abstract: Up to 25 percent of the operating budget for contaminated site restoration projects is spent on site characterization, including long-term monitoring of contaminant concentrations. The sensitivity, selectivity, and reproducibility of analytical methods have improved to the point where sampling techniques bear the primary responsibility for the accuracy and precision of the data. Most samples represent discrete concentrations in time and space; with sampling points frequently limited in both dimensions, sparse data sets are heavily extrapolated and the quality of data further limited. Methods are presented for characterizing contaminants in water (groundwater and surface waters) and indoor air. These techniques are integrative, providing information averaged over time and/or space, as opposed to instantaneous point measurements. Contaminants are concentrated from the environment, making these methods applicable to trace contaminants. These methods have the potential to complement existing techniques, providing the practitioner with opportunities to reduce costs and improve the quality of the data used in decision making. A conceptual model for integrative sampling of environmental waters is developed and a literature review establishes an advantage in precision for active samplers. A programmable sampler was employed to measure the concentration of chromate in a shallow aquifer exhibiting time-dependent contaminant concentrations, providing a unique data set and sustainability benefits. The analysis of heat exchanger condensate, a waste stream generated by air conditioning, is demonstrated in a non-intrusive method for indoor air quality assessment. In sum, these studies present new opportunities for effective, sustainable environmental characterization. / Dissertation/Thesis / Doctoral Dissertation Civil and Environmental Engineering 2015

A urbanização é uma das ações antrópicas que mais crescem no mundo atual. Por este motivo pesquisas ecológicas são realizadas nas cidades com o objetivo de reconhecer seus impactos, e as aves são utilizadas como uma das ferramentas para diagnóstico ambiental. Assim, o presente estudo avaliou o método de levantamento de aves por ponto fixo, método amplamente utilizado em estudos com aves em diversos ambientes. Foram analisados três pontos que podem influenciar a amostragem de aves através deste método: 1) o habitat onde o levantamento é realizado, observando a composição dos elementos urbanos existentes na cidade; 2) o intervalo de tempo adotado em cada ponto fixo para a coleta de dados; 3) os fatores potencialmente prejudiciais a observação de aves, tais como o ruído sonoro urbano e a presença de conversas causadas por pessoas curiosas. Com a área de estudo estratificada a partir da quantidade de cobertura arbórea existente nos bairros abrangidos, 90 unidades amostrais foram selecionadas. Nestes, foram quantificados os elementos urbanos presentes, a riqueza, o número de contato de aves, os ruídos sonoros e a presença de conversas. Os resultados demonstraram que a reunião de um número maior de espécies e contatos pode ser favorecida pelas áreas de cobertura arbórea, enquanto áreas construídas e pisos impermeáveis podem prejudicar o número de espécies, sendo o número de contato prejudicado apenas pelas áreas de pisos impermeáveis. O número de espécies observadas não foi significativamente diferente após nove minutos de coleta de dados, entretanto o número de contatos continuou crescendo, demonstrando haver recontagens de indivíduos após este intervalo. A riqueza de espécies foi significativamente diferente entre os dados coletados no período seco e no período chuvoso. Conforme houve a maior presença do ruído sonoro urbano menor foi o número de espécies e contatos obtidos nos pontos. A incidência de conversas ocasionadas por pessoas curiosas foi baixa não prejudicando as coletas de dados. Os resultados encontrados sugerem que: o levantamento de aves no meio urbano através do ponto fixo deve considerar a composição do ambiente, já que a riqueza e o número de contato podem variar de acordo com a presença dos diferentes elementos; sejam adotados intervalos de tempo por ponto não superiores a nove minutos; quando possível diferentes épocas do ano devem ser utilizadas para as coletas de dados, visto que podem ser encontradas diferenças entre as estações; sejam escolhidos locais e momentos para as coletas de dados com baixo ruído sonoro. Por fim, o método de ponto fixo foi considerado eficaz para amostragem de aves urbanas, desde que tais cuidados sejam considerados. / The urbanization is one of the anthropic activities with the highest growth rate in the world. Due to this reason, ecological research are conducted in the cities with the goal of recognizing its impacts, using birds as one of the tools to assess the environmental diagnosis. Therefore, the present study assessed the samples by point counts method, which is broadly used for bird census in many environments. Three issues that might affect the sampling of the birds by using this method were analyzed: 1) the habitat where the sampling is performed, observing the urban elements presented in the city; 2) the period of point count duration spent in each sample; 3) the potential factors which disturb the birds detectability, as urban noise and presence of curious citizens who can talk to the researcher in the point count. The research area was stratified from the amount of tree canopies in the selected suburbs, where 90 sample units were selected. In these units, the presence of urban elements, the richness, the number of birds contacts, the noise and the presence of conversations were quantified. The results showed that the number of species and contacts can be benefited from the tree canopy area, while build up areas and impermeable grounds may harm the number of species, although the contact number is harmed only by the impermeable grounds. The number of observed species did not differ significantly after nine minutes of sample period, however the number of contacts kept increasing, demonstrating a repeated counting birds after this interval. The species richness was significantly different between the samples collected in dry and wet seasons. As the urban noise increased, a lower number of species and birds contacts was acknowledged. The incidence of conversation performed by curious people was low, not being able to harm the sample collection. The results suggest that: the bird survey inside the cities by point counts should consider the composition of environment, since the richness and the number of birds contacts can vary according to the presence of different elements; the time of interval should not exceed nine minutes; when possible, different annual seasons should be used for sampling, since differences may be found among them; places and moments for the sampling should be chosen with a low noise. Finally, the point counts method was considered efficient for the sampling of urban birds, provided that such care are considered.

La génération aléatoire d'objets combinatoires est un problème qui se pose dans de nombreux domaines de recherche (réseaux de communications, physique statistique, informatique théorique, combinatoire, etc.). Couramment, la distribution des échantillons est définie comme la distribution stationnaire d'une chaîne de Markov ergodique. En 1996, Propp et Wilson ont proposé un algorithme permettant l'échantillonnage sans biais de la distribution stationnaire. Ce dernier appelé aussi algorithme de simulation parfaite, requiert la simulation en parallèle de tous les états possibles de la chaîne. Plusieurs stratégies ont été mises en œuvre afin de ne pas avoir à simuler toutes les trajectoires. Elles sont intrinsèquement liées à la structure de la chaîne considérée et reposent essentiellement sur la propriété de monotonie, la construction de processus bornants qui exploitent la structure de treillis de l'espace d'états ou le caractère local des transitions. Dans le domaine des réseaux de communications, on s'intéresse aux performances des réseaux de files d'attente. Ces derniers se distinguent en deux groupes : ceux dont la distribution stationnaire possède une forme produit qui est facile à évaluer par le calcul et les autres. Pour ce dernier groupe, on utilise la génération aléatoire pour l'évaluation de performances. De par la structure des chaînes qui leurs sont associées, les réseaux ouverts de files d'attente se prêtent bien à la simulation via l'algorithme de simulation parfaite mais pas les réseaux fermés. La difficulté réside dans la taille de l'espace des états qui est exponentielle en le nombre de files à laquelle s'ajoute une contrainte globale à savoir le nombre constant de clients. La contribution principale de cette thèse est une nouvelle structure de données appelée diagramme. Cette structure est inspirée de la programmation dynamique et introduit une nouvelle technique de construction de processus bornant. La première partie du manuscrit est consacrée à la mise en œuvre de l'algorithme de Propp et Wilson pour des réseaux fermés n'étant pas nécessairement à forme produit. La représentation des états par un diagramme et l'opération de transition pour le processus bornant a dès lors une complexité polynomiale en le nombre de files et de clients. Cette technique est ensuite étendue aux réseaux fermés multiclasses ainsi qu'aux réseaux possédant des synchronisations. Une spécification des ensembles d'objets pouvant être représentés par un diagramme ainsi que des algorithmes agissant sur cette structure de données sont également proposés dans cette thèse. La méthode de Botzmann est une autre technique de simulation sans biais. Basée sur la combinatoire analytique, elle permet l'échantillonnage uniforme d'objets appartenant à une même classe combinatoire. Elle est employée dans la seconde partie de cette thèse afin d'échantillonner la distribution stationnaire de réseaux fermés à forme produit et pour la génération des multi-ensembles de taille fixe. Dans ce cadre, les diagrammes sont une nouvelle fois mis à profit. Enfin, la troisième partie présente les logiciels découlant des travaux présentés tout au long de ce travail, et qui implémentent les diagrammes et mettent en œuvre la simulation parfaite de réseaux fermés de files d'attente. / Random generation of combinatorial objects is an important problem in many fields of research (communications networks, theoretical computing, combinatorics, statistical physics, ...). This often requires sampling the stationary distribution of an ergodic Markov chain. In 1996, Propp and Wilson introduced an algorithm to produce unbiased samples of the stationary distribution, also called a perfect sampling algorithm. It requires parallel simulation of all possible states of the chain. To avoid simulating all the trajectories, several strategies have been implemented. But they are related to the structure of the chain and require a monotonicity property, or a construction of a bounding chain that exploits the lattice structure of the state space or the local character of the transitions.In the field of communications networks, attention is paid to the performance of queueing networks, that can be distinguished into two groups: the networks that have a product form stationary distribution which is easy to compute. Random generation can be used for the others. Perfect sampling algorithms can be used for open queueing networks, thanks to the lattice structure of their state space. Unfortunately, that is not the case for closed queueing networks, due to the size of the state space which is exponential in the number of queues and a global constraint (a constant number of customers). The main contribution of this thesis is a new data structure called a diagram. It is inspired by dynamic programming and allows a new technique of construction of bounding processes. The first part of the manuscript is devoted to the implementation of the Propp and Wilson algorithm for closed queueing networks. The representation of a set of states by a diagram and the transition operation for the bounding process has a polynomial complexity in the number of queues and customers. This technique is extended to closed multi-class networks and to networks with synchronizations. Specification of sets of objects that can be represented by a diagram and generic algorithms that use this data structure are proposed in this manuscript. The Boltzmann method is another unbiased sampling technique. It is based on analytical combinatorics and produces uniform samples from objects that belong to the same combinatorial class. It is used in the second part of this thesis in order to sample the stationary distribution of closed networks with product form and for the generation of multisets of fixed cardinality. Diagrams are used again in this context. Finally, the third part presents the software produced during this thesis, implementing diagrams and perfect simulation of closed queueing networks.

The thesis apply to reliability problems approach of Voronoi tessellation, typically used in the field of samples designs evaluation and for Monte Carlo samples reweighing. It is shown, this general technique estimation converges to that of Importance Sampling method despite it does not rely on Importance Sampling's auxiliary density. Consequently, reliability analysis could be divided into sampling itself and assessment of simulation results. As an extension of this idea, adaptive statistical sampling using QHull library was attempted.

De nombreuses structures utilisées industriellement peuvent être considérées comme des guides d'ondes, comme les plaques, les tuyaux ou encore le rails. La maintenance de ces structures nécessite de pouvoir détecter efficacement des défauts internes par le Contrôle Non Destructif. Nous nous intéressons dans ce manuscrit à l'application d'une méthode d'échantillonnage, la Linear Sampling Method, au CND des guides d'ondes élastiques, qui en particulier impose des sollicitations et des mesures à la surface du guide en régime temporel. La stratégie choisie repose sur une formulation modale et multi-fréquentielle de la LSM, spécifique aux guides d'ondes, qui permet une régularisation efficace et de nature physique du problème inverse, qui est par nature mal posé. Cette stratégie permet par ailleurs une optimisation du nombre et de la position des émetteurs et des récepteurs. Nous nous limitons dans un premier temps au cas scalaire du guide d'ondes acoustiques, pour ensuite s'attaquer au cas vectoriel, et par conséquent plus complexe, du guide d'ondes élastiques.L'efficacité de la méthode inverse est dans un premier temps démontrée sur des données artificielles (obtenues numériquement), puis sur des données réelles obtenues à l'aide d'expériences réalisées sur des plaques métalliques. Ces expériences confirment la faisabilité du CND par méthode d'échantillonnage dans un cadre industriel. Dans le cas où une seule sollicitation est réalisée, l'utilisation de la LSM est exclu. Nous utilisons une approche tout à fait différente et dite "extérieure", couplant une formulation mixte de quasi-réversibilité et une méthode de lignes de niveau, pour reconstruire le défaut. / Widely used structures in an industrial context, such as plates, pipes or rails, can be considered as waveguides. Hence efficient Non Destructive Testing techniques are needed in order to detect defects in these structure during their maintenance. This work is about adapting a sampling method, the Linear Sampling Method, to the context of NDT for elastic waveguides. This context implies that the sollicitations and measurements must be on the surface of the waveguide in a time-dependent regime. A modal and multi-frequency formulation of the LSM, specific to waveguides, has been chosen to solve the problem. This formulation allows an efficient and physical regularization of the inverse problem, which is naturally ill-posed. An optimization of the number of sources and measurements and of their positioning is possible thanks to the methodology used to solve the problem. The scalar case of an acoustic waveguide is considered as a first step, while the vectorial case of an elastic waveguide, more complex by nature, is addressed in a second time.The efficiency of the method is at first tested on artificial data (numerically made), and then on real data obtained from experiments on metallic plates. These experiments show the feasibility of using sampling methods for Non Destructive Testing in an industrial context. In the case when only one sollicitation is available, the LSM can not be applied. A completely different approach is then used, which is called the ``exterior'' approach, coupling a mixed formulation of quasi-reversibility and a level-set method in order to recover the shape of the defect.

Ce mémoire de thèse concerne l’identification des facteurs de risque d’une maladie spécifique présentant une hétérogénéité spatiale au sein d’une région donnée. Plus particulièrement,nous nous sommes intéressés aux cancers des voies aéro-digestives supérieures(VADS) dans la région Nord-Pas-de-Calais (NPDC) en France. Pour cela, une étude cas témoins a d’abord été réalisée à partir de la création d’un échantillon d’individus sains qui n’étaient pas affectés par des tumeurs cancéreuses (les témoins) et d’un échantillon d’individus atteints du cancer (les cas - ou patients), recrutés dans les centres de soins dans le cadre des projets de recherche DEREDIA et NOFARIS. Concernant la méthodologie,des modèles binaires spatiaux répondant à l’objectif ont été développés à partir de travaux issus des domaines de recherche en statistique/économétrie des comportements(analyse des décisions) ainsi qu’en statistique spatiale. Un des apports méthodologiques de la thèse repose sur la combinaison de techniques provenant de ces deux champs de recherche. Dans une première partie, nous avons utilisé un modèle spatial binaire paramétrique contenant une variable spatiale latente de choix dans le cadre d’un échantillonnage des données. Ce problème est connu sous le nom de "Choice-Based Sampling" (CBS) dans les modèles discrets. Contrairement à l’échantillon aléatoire où tous les éléments de la population ont la même probabilité d’être choisi, l’échantillonnage CBS dans le modèle discret est un type d’échantillonnage dans lequel la classification de la population est faite sous forme de sous-ensembles (strates) basés sur des choix alternatifs. Dans ce contexte,l’utilisation de la procédure d’estimation par maximum de vraisemblance standard (MLE)dans le CBS pourrait mener à des estimations incohérentes (asymptotiquement biaisées).Nous avons adopté ainsi le principe du maximum de vraisemblance auprès de l’étude de scas-témoins spatiaux. Nous avons également fourni un estimateur des moments généralisés(GMM), basé sur les résidus généralisés. Dans une seconde partie, un modèle spatial binaire semi-paramétrique a été considéré. Nous présentons dans ces parties, une simulation de Monte Carlo pour étudier la performance des méthodes d’estimation au sein d’un échantillon final, que nous avons ensuite appliqué aux données du cancer VADS dans la région Nord-Pas-de-Calais. La troisième partie est consacrée à l’étude d’une fonction de risque spatiale en présence de données entachées d’erreurs. En effet, dans le cadre des données cas-témoins considérées, nous supposons que certaines données de type déclarative ne soient pas correctes. Une application de cette méthode à la cartographie du risque de développer un cancer VADS dans la région Nord-Pas-de-Calais a été étudiée. La dernière partie est consacrée à un modèle de durée spatial et son application aux données considérées. / This thesis concerns the identification of risk factors for a certain type of diseasepresenting a certain spatial heterogeneity in a given region.. More specifically, we are interested in cancers of the upper aerodigestive tract (UADT) cancers in the Nord-Pasde-Calais region (NPDC), France. For this, a case-control study was first carried out bycreating a sample of healthy individuals who are not affected by cancerous tumors (thecontrols) and a sample of individuals with cancer (Cases or patients), recruited in healthcenters as part of DEREDIA and NOFARIS research projects. From a methodologicalpoint of view, spatial binary models which meet the objective have been developed onthe basis of studies in statistical/behavioral econometrics (decision analysis) and spatialstatistics. One of the methodological contributions of the thesis on this plan is the combinationof techniques from these two fields of research.In the first part, we used a spatial binary parametric models containing spatial latentchoice variable in a context of sampling data. This problem is known as Choice-BasedSampling (CBS) in discrete choice model. Unlike the random sample where all items in the population have the same probability of being chosen, the Choice-Based Sampling indiscrete choice model is a type of sampling where the classification of the population intosubsets to be sampled is based on the choices or outcomes. In this context, the use ofstandard Maximum likelihood estimation (MLE) procedure in CBS could lead to an inconsistent(asymptotically biased) estimation. Thus, we adapt the principle of maximumlikelihood in our context of spatial case-control studies. We also provide a GMM estimatorbased on the generalized residuals.In the second part, a spatial semi-parametric binary model was considered. We present inthese parts a Monte Carlo experiment to investigate the finite sample performance of theseestimation methods, then we apply to the (UADT) cancer data in the Nord-Pas-de-Calaisregion.The third part is devoted to the study of a spatial risk function in the presence of datacontaminated by measurement errors. Indeed, in the context of the considered case-controlstudy, it is very likely that certain data transmitted by the patients is not correct. Anapplication of this method to the mapping of the risk of having UADT cancer in the Nord-Pas-de-Calais region was studied. The last part is devoted to a spatial duration modeland its application to the real data was considered.

Video classification is the task of producing a label that is relevant to the video given its frames. Active learning aims to achieve greater accuracy with fewer labeled training instances through a designed query strategy that can select representative instances from the unlabeled training instances and send them to be labeled by an oracle. It is successfully used in many modern machine learning problems. To figure out how different active learning strategies work on the video classification task, we test several active learning strategies including margin sampling, standard deviation sampling, and center sampling on Temporal Segment Networks (TSN, a classic neural network designed for video classification). We profile these three active learning strategies on systematic control experiments and get the respective models, then we compare these models’ confusion matrix, data distribution, and training log with the baseline models after the first round of query. We observe that the comparison results among models are different under different evaluation criteria. Among all the evaluation criteria we use, the average performance of center sampling is better than that of random sampling, while margin sampling and standard deviation sampling get much worse performance than random sampling and center sampling. The training log and data distribution indicate that margin sampling and standard deviation are prone to select outliers inside the data which are hard to learn but apparently not helpful to improve the model performance. Center sampling will easily outperform random sampling by F1-score. Therefore, the evaluation criteria should be formulated according to the actual application requirements. / Videoklassificering är uppgiften att producera en etikett som är relevant för videon uifrån videons bildsekvens. Aktivt lärande syftar till att uppnå större noggrannhet med färre märkta träningsexempel genom en designad frågestrategi för att välja representativa instanser som ska märkas av ett orakel från de omärkta träningsexemplen, och används framgångsrikt i många moderna maskininlärningsproblem. För att ta reda på hur olika aktiva inlärningsstrategier fungerar på videoklassificeringsuppgifter testar vi flera aktiva strategier inklusive marginalsampling, standardavvikelsessampling samt sampling baserat på Temporal Segment Networks (TSN, som är ett klassiskt neuralt nätverk designat för videoklassificeringsuppgift). Vi testar dessa tre aktiva inlärningsstrategier på systematiska kontrollexperiment, sedan jämför vi dessa modellers förvirringsmatris, datamängdsdistribution, träningslogg med baslinjemodellens efter den första frågeomgången. Vi observerar att endast metoden ”urval av centra” överträffar slumpmässigt urval. Metoden med slumpmässiga provtagningar samt metoden med är benägna att välja extremvärden som är svåra att lära sig men tydligen inte till hjälp för att förbättra modellens prestanda.

Inom gruvindustri är provtagning viktigt för att företag ska kunna försäkra sig om produkters egenskaper. Vid skeppslastning i Luleå hamn utför LKAB provtagning av järnmalmsprodukten MPBO. För att utföra representativa provtagningar är provtagningsanläggningen i hamnen designad enligt ISO 3082. Enligt standarden krävs vetskap om produktens kvalitetsvariation är klassificerad som liten, medel eller stor. Enligt ISO 3082 måste kvantifieringen och klassificeringen av kvalitetsvariationen genomföras genom metoder föreskrivna i ISO 3084. Examensarbetet syftade till att enligt ISO 3082 och ISO 3084 kvantifiera, klassificera och bedöma kvalitetsvariationen och provtagningsprecisionen utifrån 11 kvalitetsparametrar för produkten MPBO. Resultatet av examensarbetet visade klassificering av liten kvalitetsvariation för kvalitetsparametrarna järn (Fe), kiseldioxid (SiO2) samt fosfor (P) enligt gränsvärden beskrivna i ISO 3082. Resultatet av examensarbetet visade även att provtagningsprecisionen för kvalitetsparametrarna Fe, SiO2 och P vara mycket liten i förhållande rekommenderad provtagningsprecision enligt ISO 3082. De övriga kvalitetsparametrarna som undersöktes kunde dock inte klassificeras eller bedömas utifrån ISO 3082 ty avsaknaden av värden på rekommenderad provtagningsprecision och gränsvärden för klassificeringar av kvalitetsvariation. ISO 3084 föreskriver att undersökningen måste genomföras minst fem gånger vid bedömning av en malmprodukt. För att försäkra sig om kvalitetsvariationen för produkten rekommenderades LKAB därför att utföra ytterligare fler likande undersökningar i framtiden. Om LKAB planerar genomföranden av liknande undersökningar rekommenderades företaget även att utföra undersökningar enligt ISO 3085 för att bestämma provberednings- och analysvariationen. / Sampling is important for mining companies to obtain knowledge of the characteristics of their product. When loading ships in the port of Luleå, the company LKAB performs sampling of the iron-ore product MPBO. To perform representative sampling, the sampling facility in the port is designed in accordance with ISO 3082. According to the standard, knowledge is required if the product's quality variation is classified as small, medium, or large. According to ISO 3082, the quantification and classification of the quality variation must be carried out using methods prescribed in ISO 3084. The aimed aim of the thesis was to quantify, classify and assess the quality variation and sampling precision of 11 quality parameters to the product MPBO according to methods prescribed in ISO 3082 and ISO 3084. The results of the thesis showed classification of small quality variation for the quality parameters iron (Fe), silica (SiO2) and phosphorus (P) according to limit values prescribed ​in ISO 3082. Results also showed that the sampling precision for the quality parameters Fe, SiO2 and P was very small in relation to the recommended sampling precision according to ISO 3082. The precision and quality variation of the other quality parameters examined could not be classified or assessed based on ISO 3082 due to a lack of limit values. ISO 3084 prescribes those similar investigations must be carried out at least five times when assessing an ore product. To ensure the quality variation of the product, LKAB was therefore recommended to carry out further investigations in the future. If LKAB plans to carry out more investigations about the product, the company was also recommended to carry out methods prescribed in ISO 3085 to determine sample preparation variation and analysis variation.

Segmentation of magnetic resonance images is an important part of planning radiotherapy treat-ments for patients with brain tumours but due to the number of images contained within a scan and the level of detail required, manual segmentation is a time consuming task. Convolutional neural networks have been proposed as tools for automated segmentation and shown promising results. However, the data sets used for training these deep learning models are often imbalanced and contain data that does not contribute to the performance of the model. By carefully selecting which data to train on, there is potential to both speed up the training and increase the network’s ability to detect tumours. This thesis implements the method of importance sampling for training a convolutional neural network for patch-based segmentation of three dimensional multimodal magnetic resonance images of the brain and compares it with the standard way of sampling in terms of network performance and training time. Training is done for two different patch sizes. Features of the most frequently sampled volumes are also analysed. Importance sampling is found to speed up training in terms of number of epochs and also yield models with improved performance. Analysis of the sampling trends indicate that when patches are large, small tumours are somewhat frequently trained on, however more investigation is needed to confirm what features may influence the sampling frequency of a patch. / Segmentering av magnetröntgenbilder är en viktig del i planeringen av strålbehandling av patienter med hjärntumörer. Det höga antalet bilder och den nödvändiga precisionsnivån gör dock manuellsegmentering till en tidskrävande uppgift. Faltningsnätverk har därför föreslagits som ett verktyg förautomatiserad segmentering och visat lovande resultat. Datamängderna som används för att träna dessa djupinlärningsmodeller är ofta obalanserade och innehåller data som inte bidrar till modellensprestanda. Det finns därför potential att både skynda på träningen och förbättra nätverkets förmåga att segmentera tumörer genom att noggrant välja vilken data som används för träning. Denna uppsats implementerar importance sampling för att träna ett faltningsnätverk för patch-baserad segmentering av tredimensionella multimodala magnetröntgenbilder av hjärnan. Modellensträningstid och prestanda jämförs mot ett nätverk tränat med standardmetoden. Detta görs förtvå olika storlekar på patches. Egenskaperna hos de mest valda volymerna analyseras också. Importance sampling uppvisar en snabbare träningsprocess med avseende på antal epoker och resulterar också i modeller med högre prestanda. Analys av de oftast valda volymerna indikerar att under träning med stora patches förekommer små tumörer i en något högre utsträckning. Vidareundersökningar är dock nödvändiga för att bekräfta vilka aspekter som påverkar hur ofta en volym används.

This dissertation approaches high resolution scatterometry from a new perspective. Three related general topics are addressed: high resolution σ^0 imaging, wind estimation from high resolution σ^0 images over the ocean, and high resolution wind estimation directly from the scatterometer measurements. Theories of each topic are developed, and previous approaches are generalized and formalized. Improved processing algorithms for these theories are developed, implemented for particular scatterometers, and analyzed. Specific results and contributions are noted below. The σ^0 imaging problem is approached as the inversion of a noisy aperture-filtered sampling operation-extending the current theory to deal explicitly with noise. A maximum aposteriori (MAP) reconstruction estimator is developed to regularize the problem and deal appropriately with noise. The method is applied to the SeaWinds scatterometer and the Advanced Scatterometer (ASCAT). The MAP approach produces high resolution σ^0 images without introducing the ad-hoc processing steps employed in previous methods. An ultra high resolution (UHR) wind product has been previously developed and shown to produce valuable high resolution information, but the theory has not been formalized. This dissertation develops the UHR sampling model and noise model, and explicitly states the implicit assumptions involved. Improved UHR wind retrieval methods are also developed. The developments in the σ^0 imaging problem are extended to deal with the nonlinearities involved in wind field estimation. A MAP wind field reconstruction estimator is developed and implemented for the SeaWinds scatterometer. MAP wind reconstruction produces a wind field estimate that is consistent with the conventional product, but with higher resolution. The MAP reconstruction estimates have a resolution similar to the UHR estimates, but with less noise. A hurricane wind model is applied to obtain an informative prior used in MAP estimation, which reduces noise and ameliorates ambiguity selection and rain contamination.