Éditeur(s) : HAL CCSD
Résumé : 20 pp
We first analyze some atmospheric parameters measured in 2004 at the top of La Soufrière volcano: wind speed, pressure and temperature. Next, we study the stochastic process of the wind speed modulus which is of interest for prediction of pollution induced by the plume. We fit to the data various models : FARIMA, periodic trend plus multifractional Brownian noise, multifractal continuous cascades. The estimations show that they evoluate during some transition phases in response to environment changes. Thus, we finally suggest, for future works, some settings that should be more appropriate: time series with regime changes and stochastic processes in random environment.
https://hal.archives-ouvertes.fr/hal-00165572

hal-00165572
https://hal.archives-ouvertes.fr/hal-00165572
https://hal.archives-ouvertes.fr/hal-00165572/document
https://hal.archives-ouvertes.fr/hal-00165572/file/Windsouf_v11.pdf

Éditeur(s) : HAL CCSD
Résumé : 15 pages
A Stochastic Differential Equation appearing in the statistical theory of turbulence is extended in random environment by assuming that its two parameters are switched by an unobserved continuoustime Markov chain whose states represent the states of the environment. A Dirichlet process is placed as a prior on the space of the sample paths of this chain, leading to a hierarchical Dirichlet model whose estimation is done both on simulated data and on real data of wind speed measured at the entrance of a mangrove ecosystem.
https://hal.archives-ouvertes.fr/hal-00455050

hal-00455050
https://hal.archives-ouvertes.fr/hal-00455050
https://hal.archives-ouvertes.fr/hal-00455050/document
https://hal.archives-ouvertes.fr/hal-00455050/file/CSDA06_Srik_Hal.pdf

Éditeur(s) : HAL CCSD Elsevier
Résumé : International audience
Wind energy production is very sensitive to instantaneous wind speed fluctuations. Thus rapid variation of wind speed due to changes in the local meteorological conditions can lead to electrical power variations of the order of the nominal power output. The high variability of this renewable energy source can caused a disruptive effect on power quality and reliability, in non-interconnected island networks as in Guadeloupe (French West Indies). To palliate these difficulties, it is essential to identify and characterize the wind speed distribution over very short time intervals. This allows anticipating the eventuality of power shortage or power surge. Therefore, it is of interest to categorize wind speed fluctuations into distinct classes and to estimate the probability of a distribution to belong to a class. This paper presents a method for classifying wind speed distributions by estimating a finite mixture of Dirichlet distributions. The SAEM algorithm that we use provides a fine distinction between three wind speed distribution classes. It is a new nonparametric method for wind speed classification.
ISSN: 0960-1481

hal-01527881
https://hal.archives-ouvertes.fr/hal-01527881
DOI : 10.1016/j.renene.2011.03.024

Éditeur(s) : HAL CCSD
Résumé : 27 pages
Cascade Stochastic Differential Equation (SDE), a continuous time model for energy dissipation in turbulence, is a generalization of the Yaglom discrete cascade model. We extend this SDE to a model in random environment by assuming that its two parameters are switched by a continuous time Markov chain whose states represent the states of the environment. Moreover, a Dirichlet process is placed as a prior on the space of sample paths of this chain. We propose a Bayesian estimation method of this model which is tested both on simulated data and on real data of wind speed measured at the entrance of the mangrove ecosystem in Guadeloupe.
https://hal.archives-ouvertes.fr/hal-00286131

hal-00286131
https://hal.archives-ouvertes.fr/hal-00286131
https://hal.archives-ouvertes.fr/hal-00286131/document
https://hal.archives-ouvertes.fr/hal-00286131/file/Srik11_PhysicaDDspace.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
Les processus ponctuels temporel, spatial et spatio-temporel permettent de décrire divers phénomènes consistant en des distributions d'événements : on peut citer les occurrences d'infection en épidémiologie, les épicentres en sismologie, ou les décharges électriques en neurologie. Dans le cadre de la détection de la résurgence de maladies, nous considérons un processus doublement stochastique (Cox) défini par son processus intensité spatio-temporel. Il s'agit d'un modèle hiérarchique spatio-temporel à trois composantes pour la fonction d'intensité : un effet spatial, une tendance temporelle et un effet spatio-temporel. Des études par simulations numériques sont menées afin de vérifier la performance des estimateurs proposés
41èmes Journées de Statistique, SFdS, Bordeaux
Bordeaux, France, France

inria-00386679
https://hal.inria.fr/inria-00386679
https://hal.inria.fr/inria-00386679/document
https://hal.inria.fr/inria-00386679/file/p118.pdf

Éditeur(s) : HAL CCSD Springer
Résumé : International audience
Wind energy production is very sensitive to turbulent wind, in particular when wind power variations range from few seconds to 1 hour, are considered. Indeed rapid changes in the local meteorological condition as observed in tropical climate can provoke large variations of wind speed. Consequently the electric grid security can be jeopardized due to these fluctuations. This is particularly the case of island networks as in the Guadeloupean archipelago (French West Indies) where the installed 20 MW wind power already represents 11% of the electrical consumption. From 1 million wind sequences of duration 10 minutes, sampled at 1 Hz during the trade season, we proceed toward two objectives: i) the characterization of the wind speed sequences, ii) the dynamical simulation of the wind sequences using Langevin equation.
Progress in Turbulence and Wind Energy IV

ISBN : 978-3-642-28968-2.
hal-01527883
https://hal.archives-ouvertes.fr/hal-01527883
DOI : 10.1007/978-3-642-28968-2-50

Éditeur(s) : HAL CCSD
Résumé : Aricle soumis à Solar Energy
In order to qualify the fluctuating nature of solar radiation under tropical climate, we classify daily distributions of the clearness index kt by estimating a finite mixture of Dirichlet distributions without assuming any parametric hypothesis on these daily distributions. The method is applied to solar radiation measurements performed in Guadeloupe (16°2 N, 61 W) where important fluctuations can be observed even within a short period of a few minutes. The results put in evidence four distinct classes of distributions corresponding to different types of days. The sequence of such classes can be of interest for prediction.
https://hal.archives-ouvertes.fr/hal-00289567

hal-00289567
https://hal.archives-ouvertes.fr/hal-00289567
https://hal.archives-ouvertes.fr/hal-00289567/document
https://hal.archives-ouvertes.fr/hal-00289567/file/Article_Classif_soumis.pdf

Éditeur(s) : HAL CCSD
Résumé : Red blood cell hemodynamics influence blood rheology and thus circulatory function. Different authors showed that red blood cells are heterogeneous in blood flow. This heterogeneity could be explained by physical characteristics such as morphology, aggregability and deformability, but also by cellular and molecular environment. All these notions are found in sickle cell disease where sickle red blood cells become more rigid, leading to vascular occlusions, increased with an inflammatory context. In a preceding study, our results showed that velocity heterogeneity allow RBC classification, leading to different RBC sub-groups, using a dynamical approach and flow studies. In order to have a better understanding of the physiological meaning of such an heterogeneity, dynamical velocity experiences have been conducted in the case of normal and sickle red blood cells with different endothelial activations by proinflammatory cytokines, under a constant venular flow. Thus, normal and sickle red blood cells are classified into different sub-groups, showing their heterogeneity. Moreover, sub-population velocities and distribution evolve differently according to vascular state or treatment. These results show that red blood cell velocities and rheology depend on vascular environment and red blood cell morphology. However, the physiological meaning of this behavior should be explained by cellular and molecular effects of such activation.
https://hal.archives-ouvertes.fr/hal-00201461

hal-00201461
https://hal.archives-ouvertes.fr/hal-00201461
https://hal.archives-ouvertes.fr/hal-00201461/document
https://hal.archives-ouvertes.fr/hal-00201461/file/RBCV_Marianne_v1.pdf

Éditeur(s) : HAL CCSD
Résumé : Background Acute splenic sequestration is one of the major clinical forms of sickle cell disease. This potentially life-threatening complication is defined by a rapid sequestration of sickle red blood cells in the spleen. Approximately 30% of young patients will develop this complication and 49% of them will have recurrences. Methods The decision tree method is a statistical method that can act as a medical decision tool in the case of a complex biological problem. The decision tree method is used here to determine the variables involved in the severity and recurrence of acute splenic sequestration crises. Results A prior decision tree shows that platelet level, variation in spleen size, patient age and hygrometry also called relative humidity define acute splenic sequestration severity. A second one shows that spleen size variation, atmospheric pressure and patient age define recurrence. Conclusions For the first time, biological and environmental parameters are combined to discover some interesting rules which can lead to more accurate evaluations of acute splenic sequestration severity and recurrence. Thus, this method provides a sharp diagnostic tool which could improve medical treatment for better patient care.
https://hal.archives-ouvertes.fr/hal-00201460

hal-00201460
https://hal.archives-ouvertes.fr/hal-00201460
https://hal.archives-ouvertes.fr/hal-00201460v2/document
https://hal.archives-ouvertes.fr/hal-00201460/file/DT_Marianne_v2.pdf

Éditeur(s) : HAL CCSD
Résumé : National audience
Dans cet article, nous présentons une généralisation de l'opérateur d'agrégation 3Pi. Cette généralisation est appelée G3Pi, et peut être utilisée pourrésumer des éléments d'une série temporelle sur un intervalle. Quelques-unes des inégalités de cette généralisation sont présentées et démontrées.
Actes de l'Atelier de Fouille de données complexes : complexité liée aux données multiples et massives - AFD- EGC 2013

hal-00834021
https://hal.archives-ouvertes.fr/hal-00834021

Éditeur(s) : HAL CCSD Wiley
Résumé : International audience
ISSN: 0884-8173

hal-00858729
https://hal.archives-ouvertes.fr/hal-00858729

Éditeur(s) : HAL CCSD
Résumé : 32 pages
Wind energy production is very sensitive to instantaneous wind speed fluctuations. Thus rapid variation of wind speed due to changes in the local meteorological conditions can lead to electrical power variations of the order of the nominal power output. In small grids, as they exist for example on some islands in the French West Indies, such fluctuations can cause instabilities in case of intermediate power shortages. To palliate these difficulties, it is essential to identify and characterize the wind speed distributions. This allows to anticipate the eventuality of power shortage or power surge. Therefore, it is of interest to categorize wind speed fluctuations into distinct classes and to estimate the probability of a distribution to belong to a class. This paper presents a method for classifying wind speed histograms by estimating a finite mixture of Dirichlet distributions. The SAEM algorithm that we use provides a fine distinction between wind speed distribution classes. It's a new nonparametric method for wind speed sequences classification. However, we show that the wind speed distributions in each class correspond to specific Gram- Charlier densities.
https://hal.archives-ouvertes.fr/hal-00319608

hal-00319608
https://hal.archives-ouvertes.fr/hal-00319608
https://hal.archives-ouvertes.fr/hal-00319608v2/document
https://hal.archives-ouvertes.fr/hal-00319608/file/Article_dirichlet.pdf
ARXIV : 0810.4422