take into consideration the magnetic saturation phenomena occuring on both axes. The estimation law is obtained thanks to a Lyapunov-based analysis and thus the stability of the entire control system, including the estimation algorithm, is intrinsically guaran…

Low-complexity AoA and AoD estimation in the transformed spatial domain for millimeter wave MIMO channels

2021

La estimación del ángulo de llegada (AoA) y del ángulo de salida (AoD) es fundamental para la búsqueda de celdas, las comunicaciones estables y el posicionamiento en los sistemas celulares de ondas milimétricas (mmWave). Además, el diseño de algoritmos de estimación de AoA/AoD de baja complejidad resulta también de gran importancia en el despliegue de sistemas prácticos para permitir un cálculo rápido y eficiente de la conformación de haz. La estimación paramétrica del canal en ondas milimétricas permite describir la matriz del canal como una combinación de trayectorias de señales dependientes de la dirección, explotando la característica de dispersión de los canales mmWave. En este context…

Quantifying uncertainty in high resolution biophysical variable retrieval with machine learning

2022

The estimation of biophysical variables is at the core of remote sensing science, allowing a close monitoring of crops and forests. Deriving temporally resolved and spatially explicit maps of parameters of interest has been the subject of intense research. However, deriving products from optical sensors is typically hampered by cloud contamination and the trade-off between spatial and temporal resolutions. In this work we rely on the HIghly Scalable Temporal Adaptive Reflectance Fusion Model (HISTARFM) algorithm to generate long gap-free time series of Landsat surface reflectance data by fusing MODIS and Landsat reflectances. An artificial neural network is trained on PROSAIL inversion to p…