Ce travail porte sur l'estimation des incertitudes et la prévision de risques en qualité de l'air. Il consiste dans un premier temps à construire un ensemble de simulations de la qualité de l'air qui prend en compte toutes les incertitudes liées à la modélisation de la qualité de l'air. Des ensembles de simulations photochimiques à l'échelle continentale ou régionale sont générés automatiquement. Ensuite, les ensembles générés sont calibrés par une méthode d'optimisation combinatoire qui sélectionne un sous-ensemble représentatif de l'incertitude ou performant (fiabilité et résolution) pour des prévisions probabilistes. Ainsi, il est possible d'estimer et de prévoir des champs d'incertitude sur les concentrations d'ozone ou de dioxyde d'azote, ou encore d'améliorer la fiabilité des prévisions de dépassement de seuil. Cette approche est ensuite comparée avec la calibration d'un ensemble Monte Carlo. Ce dernier, moins dispersé, est moins représentatif de l'incertitude. Enfin, on a pu estimer la part des erreurs de mesure, de représentativité et de modélisation de la qualité de l'air

Multiple classifier system has shown to be an effective technique for classification. The success of multiple classifiers does not entirely depend on the base classifiers and/or the aggregation technique. Other parameters, such as training data, feature attributes, and correlation among the base classifiers may also contribute to the success of multiple classifiers. In addition, interaction of these parameters with each other may have an impact on multiple classifiers performance. In the present study, we intended to examine some of these interactions and investigate further the effects of these interactions on the performance of classifier ensembles. The proposed research introduces a different direction in the field of multiple classifiers systems. We attempt to understand and compare ensemble methods from the cooperation perspective. In this thesis, we narrowed down our focus on cooperation at training level. We first developed measures to estimate the degree and type of cooperation among training data partitions. These evaluation measures enabled us to evaluate the diversity and correlation among a set of disjoint and overlapped partitions. With the aid of properly selected measures and training information, we proposed two new data partitioning approaches: Cluster, De-cluster, and Selection (CDS) and Cooperative Cluster, De-cluster, and Selection (CO-CDS). In the end, a comprehensive comparative study was conducted where we compared our proposed training approaches with several other approaches in terms of robustness of their usage, resultant classification accuracy and classification stability. Experimental assessment of CDS and CO-CDS training approaches validates their robustness as compared to other training approaches. In addition, this study suggests that: 1) cooperation is generally beneficial and 2) classifier ensembles that cooperate through sharing information have higher generalization ability compared to the ones that do not share training information.

Being an immigrant in a Swedish school today might not be easy. It´s quite difficult to be accepted and becoming a part of an already functioning group. Difficulties with the Swedish language doesn´t make it easier. Besides that the requisites of the school curriculum program are very demanding and Swedish students are often in advantage already being a part of the system for many years. By following five immigrant boys in grade 6 during ten ensemble lessons, one concert and individual interviews with the boys as well as with their teacher, this study aims to investigate how ensemble playing can function as a social tool and promote interaction as well as integration. The results in this study show that ensemble playing in fact can function as a social tool. The boys developed abilities in playing an instrument as well as cooperating and analyzing by using the social tool of ensemble playing. The results even show that ensemble playing can promote interaction as well as integration. Above everything was the concert where the boys acted in front of their classmates and were treated with great respect and acceptance.

We propose a new ensemble algorithm: the meta-boosting algorithm. This algorithm enables the original Adaboost algorithm to improve the decisions made by different WeakLearners utilizing the meta-learning approach. Better accuracy results are achieved since this algorithm reduces both bias and variance. However, higher accuracy also brings higher computational complexity, especially on big data. We then propose the parallelized meta-boosting algorithm: Parallelized-Meta-Learning (PML) using the MapReduce programming paradigm on Hadoop. The experimental results on the Amazon EC2 cloud computing infrastructure show that PML reduces the computation complexity enormously while retaining lower error rates than the results on a single computer. As we know MapReduce has its inherent weakness that it cannot directly support iterations in an algorithm, our approach is a win-win method, since it not only overcomes this weakness, but also secures good accuracy performance. The comparison between this approach and a contemporary algorithm AdaBoost.PL is also performed.

A pivotal moment in machine learning research was the creation of an important new research area, known as Ensemble Learning. In this work, we argue that ensembles are a very general concept, and though they have been widely used, they can be applied in more situations than they have been to date. Rather than using them only to combine the output of an algorithm, we can apply them to decisions made inside the algorithm itself, during the learning step. We call this approach Inner Ensembles. The motivation to develop Inner Ensembles was the opportunity to produce models with the similar advantages as regular ensembles, accuracy and stability for example, plus additional advantages such as comprehensibility, simplicity, rapid classification and small memory footprint. The main contribution of this work is to demonstrate how broadly this idea can be applied, and highlight its potential impact on all types of algorithms. To support our claim, we first provide a general guideline for applying Inner Ensembles to different algorithms. Then, using this framework, we apply them to two categories of learning methods: supervised and un-supervised. For the former we chose Bayesian network, and for the latter K-Means clustering. Our results show that 1) the overall performance of Inner Ensembles is significantly better than the original methods, and 2) Inner Ensembles provide similar performance improvements as regular ensembles.

Many modern entry guidance systems depend on predictions of atmospheric parameters, notably atmospheric density, in order to guide the entry vehicle to some desired final state. However, in highly dynamic atmospheric environments such as the Martian atmosphere, the density may vary by as much as 200% from predicted pre-entry trends. This high level of atmospheric density uncertainty can cause significant complications for entry guidance processes and may in extreme scenarios cause complete failure of the entry. In the face of this uncertainty, mission designers are compelled to apply large trajectory and design safety margins which typically drive the system design towards less efficient solutions with smaller delivered payloads. The margins necessary to combat the high levels of atmospheric uncertainty may even preclude scientifically interesting destinations or architecturally useful mission modes such as aerocapture. Aerocapture is a method for inserting a spacecraft into an orbit about a planetary body with an atmosphere without the need for significant propulsive maneuvers. This can reduce the required propellant and propulsion hardware for a given mission which lowers mission costs and increases the available payload fraction. However, large density dispersions have a particularly acute effect on aerocapture trajectories due to the interaction of the high required speeds and relatively low densities encountered at aerocapture altitudes. Therefore, while the potential system level benefits of aerocapture are great, so too are the risks associated with this mission mode in highly uncertain atmospheric environments such as Mars. Contemporary entry guidance systems utilize static atmospheric density models for trajectory prediction and control. These static models are unable to alter the fundamental nature of the underlying state equations which are used to predict atmospheric density. This limits both the fidelity and adaptive freedom of these models and forces the guidance system to retroactively correct for the density prediction errors after those errors have already impacted the trajectory. A new class of dynamic density estimator called a Plastic Ensemble Neural System (PENS) is introduced which is able to generate high fidelity, adaptable density forecast models by altering the underlying atmospheric state equations to better agree with observed atmospheric trends. A new construct called an ensemble echo is also introduced which creates an associative learning architecture, permitting PENS to evolve with increasing atmospheric exposure. The PENS estimator is applied to a numerical guidance system and the performance of the composite system is investigated with over 144,000 guided trajectory simulations. The results demonstrate that the PENS algorithm achieves significant reductions in both the required post-aerocapture performance, and the aerocapture failure rates relative to historical density estimators.

In this dissertation, the problem of learning from highly imbalanced data is studied. Imbalance data learning is of great importance and challenge in many real applications. Dealing with a minority class normally needs new concepts, observations and solutions in order to fully understand the underlying complicated models. We try to systematically review and solve this special learning task in this dissertation.We propose a new ensemble learning framework—Diversified Ensemble Classifiers for Imbal-anced Data Learning (DECIDL), based on the advantages of existing ensemble imbalanced learning strategies. Our framework combines three learning techniques: a) ensemble learning, b) artificial example generation, and c) diversity construction by reversely data re-labeling. As a meta-learner, DECIDL utilizes general supervised learning algorithms as base learners to build an ensemble committee. We create a standard benchmark data pool, which contains 30 highly skewed sets with diverse characteristics from different domains, in order to facilitate future research on imbalance data learning. We use this benchmark pool to evaluate and compare our DECIDL framework with several ensemble learning methods, namely under-bagging, over-bagging, SMOTE-bagging, and AdaBoost. Extensive experiments suggest that our DECIDL framework is comparable with other methods. The data sets, experiments and results provide a valuable knowledge base for future research on imbalance learning. We develop a simple but effective artificial example generation method for data balancing. Two new methods DBEG-ensemble and DECIDL-DBEG are then designed to improve the power of imbalance learning. Experiments show that these two methods are comparable to the state-of-the-art methods, e.g., GSVM-RU and SMOTE-bagging. Furthermore, we investigate learning on imbalanced data from a new angle—active learning. By combining active learning with the DECIDL framework, we show that the newly designed Active-DECIDL method is very effective for imbalance learning, suggesting the DECIDL framework is very robust and flexible.Lastly, we apply the proposed learning methods to a real-world bioinformatics problem—protein methylation prediction. Extensive computational results show that the DECIDL method does perform very well for the imbalanced data mining task. Importantly, the experimental results have confirmed our new contributions on this particular data learning problem.

TEMPS EN TEMPS (times in time): Music for voice and instruments in a multi-track recording environment, by Marc Beaulieu, is a work meant to be experienced on many levels of perception. This analysis attempts to present the work at its most important (relevant) levels. / This work is written for a multi-track recording studio. The first section of this thesis describes the expanded possibilities of compositional procedure, orchestration and vocal/linguistic construction inherent in this particular medium. / The concept of the work is deeply rooted in the sociological thesis expounded in Alvin Toffler's "The Third Wave". These sociological 'undertones' and their bearing on the background structure of the work are examined in the following section of the thesis. / The subsequent sections of the thesis introduce the perceptual and conceptual aspects of the overall musical language, and discuss essential characteristics of the harmonic, rhythmic and linguistic fabric of the work as well as special applications of studio recording techniques such as digital sound processing, sampling and mixing. This leads to a discussion of formal structure based on three (3) conceptual waves co-existing and interacting in time.

As more and more remotely sensed data becomes available it is becoming increasingly harder to analyse it with the more traditional labour intensive, manual methods. The commonly used techniques, that involve expert evaluation, are widely acknowledged as providing inconsistent results, at best. We need more general techniques that can adapt to a given situation and that incorporate the strengths of the traditional methods, human operators and new technologies. The difficulty in interpreting remotely sensed data is that often only a small amount of data is available for classification. It can be noisy, incomplete or contain irrelevant information. Given that the training data may be limited we demonstrate a variety of techniques for highlighting information in the available data and how to select the most relevant information for a given classification task. We show that more consistent results between the training data and an entire image can be obtained, and how misclassification errors can be reduced. Specifically, a new technique for attribute selection in neural networks is demonstrated. Machine learning techniques, in particular, provide us with a means of automating classification using training data from a variety of data sources, including remotely sensed data and expert knowledge. A classification framework is presented in this thesis that can be used with any classifier and any available data. While this was developed in the context of vegetation mapping from remotely sensed data using machine learning classifiers, it is a general technique that can be applied to any domain. The emphasis of the applicability for this framework being domains that have inadequate training data available.

Accurate knowledge of water content in seasonal snow can be helpful for water resource management. In this study, a distributed temperature index snow model based on temperature and precipitation as forcing data, is used to estimate snow storage in the Jollie catchment approximately 20km east of the main divide of the central Southern Alps, New Zealand. The main objective is to apply a frequently used assimilation method, the ensemble Kalman square root filter, to assimilate remotely sensed snow covered area into the model and evaluate the impacts of this approach on simulations of snow water equivalent. A 250m resolution remotely sensed data from Moderate Resolution Imaging Spectroradiometer (MODIS), specifically tuned to the study location was used. Temperature and precipitation were given on a 0.055 latitude/longitude grid. Precipitation was perturbed as input into the model, generating 100 ensemble members, which represented model error. Only observations of snow covered area that had less that 25% cloud cover classification were used in the assimilation precess. The error in the snow covered area observations was assumed to be 0.1 and grow linearly with cloud cover fraction up to 1 for a totally cloud covered pixel. As the model was not calibrated, two withholding experiments were conducted, in which observations withheld from the assimilation process were compared to the results. Two model states were updated in the assimilation, the total snow accumulation state variable and the total snow melt state variable. The results of this study indicate that the model underestimates snow storage at the end of winter and/or does not detect snow fall events during the ablation period. The assimilation method only affected simulated snow covered area and snow storage during the ablation period. That corresponded to higher correlation between modelled snow cover area and the updated state variables. Withholding experiments show good agreement between observations and simulated snow covered area. This study successfully applied the ensemble Kalman square root filter and showed its applicability for New Zealand conditions.