Reproduction de : Thèse de doctorat : Automatique et informatique industrielle : Villeneuve d'Ascq, Ecole centrale de Lille : 2006. / Résumé en français et en anglais. Titre provenant de la page de titre du document numérisé. Bibliogr. p. 105-109.

In the subtropical oligotrophic ocean, nitrogen fixation is an important source of new nitrogen (N) for supporting biological production. Previous studies have found that nitrogen-fixing Diatom-Diazotroph Associations (DDAs) are in high abundance in the intermediate salinity zone of large river plumes such as the Amazon and Mekong rivers, while Trichodesmium spp. becomes more abundant at higher salinities. This recurring pattern in the Amazon River plume suggests that strong salinity and nutrient gradients within the river plumes may lead to a cascade in diazotroph communities. I hypothesized that the Mississippi River, a major source of freshwater, nutrients and sediments to the northern Gulf of Mexico, creates a similar distribution of diazotroph communities. The relationship between large diazotrophs and salinity was examined in samples collected in July 2011 during a flood outflow from the Mississippi River. The dominant DDA, Hemiaulus spp. – Richelia spp., was at greatest abundance (≈31,000 cells L-1) west of the birdfoot delta on the periphery of the plume (≈29 salinity) where bottom water hypoxia was also observed. Trichodesmium spp., a cyanobacterium genus that occurs in both colonial and free trichome morphologies, was abundant at both high (≈35) salinities east of the delta reaching 20+ colonies L-1, as well as in the fresher (≈28) waters of the plume where it reached 3,500 trichomes L-1. Diazotroph distributions were separated east and west of the Mississippi River outflow, with DDAs being most abundant over bottom water hypoxic regions to the west and Trichodesmium spp. in high abundance to the east. The diazotroph – salinity gradient relationships present within the Amazon River plume were not present within the Gulf of Mexico. This study suggests that environmental factors other than salinity, such as nutrients or hypoxia, are influencing the distribution of diazotrophs around the Mississippi River plume. The seasonal hypoxia seen in the Gulf of Mexico with the co-occurring DDA increase could appear in other river systems. / text

Analysis of circular data becomes more and more popular in many fields of studies. In this report, I present two statistical analysis of circular data using von Mises distributions. Firstly, the maximization-expectation algorithm is reviewed and used to classify and estimate circular data from the mixture of von Mises distributions. Secondly, Forward Filtering Backward Smoothing method via particle filtering is reviewed and implemented when circular data appears in the dynamic state-space models. / text

Multiple distribution travel time data has been observed in signalized corridors as well as freeway corridors. This behavior is typically caused by congestion, uncoordinated signals, or routes through a coordinated corridor that are not a priority. On the SR140 corridor near the Jimmy Carter Boulevard / I-85 Interchange, it was found that the travel times recorded on the corridor contained multiple distributions and thus a methodology was sought to properly separate the distributions in order to perform more robust statistical analysis. Next, an R statistical language library was found, called “mixtools”, which contained a multiple gamma distribution fitting function called “gammamixEM”. Gamma distributions were chosen for this application as typical travel time distributions tend contain a one sided tail. This function was used in conjunction with a monte-carlo approach to find fits for one to six distributions. The accuracy of the fit was confirmed through visual inspection of the plotted distributions. Then, the Akaike Information Criteria were used to compare the fits to determine the best fit number of distributions. This thesis contains a detailed outline of the algorithm as well as results from the algorithm for the combined Tuesday dataset from this project. It was found that the approach worked well for 60 out of 70 cases. In the 10 cases that were not ideal, the distributional fits make sense on a statistical level, however, for the purposes of the before and after project the next best Akaike Information Criteria value fit may need to used. These 10 cases tended to split obvious single distributions into two distributions, which is not desirable in a before and after analysis where one is not only testing individual distributions before and after construction but also determining if distributions were created or removed as a result of the change in operation of the interchange.

Interactions are crucial for galaxy formation and profoundly affect their evolution. However, our understanding of the impact of interactions on star formation and activity of the central supermassive black hole remains incomplete. In the canonical picture of the interaction process, these processes are expected to undergo a strong enhancement, but some recent studies have not found this prediction to be true in a statistically meaningful sense. This thesis uses a sample of local interactions observed from the ultraviolet to the far-infrared and a suite of N-body hydrodynamic simulations of interactions to examine the evolution of star formation, stellar mass, dust properties, and spectral energy distributions (SEDs) over the interaction sequence. / Astronomy

Šiame magistro baigiamajame darbe yra aiškiai ir plačiai nagrinėjami tikimybių teorijos dėsniai, aiškinamos pagrindinės savybės ir tarpusavio ryšiai. Yra taip pat pateikiama atsitiktinių dydžių serijos aproksimavimas vienu iš tų dėsnių. Dalinant ir dauginant nepriklausomus atsitiktinius dydžius vienus iš kitų randami nauji pasiskirstymai ir jų formos. Visa tai suprasti palengvina prieduose pateiktos vaizdinės išraiškos. / In this master thesis is clearly and widely considered laws of probability theory, explained the main features and mutual relations. There is also a series of random variables approximated by the one of those laws. There is given interest results of the product XY and the ratio X/Y where X and Y is randomly distributed variables. All that facilitates to understand added Additives with the visual expression.

Darbe nagrinėjami vienmačių nepriklausomų dydžių tiesiškai normuotų maksimumų skirstinių konvergavimo greičiai perkėlimo teoremoje. Tiriami du atvejai: • konvergavimo greičio įvertis, kai dydžių skirstiniai yra maks – stabilūs; • įverčiai, kai atsitiktiniai dydžiai yra apibendrintieji Pareto. Nagrinėjami netolygieji konvergavimo greičio įverčiai, kai nepriklausomų atsitiktinių dydžių skaičius pasiskirstęs pagal geometrinį arba diskretųjį tolygųjį skirstinį. Taip pat randamos tiksliosios absoliučiosios paklaidos pastarųjų skirstinių atveju. Atliekama kompiuterinė konvergavimo greičių įverčių ir absoliučiųjų paklaidų palyginamoji analizė. Tyrimo rezultatai patikslina A. Aksomaičio (1999) ir Gnedenkos (1982) darbų teiginius. / Asymptotics of maxima of independent and identically distributed random variables (i. i. d.) is presented in the paper. We will research the cases when the distributions are max – stable, distributions are generalized Pareto and the size of set of independent random variables is random. The non – uniform and uniform estimates of the rate of convergence for transfer theorem are obtained in this scheme. These estimations improve the result given in A. Aksomaitis (1999) and Gnedenko (1982).

No description available.

No description available.

Nagrinėjama silpnai priklausomų atsitiktinių dydžių statistika. Šio magistrinio darbo tikslas, turimą sumą, suvesti į nepriklausomų atsitiktinių dydžių sumą, kuri leistų tolimesniam tyrimui, pritaikyti žinomas teoremas, skaičiavimus bei rezultatus iš nepriklausomų atsitiktinių dydžių teorijos. / We analyze of weakly dependent random variables statistics. The objective of this master thesis is to deduce sum to independent random variables sum, which will be useful for applaying known theorems, calculations and results from the theory in independent random variables.