Series data, sequences of measured values, are ubiquitous. Whenever observations are made along a path in space or time, a data sequence results. To comprehend nature and shape it to our will, or to make informed decisions based on what we know, we need methods to make sense of such data. Of particular interest are probabilistic descriptions, which enable us to represent uncertainty and random variation inherent to the world around us. This thesis presents and expands upon some tools for creating probabilistic models of sequences, with an eye towards applications involving speech and language. Modelling speech and language is not only of use for creating listening, reading, talking, and writing machines---for instance allowing human-friendly interfaces to future computational intelligences and smart devices of today---but probabilistic models may also ultimately tell us something about ourselves and the world we occupy. The central theme of the thesis is the creation of new or improved models more appropriate for our intended applications, by weakening limiting and questionable assumptions made by standard modelling techniques. One contribution of this thesis examines causal-state splitting reconstruction (CSSR), an algorithm for learning discrete-valued sequence models whose states are minimal sufficient statistics for prediction. Unlike many traditional techniques, CSSR does not require the number of process states to be specified a priori, but builds a pattern vocabulary from data alone, making it applicable for language acquisition and the identification of stochastic grammars. A paper in the thesis shows that CSSR handles noise and errors expected in natural data poorly, but that the learner can be extended in a simple manner to yield more robust and stable results also in the presence of corruptions. Even when the complexities of language are put aside, challenges remain. The seemingly simple task of accurately describing human speech signals, so that natural synthetic speech can be generated, has proved difficult, as humans are highly attuned to what speech should sound like. Two papers in the thesis therefore study nonparametric techniques suitable for improved acoustic modelling of speech for synthesis applications. Each of the two papers targets a known-incorrect assumption of established methods, based on the hypothesis that nonparametric techniques can better represent and recreate essential characteristics of natural speech. In the first paper of the pair, Gaussian process dynamical models (GPDMs), nonlinear, continuous state-space dynamical models based on Gaussian processes, are shown to better replicate voiced speech, without traditional dynamical features or assumptions that cepstral parameters follow linear autoregressive processes. Additional dimensions of the state-space are able to represent other salient signal aspects such as prosodic variation. The second paper, meanwhile, introduces KDE-HMMs, asymptotically-consistent Markov models for continuous-valued data based on kernel density estimation, that additionally have been extended with a fixed-cardinality discrete hidden state. This construction is shown to provide improved probabilistic descriptions of nonlinear time series, compared to reference models from different paradigms. The hidden state can be used to control process output, making KDE-HMMs compelling as a probabilistic alternative to hybrid speech-synthesis approaches. A final paper of the thesis discusses how models can be improved even when one is restricted to a fundamentally imperfect model class. Minimum entropy rate simplification (MERS), an information-theoretic scheme for postprocessing models for generative applications involving both speech and text, is introduced. MERS reduces the entropy rate of a model while remaining as close as possible to the starting model. This is shown to produce simplified models that concentrate on the most common and characteristic behaviours, and provides a continuum of simplifications between the original model and zero-entropy, completely predictable output. As the tails of fitted distributions may be inflated by noise or empirical variability that a model has failed to capture, MERS's ability to concentrate on high-probability output is also demonstrated to be useful for denoising models trained on disturbed data. / <p>QC 20131128</p> / ACORNS: Acquisition of Communication and Recognition Skills / LISTA – The Listening Talker

Les stratégies de contrôle d’écoulement, telles que le soufflage / aspiration, ont prouvé leur efficacité à modifier les caractéristiques d’écoulement à des fins diverses en cas de configurations usuellement simples. Pour étendre cette approche sur des cas industriels, la simulation de dispositifs à échelle réelle et l’optimisation des paramètres de contrôle s’avèrent nécessaires. L’objectif de cette thèse est de mettre en place une procédure d’optimisation pour résoudre cette catégorie de problèmes. Dans cette perspective, l’organisation de la thèse est divisé en trois parties. Tout d’abord, le développement et la validation d’un solveur d’écoulement turbulent compressible instationnaire, résolvant les équations de Navier-Stokes moyennées (RANS) dans le cadre d’une discrétisation mixte de type éléments finis / volumes finis (MEV) sont présentés. Une attention particulière est portée sur la mise en œuvre de modèles numériques de jet synthétique à l’aide de simulations sur une plaque plane. Le deuxième axe de la thèse décrit et valide la mise en œuvre d’une méthode d’optimisation globale basée sur un modèle réduit du type processus gaussien (GP), incluant une approche de filtrage d’erreurs numériques liées aux observations. Cette méthode EGO (Efficient Global Optimization), est validée sur des cas analytiques bruités 1D et 2D. Pour finir, l’optimisation de paramètres de contrôle de jet synthétique sur deux cas test pertinents pour les industriels : un profil d’aile NACA0015, avec objectif de maximiser la portance moyenne et une marche descendante avec objectif de minimiser la longueur de recirculation moyenne. / Active flow control strategies, such as oscillatory blowing / suction, have proved their efficiency to modify flow characteristics for various purposes (e.g. skin friction reduction, separation delay, etc.) in case of rather simple configurations. To extend this approach to industrial cases, the simulation of a large number of devices at real scale and the optimization of parameters are required. The objective of this thesis is to set up an optimization procedure to solve this category of problems. In this perspective, the organization of the thesis is split into three main parts. First, the development and validation of an unsteady compressible turbulent flow solver using the Reynolds-Averaged Navier-Stokes (RANS) using a Mixed finite-Element/finite-Volume (MEV) framework is described. A particular attention is drawn on synthetic jet numerical model implementation by comparing different models in the context of a simulation over a flat plate. The second axis of the thesis describes and validates the implementation of a Gaussian Process surrogate model based global optimization method including an approach to account for some numerical errors during the optimization. This EGO (Efficient Global Optimization) method, is validated on noisy 1D and 2D analytical test cases. Finally, the optimization of two industrial relevant test cases using a synthetic jet actuator are considered: a turbulent flow over a NACA0015 for which the time-averaged lift is regarded as the control criterion to be maximized, and an incompressible turbulent flow over a Backward Facing Step for which the time-averaged recirculation length is minimized.

Human activities have increased the concentration of CO2 into the atmosphere, thus it has caused global warming. Construction equipment are semi-stationary machines and spend at least 30% of its life time during idling. The majority of the construction equipment is diesel powered and emits toxic emission into the environment. In this work, the idling will be investigated through adopting several statistical regressions models to quantify the fuel consumption of construction equipment during idling. The regression models which are studied in this work: Multivariate Linear Regression (ML-R), Support Vector Machine Regression (SVM-R), Gaussian Process regression (GP-R), Artificial Neural Network (ANN), Partial Least Square Regression (PLS-R) and Principal Components Regression (PC-R). Findings show that pre-processing has a significant impact on the goodness of the prediction of the explanatory data analysis in this field. Moreover, through mean centering and application of the max-min scaling feature, the accuracy of models increased remarkably. ANN and GP-R had the highest accuracy (99%), PLS-R was the third accurate model (98% accuracy), ML-R was the fourth-best model (97% accuracy), SVM-R was the fifth-best (73% accuracy) and the lowest accuracy was recorded for PC-R (83% accuracy). The second part of this project estimated the CO2 emission based on the fuel used and by adopting the NONROAD2008 model.  Keywords:

<div><div><div><p>The process of acquiring the large-scale complex systems is usually characterized with cost and schedule overruns. To investigate the causes of this problem, we may view the acquisition of a complex system in several different time scales. At finer time scales, one may study different stages of the acquisition process from the intricate details of the entire systems engineering process to communication between design teams to how individual designers solve problems. At the largest time scale one may consider the acquisition process as series of actions which are, request for bids, bidding and auctioning, contracting, and finally building and deploying the system, without resolving the fine details that occur within each step. In this work, we study the acquisition processes in multiple scales. First, we develop a game-theoretic model for engineering of the systems in the building and deploying stage. We model the interactions among the systems and subsystem engineers as a principal-agent problem. We develop a one-shot shallow systems engineering process and obtain the optimum transfer functions that best incentivize the subsystem engineers to maximize the expected system-level utility. The core of the principal-agent model is the quality function which maps the effort of the agent to the performance (quality) of the system. Therefore, we build the stochastic quality function by modeling the design process as a sequential decision-making problem. Second, we develop and evaluate a model of the acquisition process that accounts for the strategic behavior of different parties. We cast our model in terms of government-funded projects and assume the following steps. First, the government publishes a request for bids. Then, private firms offer their proposals in a bidding process and the winner bidder enters in a con- tract with the government. The contract describes the system requirements and the corresponding monetary transfers for meeting them. The winner firm devotes effort to deliver a system that fulfills the requirements. This can be assumed as a game that the government plays with the bidder firms. We study how different parameters in the acquisition procedure affect the bidders’ behaviors and therefore, the utility of the government. Using reinforcement learning, we seek to learn the optimal policies of involved actors in this game. In particular, we study how the requirements, contract types such as cost-plus and incentive-based contracts, number of bidders, problem complexity, etc., affect the acquisition procedure. Furthermore, we study the bidding strategy of the private firms and how the contract types affect their strategic behavior.</p></div></div></div>

<p>  </p> <p>With the recent advancement of computation and imaging technology, Image-based computational fluid dynamics (ICFD) has emerged as a great non-invasive capability to study biomedical flows. These modern technologies increase the potential of computation-aided diagnostics and therapeutics in a patient-specific environment. I studied three components of this image-based computational fluid dynamics process in this work.</p> <p>To ensure accurate medical assessment, realistic computational analysis is needed, for which patient-specific image segmentation of the diseased vessel is of paramount importance. In this work, image segmentation of several human arteries, veins, capillaries, and organs was conducted to use them for further hemodynamic simulations. To accomplish these, several open-source and commercial software packages were implemented. </p> <p>This study incorporates a new computational platform, called <em>InVascular</em>, to quantify the 4D velocity field in image-based pulsatile flows using the Volumetric Lattice Boltzmann Method (VLBM). We also conducted several parametric studies on an idealized case of a 3-D pipe with the dimensions of a human renal artery. We investigated the relationship between stenosis severity and Resistive index (RI). We also explored how pulsatile parameters like heart rate or pulsatile pressure gradient affect RI.</p> <p>As the process of ICFD analysis is based on imaging and other hemodynamic data, it is often time-consuming due to the extensive data processing time. For clinicians to make fast medical decisions regarding their patients, we need rapid and accurate ICFD results. To achieve that, we also developed surrogate models to show the potential of supervised machine learning methods in constructing efficient and precise surrogate models for Hagen-Poiseuille and Womersley flows.</p>

<p>A wide range of optoelectronic applications demand semiconductors optimized for purpose.</p> <p>My research focused on data-driven identification of ABX3 Halide perovskite compositions for optimum photovoltaic absorption in solar cells.</p> <p>I trained machine learning models on previously reported datasets of halide perovskite band gaps based on first principles computations performed at different fidelities.</p> <p>Using these, I identified mixtures of candidate constituents at the A, B or X sites of the perovskite supercell which leveraged how mixed perovskite band gaps deviate from the linear interpolations predicted by Vegard's law of mixing to obtain a selection of stable perovskites with band gaps in the ideal range of 1 to 2 eV for visible light spectrum absorption.</p> <p>These models predict the perovskite band gap using the composition and inherent elemental properties as descriptors.</p> <p>This enables accurate, high fidelity prediction and screening of the much larger chemical space from which the data samples were drawn.</p> <p><br></p> <p>I utilized a recently published density functional theory (DFT) dataset of more than 1300 perovskite band gaps from four different levels of theory, added to an experimental perovskite band gap dataset of \textasciitilde{}100 points, to train random forest regression (RFR), Gaussian process regression (GPR), and Sure Independence Screening and Sparsifying Operator (SISSO) regression models, with data fidelity added as one-hot encoded features.</p> <p>I found that RFR yields the best model with a band gap root mean square error of 0.12 eV on the total dataset and 0.15 eV on the experimental points.</p> <p>SISSO provided compound features and functions for direct prediction of band gap, but errors were larger than from RFR and GPR.</p> <p>Additional insights gained from Pearson correlation and Shapley additive explanation (SHAP) analysis of learned descriptors suggest the RFR models performed best because of (a) their focus on identifying and capturing relevant feature interactions and (b) their flexibility to represent nonlinear relationships between such interactions and the band gap.</p> <p>The best model was deployed for predicting experimental band gap of 37785 hypothetical compounds.</p> <p>Based on this, we identified 1251 stable compounds with band gap predicted to be between 1 and 2 eV at experimental accuracy, successfully narrowing the candidates to about 3% of the screened compositions.</p>

<p>This work focuses on the collection and analysis of Lithium-ion battery operational and temperature data during nail penetration testing through two different experimental approaches. Raman spectroscopy, machine learning, and internal temperature sensors are used to collect and analyze data to further investigate the effects on cell operation during and after nail penetrations, and the feasibility of using this data to predict future performance.</p> <p><br></p> <p>The first section of this work analyzes the effects on continued operation of a small Lithium-ion prismatic cell after nail penetration. Raman spectroscopy is used to examine the effects on the anode and cathode materials of cells that are cycled for different amounts of time after a nail puncture. Incremental capacity analysis is then used to corroborate the findings from the Raman analysis. The study finds that the operational capacity and lifetime of cells is greatly reduced due to the accelerated degradation caused by loss of material, uneven current distribution, and exposure to atmosphere. This leads into the study of using the magnitude and corresponding voltage of incremental capacity peaks after nail puncture to forecast the operation of damaged cells. A Gaussian process regression is used to predict discharge capacity of different cells that experience the same type of nail puncture. The results from this study show that the method is capable of making accurate predictions of cell discharge capacity even with the higher rate of variance in operation after nail puncture, showing the method of prediction has the potential to be implemented in devices such as battery management systems.</p> <p><br></p> <p>The second section of this work proposes a method of inserting temperature sensors into commercially-available cylindrical cells to directly obtain internal temperature readings. Characterization tests are used to determine the effect on the operability of the modified cells after the sensors are inserted, and lifetime cycle testing is implemented to determine the long-term effects on cell performance. The results show the sensor insertion causes a small reduction in operational performance, and lifetime cycle testing shows the cells can operate near their optimal output for approximately 100-150 cycles. Modified cells are then used to monitor internal temperatures during nail penetration tests and how the amount of aging affects the temperature response. The results show that more aging in a cell causes higher temperatures during nail puncture, as well as a larger difference between internal and external temperatures, due mostly to the larger contribution of Joule heating caused by increased internal resistance.</p>

Cette thèse cherche à examiner les conditions optimales dans lesquelles les surfaces cornéennes antérieures peuvent être efficacement pré-traitées, classifiées et prédites en utilisant des techniques de modélisation géométriques (MG) et d’apprentissage automatiques (AU). La première étude (Chapitre 2) examine les conditions dans lesquelles la modélisation géométrique peut être utilisée pour réduire la dimensionnalité des données utilisées dans un projet d’apprentissage automatique. Quatre modèles géométriques ont été testés pour leur précision et leur rapidité de traitement : deux modèles polynomiaux (P) – polynômes de Zernike (PZ) et harmoniques sphériques (PHS) – et deux modèles de fonctions rationnelles (R) : fonctions rationnelles de Zernike (RZ) et fonctions rationnelles d’harmoniques sphériques (RSH). Il est connu que les modèles PHS et RZ sont plus précis que les modèles PZ pour un même nombre de coefficients (J), mais on ignore si les modèles PHS performent mieux que les modèles RZ, et si, de manière plus générale, les modèles SH sont plus précis que les modèles R, ou l’inverse. Et prenant en compte leur temps de traitement, est-ce que les modèles les plus précis demeurent les plus avantageux? Considérant des valeurs de J (nombre de coefficients du modèle) relativement basses pour respecter les contraintes de dimensionnalité propres aux taches d’apprentissage automatique, nous avons établi que les modèles HS (PHS et RHS) étaient tous deux plus précis que les modèles Z correspondants (PZ et RR), et que l’avantage de précision conféré par les modèles HS était plus important que celui octroyé par les modèles R. Par ailleurs, les courbes de temps de traitement en fonction de J démontrent qu’alors que les modèles P sont traités en temps quasi-linéaires, les modèles R le sont en temps polynomiaux. Ainsi, le modèle SHR est le plus précis, mais aussi le plus lent (un problème qui peut en partie être remédié en appliquant une procédure de pré-optimisation). Le modèle ZP était de loin le plus rapide, et il demeure une option intéressante pour le développement de projets. SHP constitue le meilleur compromis entre la précision et la rapidité. La classification des cornées selon des paramètres cliniques a une longue tradition, mais la visualisation des effets moyens de ces paramètres sur la forme de la cornée par des cartes topographiques est plus récente. Dans la seconde étude (Chapitre 3), nous avons construit un atlas de cartes d’élévations moyennes pour différentes variables cliniques qui pourrait s’avérer utile pour l’évaluation et l’interprétation des données d’entrée (bases de données) et de sortie (prédictions, clusters, etc.) dans des tâches d’apprentissage automatique, entre autres. Une base de données constituée de plusieurs milliers de surfaces cornéennes antérieures normales enregistrées sous forme de matrices d’élévation de 101 by 101 points a d’abord été traitée par modélisation géométrique pour réduire sa dimensionnalité à un nombre de coefficients optimal dans une optique d’apprentissage automatique. Les surfaces ainsi modélisées ont été regroupées en fonction de variables cliniques de forme, de réfraction et de démographie. Puis, pour chaque groupe de chaque variable clinique, une surface moyenne a été calculée et représentée sous forme de carte d’élévations faisant référence à sa SMA (sphère la mieux ajustée). Après avoir validé la conformité de la base de donnée avec la littérature par des tests statistiques (ANOVA), l’atlas a été vérifié cliniquement en examinant si les transformations de formes cornéennes présentées dans les cartes pour chaque variable étaient conformes à la littérature. C’était le cas. Les applications possibles d’un tel atlas sont discutées. La troisième étude (Chapitre 4) traite de la classification non-supervisée (clustering) de surfaces cornéennes antérieures normales. Le clustering cornéen un domaine récent en ophtalmologie. La plupart des études font appel aux techniques d’extraction des caractéristiques pour réduire la dimensionnalité de la base de données cornéennes. Le but est généralement d’automatiser le processus de diagnostique cornéen, en particulier en ce qui a trait à la distinction entre les cornées normales et les cornées irrégulières (kératocones, Fuch, etc.), et dans certains cas, de distinguer différentes sous-classes de cornées irrégulières. L’étude de clustering proposée ici se concentre plutôt sur les cornées normales afin de mettre en relief leurs regroupements naturels. Elle a recours à la modélisation géométrique pour réduire la dimensionnalité de la base de données, utilisant des polynômes de Zernike, connus pour leur interprétativité transparente (chaque terme polynomial est associé à une caractéristique cornéenne particulière) et leur bonne précision pour les cornées normales. Des méthodes de différents types ont été testées lors de prétests (méthodes de clustering dur (hard) ou souple (soft), linéaires or non-linéaires. Ces méthodes ont été testées sur des surfaces modélisées naturelles (non-normalisées) ou normalisées avec ou sans traitement d’extraction de traits, à l’aide de différents outils d’évaluation (scores de séparabilité et d’homogénéité, représentations par cluster des coefficients de modélisation et des surfaces modélisées, comparaisons statistiques des clusters sur différents paramètres cliniques). Les résultats obtenus par la meilleure méthode identifiée, k-means sans extraction de traits, montrent que les clusters produits à partir de surfaces cornéennes naturelles se distinguent essentiellement en fonction de la courbure de la cornée, alors que ceux produits à partir de surfaces normalisées se distinguent en fonction de l’axe cornéen. La dernière étude présentée dans cette thèse (Chapitre 5) explore différentes techniques d’apprentissage automatique pour prédire la forme de la cornée à partir de données cliniques. La base de données cornéennes a d’abord été traitée par modélisation géométrique (polynômes de Zernike) pour réduire sa dimensionnalité à de courts vecteurs de 12 à 20 coefficients, une fourchette de valeurs potentiellement optimales pour effectuer de bonnes prédictions selon des prétests. Différentes méthodes de régression non-linéaires, tirées de la bibliothèque scikit-learn, ont été testées, incluant gradient boosting, Gaussian process, kernel ridge, random forest, k-nearest neighbors, bagging, et multi-layer perceptron. Les prédicteurs proviennent des variables cliniques disponibles dans la base de données, incluant des variables géométriques (diamètre horizontal de la cornée, profondeur de la chambre cornéenne, côté de l’œil), des variables de réfraction (cylindre, sphère et axe) et des variables démographiques (âge, genre). Un test de régression a été effectué pour chaque modèle de régression, défini comme la sélection d’une des 256 combinaisons possibles de variables cliniques (les prédicteurs), d’une méthode de régression, et d’un vecteur de coefficients de Zernike d’une certaine taille (entre 12 et 20 coefficients, les cibles). Tous les modèles de régression testés ont été évalués à l’aide de score de RMSE établissant la distance entre les surfaces cornéennes prédites (les prédictions) et vraies (les topographies corn¬éennes brutes). Les meilleurs d’entre eux ont été validés sur l’ensemble de données randomisé 20 fois pour déterminer avec plus de précision lequel d’entre eux est le plus performant. Il s’agit de gradient boosting utilisant toutes les variables cliniques comme prédicteurs et 16 coefficients de Zernike comme cibles. Les prédictions de ce modèle ont été évaluées qualitativement à l’aide d’un atlas de cartes d’élévations moyennes élaborées à partir des variables cliniques ayant servi de prédicteurs, qui permet de visualiser les transformations moyennes d’en groupe à l’autre pour chaque variables. Cet atlas a permis d’établir que les cornées prédites moyennes sont remarquablement similaires aux vraies cornées moyennes pour toutes les variables cliniques à l’étude. / This thesis aims to investigate the best conditions in which the anterior corneal surface of normal corneas can be preprocessed, classified and predicted using geometric modeling (GM) and machine learning (ML) techniques. The focus is on the anterior corneal surface, which is the main responsible of the refractive power of the cornea. Dealing with preprocessing, the first study (Chapter 2) examines the conditions in which GM can best be applied to reduce the dimensionality of a dataset of corneal surfaces to be used in ML projects. Four types of geometric models of corneal shape were tested regarding their accuracy and processing time: two polynomial (P) models – Zernike polynomial (ZP) and spherical harmonic polynomial (SHP) models – and two corresponding rational function (R) models – Zernike rational function (ZR) and spherical harmonic rational function (SHR) models. SHP and ZR are both known to be more accurate than ZP as corneal shape models for the same number of coefficients, but which type of model is the most accurate between SHP and ZR? And is an SHR model, which is both an SH model and an R model, even more accurate? Also, does modeling accuracy comes at the cost of the processing time, an important issue for testing large datasets as required in ML projects? Focusing on low J values (number of model coefficients) to address these issues in consideration of dimensionality constraints that apply in ML tasks, it was found, based on a number of evaluation tools, that SH models were both more accurate than their Z counterparts, that R models were both more accurate than their P counterparts and that the SH advantage was more important than the R advantage. Processing time curves as a function of J showed that P models were processed in quasilinear time, R models in polynomial time, and that Z models were fastest than SH models. Therefore, while SHR was the most accurate geometric model, it was the slowest (a problem that can partly be remedied by applying a preoptimization procedure). ZP was the fastest model, and with normal corneas, it remains an interesting option for testing and development, especially for clustering tasks due to its transparent interpretability. The best compromise between accuracy and speed for ML preprocessing is SHP. The classification of corneal shapes with clinical parameters has a long tradition, but the visualization of their effects on the corneal shape with group maps (average elevation maps, standard deviation maps, average difference maps, etc.) is relatively recent. In the second study (Chapter 3), we constructed an atlas of average elevation maps for different clinical variables (including geometric, refraction and demographic variables) that can be instrumental in the evaluation of ML task inputs (datasets) and outputs (predictions, clusters, etc.). A large dataset of normal adult anterior corneal surface topographies recorded in the form of 101×101 elevation matrices was first preprocessed by geometric modeling to reduce the dimensionality of the dataset to a small number of Zernike coefficients found to be optimal for ML tasks. The modeled corneal surfaces of the dataset were then grouped in accordance with the clinical variables available in the dataset transformed into categorical variables. An average elevation map was constructed for each group of corneal surfaces of each clinical variable in their natural (non-normalized) state and in their normalized state by averaging their modeling coefficients to get an average surface and by representing this average surface in reference to the best-fit sphere in a topographic elevation map. To validate the atlas thus constructed in both its natural and normalized modalities, ANOVA tests were conducted for each clinical variable of the dataset to verify their statistical consistency with the literature before verifying whether the corneal shape transformations displayed in the maps were themselves visually consistent. This was the case. The possible uses of such an atlas are discussed. The third study (Chapter 4) is concerned with the use of a dataset of geometrically modeled corneal surfaces in an ML task of clustering. The unsupervised classification of corneal surfaces is recent in ophthalmology. Most of the few existing studies on corneal clustering resort to feature extraction (as opposed to geometric modeling) to achieve the dimensionality reduction of the dataset. The goal is usually to automate the process of corneal diagnosis, for instance by distinguishing irregular corneal surfaces (keratoconus, Fuch, etc.) from normal surfaces and, in some cases, by classifying irregular surfaces into subtypes. Complementary to these corneal clustering studies, the proposed study resorts mainly to geometric modeling to achieve dimensionality reduction and focuses on normal adult corneas in an attempt to identify their natural groupings, possibly in combination with feature extraction methods. Geometric modeling was based on Zernike polynomials, known for their interpretative transparency and sufficiently accurate for normal corneas. Different types of clustering methods were evaluated in pretests to identify the most effective at producing neatly delimitated clusters that are clearly interpretable. Their evaluation was based on clustering scores (to identify the best number of clusters), polar charts and scatter plots (to visualize the modeling coefficients involved in each cluster), average elevation maps and average profile cuts (to visualize the average corneal surface of each cluster), and statistical cluster comparisons on different clinical parameters (to validate the findings in reference to the clinical literature). K-means, applied to geometrically modeled surfaces without feature extraction, produced the best clusters, both for natural and normalized surfaces. While the clusters produced with natural corneal surfaces were based on the corneal curvature, those produced with normalized surfaces were based on the corneal axis. In each case, the best number of clusters was four. The importance of curvature and axis as grouping criteria in corneal data distribution is discussed. The fourth study presented in this thesis (Chapter 5) explores the ML paradigm to verify whether accurate predictions of normal corneal shapes can be made from clinical data, and how. The database of normal adult corneal surfaces was first preprocessed by geometric modeling to reduce its dimensionality into short vectors of 12 to 20 Zernike coefficients, found to be in the range of appropriate numbers to achieve optimal predictions. The nonlinear regression methods examined from the scikit-learn library were gradient boosting, Gaussian process, kernel ridge, random forest, k-nearest neighbors, bagging, and multilayer perceptron. The predictors were based on the clinical variables available in the database, including geometric variables (best-fit sphere radius, white-towhite diameter, anterior chamber depth, corneal side), refraction variables (sphere, cylinder, axis) and demographic variables (age, gender). Each possible combination of regression method, set of clinical variables (used as predictors) and number of Zernike coefficients (used as targets) defined a regression model in a prediction test. All the regression models were evaluated based on their mean RMSE score (establishing the distance between the predicted corneal surfaces and the raw topographic true surfaces). The best model identified was further qualitatively assessed based on an atlas of predicted and true average elevation maps by which the predicted surfaces could be visually compared to the true surfaces on each of the clinical variables used as predictors. It was found that the best regression model was gradient boosting using all available clinical variables as predictors and 16 Zernike coefficients as targets. The most explicative predictor was the best-fit sphere radius, followed by the side and refractive variables. The average elevation maps of the true anterior corneal surfaces and the predicted surfaces based on this model were remarkably similar for each clinical variable.

<p>Uncertainty analysis is of great use both for calculating outputs that are more akin to real<br> flight, and for optimization to more robust shapes. However, implementation of uncertainty<br> has been a longstanding challenge in the field of aerodynamics due to the computational cost<br> of simulations. Geometric uncertainty in particular is often left unexplored in favor of uncer-<br> tainties in freestream parameters, turbulence models, or computational error. Therefore, this<br> work proposes a method of geometric uncertainty analysis for aerodynamic shapes that miti-<br> gates the barriers to its feasible computation. The process takes a two- or three-dimensional<br> shape and utilizes a combination of multifidelity meshes and Gaussian process regression<br> (GPR) surrogates in a multifidelity Monte Carlo (MFMC) algorithm. Multifidelity meshes<br> allow for finer sampling with a given budget, making the surrogates more accurate. GPR<br> surrogates are made practical to use by parameterizing major factors in geometric uncer-<br> tainty with only four variables in 2-D and five in 3-D. In both cases, two parameters control<br> the heights of steps that occur on the top and bottom of airfoils where leading and trailing<br> edge devices are attached. Two more parameters control the height and length of waves<br> that can occur in an ideally smooth shape during manufacturing. A fifth parameter controls<br> the depth of span-wise skin buckling waves along a 3-D wing. Parameters are defined to<br> be uniformly distributed with a maximum size of 0.4 mm and 0.15 mm for steps and waves<br> to remain within common manufacturing tolerances. The analysis chain is demonstrated<br> with two test cases. The first, the RAE2822 airfoil, uses transonic freestream parameters<br> set by the ADODG Benchmark Case 2. The results show a mean drag of nearly 10 counts<br> above the deterministic case with fixed lift, and a 2 count increase for a fixed angle of attack<br> version of the case. Each case also has small variations in lift and angle of attack of about<br> 0.5 counts and 0.08◦, respectively. Variances for each of the three tracked outputs show that<br> more variability is possible, and even likely. The ONERA M6 transonic wing, popular due<br> to the extensive experimental data available for computational validation, is the second test<br> case. Variation is found to be less substantial here, with a mean drag increase of 0.5 counts,<br> and a mean lift increase of 0.1 counts. Furthermore, the MFMC algorithm enables accurate<br> results with only a few hours of wall time in addition to GPR training. </p>

The understanding of what motivates a customer to pay more for a product or service has al-ways been a fundamental question in business. To the end of answering this question, revenue management is a business practice that revolves around using analytics to predict consumer behavior and willingness-to-pay. It has been a common practice within the commercial airline and hospitality industries for over 30 years, allowing adopters to reach their service capacity with increased profit margins. In this thesis, we investigated the possibility to apply revenue management to the last mile delivery industry, an industry that provides the service of delivering goods from e-commerce companies to the consumer’s front door. To achieve this objective, a revenue management framework was conceived, detailing the interaction between the customer and a dynamic pricing model. The model itself was a product of a machine learning model, intended to segment the customers and predict the willingness-to-pay of each customer segment. The performance of this model was tested through a quantitative study on synthetic buyers, subject to parameters that influence their willingness-to-pay. It was observed that the model was able to distinguish between different types of customers, yielding a pricing policy that increased profits by 7.5% in comparison to fixed price policies. It was concluded that several factors may impact the customer’s willingness-to-pay within the last mile delivery industry. Amongst these, the convenience that the service provides and the disparity between the price of the product and the price of the service were the most notable. However, the magnitude of considering these parameters was never determined. Finally, em-ploying dynamic pricing has the potential to increase the availability of the service, enabling a wider audience to afford the service. / Vad som motiverar en kund att betala mer för en tjänst eller en produkt har länge varit ett centralt koncept inom affärslivet. Intäktsoptimering är en affärspraxis som strävar efter att besvara den frågan, genom att med analytiska verktyg mäta och förutse betalningsviljan hos kunden. Intäktsoptimering har länge varit framträdande inom flyg- och hotellbranschen, där företag som anammat strategin har möjlighets att öka försäljningsvinsten. I detta examensarbete undersöker vi möjligheten att applicera intäktsoptimering på sista milen industrin, en industri som leverar köpta produkten hem till kunden. För att uppnå detta har vi tagit fram ett ramverk för informationsflöden inom intäktsoptimering som beskriver hur kunder interagerar med en dynamisk prissättningsmodell. Denna prissättningsmodell framställs genom maskininlärning med avsikt att segmentera kundbasen, för att sedan förutse betalningsviljan hos varje kundsegment. Modellens prestanda mättes genom en kvantitativ studie på syntetiska kunder som beskrivs av parametrar som påverkar betalningsviljan. Studien påvisade att modellen kunde skilja på betalningsviljan hos olika kunder och resulterade i en genomsnittlig vinstökning på 7.5% i jämförelse med statiska prissättningsmodeller. Det finns mänga olika faktorer som spelar in på kundens betalningsvilja inom sista milen industrin. Bekvämlighet och skillnader i priset på produkten som levereras och tjänsten att leverera produkten är två anmärkningsvärda faktorer. Hur stor inverkan faktorerna som beskrivs i detta examensarbete, har på betalningsviljan, förblev obesvarat. Slutligen uppmärksammades möjligheten att, med hjälp av dynamisk prissättning, öka tillgängligheten av tjänsten då flera kunder kan ha råd med en prissättning som överväger deras betalningsvilja.