Various improvements which have been made to the vehicle (reduced engine noise, reducedaerodynamic related NVH), have resulted in tire road noise as the dominant source of thevehicle interior noise. Generally, vehicle interior noise has two main sources, 1) travellinglow frequency excitation below 800 Hz from road surface through a structure- borne pathand 2) the high frequency (above 800 Hz) air-borne noise that is caused by air- pumpingnoise caused by tread pattern.The structure-borne waves of the circumference of the tire are generated by excitation atthe contact patch due to the road surface texture and characteristics. These vibrations arethen transferred from the sidewalls of the tire to the rim and then are transmitted throughthe spindle-wheel interface, resulting in high frequency vibration of vehicle body panels andwindows.The focus of this study is to develop several statistical-based models for analyzing the roadsurface and using them to predict the tire-road noise structure-borne component. In order todo this, a new methodology for sensing the road characteristics, such as asperities and roadsurface condition, were developed using virtual sensing and intelligent tire technology. In ad-dition, the spindle forces were used as an indicator to the structure-borne noise of the vehicle.Several data mining and multivariate analysis-based methods were developed to extractfeatures and to develop an empirical model to predict the power of structure-borne noiseunder different operational and road conditions. Finally, multiple data driven models-basedmodels were developed to classify the road types, and conditions and use them for the noisefrequency spectrum prediction. / Doctor of Philosophy / Multiple data driven models were developed in this study to use the vibration of the tirecontact patch as an input to sense some characteristics of road such as asperity, surface type,and the surface condition, and use them to predict the structure-borne noise power. Also,instead of measuring the noise using microphones, forces at wheel spindle were measuredas a metric for the noise power. In other words, a statistical model was developed that bysensing the road, and using the data along with other inputs, one can predict forces at thewheel spindle.

Les modèles génératifs basés sur la vraisemblance sont des éléments fondamentaux pour la modélisation statistique des données structurées. Ils peuvent être utilisés pour synthétiser des échantillons de données réalistes, et la fonction de vraisemblance peut être utilisée pour comparer les modèles et déduire diverses quantités statistiques. Cependant, le défi réside dans le développement de modèles capables de saisir avec précision les schémas statistiques présentés dans la distribution des données. Les modèles existants rencontrent souvent des limitations en termes de flexibilité représentationnelle et d’évolutivité computationnelle en raison du choix de la paramétrisation, freinant ainsi la progression vers cet idéal. Cette thèse présente une exploration systématique des structures appropriées qui peuvent être exploitées pour concevoir des modèles génératifs basés sur la vraisemblance, allant des architectures spécialisées telles que les applications triangulaires et les applications de potentiel convexes aux systèmes dynamiques paramétriques tels que les équations différentielles neuronales qui présentent des contraintes minimales en termes de paramétrisation. Les modèles proposés sont fondés sur des motivations théoriques et sont analysés à travers le prisme du changement de variable associé au processus de génération de données. Cette perspective permet de considérer ces modèles comme des formes distinctes de probability flows, unifiant ainsi des classes apparemment non liées de modèles génératifs basés sur la vraisemblance. De plus, des conceptions algorithmiques pratiques sont introduites pour calculer, approximer ou estimer les quantités nécessaires pour l’apprentissage et l’évaluation. Il est prévu que cette thèse suscite l’intérêt des communautés de modélisation générative et d’apprentissage automatique Bayésien/probabiliste, et qu’elle serve de ressource précieuse et d’inspiration pour les chercheurs et les praticiens du domaine. / Likelihood-based generative models are fundamental building blocks for statistical modeling of structured data. They can be used to synthesize realistic data samples, and the likelihood function can be used for comparing models and inferring various statistical quantities. However, the challenge lies in developing models capable of accurately capturing the statistical patterns presented in the data distribution. Existing models often face limitations in representational flexibility and computational scalability due to the choice of parameterization, impeding progress towards this ideal. This thesis presents a systematic exploration of suitable structures that can be exploited to design likelihood-based generative models, spanning from specialized architectures like triangular maps and convex potential maps to parametric dynamical systems such as neural differential equations that bear minimal parameterization restrictions. The proposed models are rooted in theoretical foundations and analyzed through the lens of the associated change of variable in the data generation process. This perspective allows for viewing these models as distinct forms of probability flows, thereby unifying seemingly unrelated classes of likelihood-based generative models. Moreover, practical algorithmic designs are introduced to compute, approximate, or estimate necessary quantities for training and testing purposes. It is anticipated that this thesis would be of interest to the generative modeling and Bayesian/probabilistic machine learning communities, and will serve as a valuable resource and inspiration for both researchers and practitioners in the field.

<p dir="ltr">This research involves numerous network intrusion techniques through novel applications of graph representation learning and image representation learning. The methods are tested on multiple publicly available network flow datasets.</p>

Dans ce mémoire, nous présentons une étude visant à améliorer les soins aux personnes âgées grâce à la mise en œuvre d'un système de vidéosurveillance intelligent avancé. Ce système est conçu pour exploiter la puissance des algorithmes d’apprentissage profond pour détecter les anomalies de mobilité, avec un accent particulier sur l’identification des quasi-chutes. L’importance d’identifier les quasi-chutes réside dans le fait que les personnes qui subissent de tels événements au cours de leurs activités quotidiennes courent un risque accru de subir des chutes à l’avenir pouvant mener à des blessures graves et une hospitalisation. L’une des principales réalisations de notre étude est le développement d’un auto-encodeur capable de détecter les anomalies de mobilité, en particulier les quasi-chutes, en identifiant des erreurs de reconstruction élevées sur cinq images consécutives. Pour extraire avec précision une structure squelettique de la personne, nous avons utilisé MoveNet et affiné ce modèle sur sept points clés. Par la suite, nous avons utilisé un ensemble complet de 20 caractéristiques, englobant les positions des articulations, les vitesses, les accélérations, les angles et les accélérations angulaires, pour entraîner l’auto-encodeur. Afin d'évaluer l'efficacité de notre modèle, nous avons effectué des tests rigoureux à l'aide de 100 vidéos d'activités quotidiennes simulées enregistrées dans un laboratoire d'appartement, la moitié des vidéos contenant des cas de quasi-chutes. Un autre ensemble de 50 vidéos a été utilisé pour l’entrainement. Les résultats de notre phase de test sont très prometteurs, car ils indiquent que notre modèle est capable de détecter efficacement les quasi-chutes avec une sensibilité, une spécificité et une précision impressionnantes de 90 %. Ces résultats soulignent le potentiel de notre modèle à améliorer considérablement les soins aux personnes âgées dans leur environnement de vie. / In this thesis, we present a comprehensive study aimed at enhancing elderly care through the implementation of an advanced intelligent video surveillance system. This system is designed to leverage the power of deep learning algorithms to detect mobility anomalies, with a specific focus on identifying near-falls. The significance of identifying near-falls lies in the fact that individuals who experience such events during their daily activities are at an increased risk of experiencing falls in the future that can lead to serious injury and hospitalization. A key achievement of our study is the successful development of an autoencoder capable of detecting mobility anomalies, particularly near-falls, by pinpointing high reconstruction errors across five consecutive frames. To precisely extract a person's skeletal structure, we utilized MoveNet and focused on seven key points. Subsequently, we employed a comprehensive set of 20 features, encompassing joint positions, velocities, accelerations, angles, and angular accelerations, to train the model. In order to assess the efficacy of our model, we conducted rigorous testing using 100 videos of simulated daily activities recorded in an apartment laboratory, with half of the videos containing instances of near-falls. Another set of 50 videos was used for training. The results from our testing phase are highly promising, as they indicate that our model is able to effectively detect near-falls with an impressive 90% sensitivity, specificity, and accuracy. These results underscore the potential of our model to significantly enhance elderly care within their living environments.

Methodologies designed to support new product development are receiving increasing interest in recent literature. A significant percentage of new product failure is attributed to a mismatch between designed product features and consumer liking. A variety of methodologies have been proposed and tested for consumer liking or preference prediction, ranging from statistical methodologies e.g. multiple linear regression (MLR) to non-statistical approaches e.g. artificial neural networks (ANN), support vector machines (SVM), and belief rule-based (BRB) systems. BRB has been previously tested for consumer preference prediction and target setting in case studies from the beverages industry. Results have indicated a number of technical and conceptual advantages which BRB holds over the aforementioned alternative approaches. This thesis focuses on presenting further advantages and applications of the BRB methodology for consumer liking prediction. The features and advantages are selected in response to challenges raised by three addressed case studies. The first case study addresses a novel industry for BRB application: the fast moving consumer goods industry, the personal care sector. A series of challenges are tackled. Firstly, stepwise linear regression, principal component analysis and AutoEncoder are tested for predictors’ selection and data reduction. Secondly, an investigation is carried out to analyse the impact of employing complete distributions, instead of averages, for sensory attributes. Moreover, the effect of modelling instrumental measurement error is assessed. The second case study addresses a different product from the personal care sector. A bi-objective prescriptive approach for BRB model structure selection and validation is proposed and tested. Genetic Algorithms and Simulated Annealing are benchmarked against complete enumeration for searching the model structures. A novel criterion based on an adjusted Akaike Information Criterion is designed for identifying the optimal model structure from the Pareto frontier based on two objectives: model complexity and model fit. The third case study introduces yet another novel industry for BRB application: the pastry and confectionary specialties industry. A new prescriptive framework, for rule validation and random training set allocation, is designed and tested. In all case studies, the BRB methodology is compared with the most popular alternative approaches: MLR, ANN, and SVM. The results indicate that BRB outperforms these methodologies both conceptually and in terms of prediction accuracy.

The purpose of this research is to study the detection of temporal changes between two (or more) multimodal images satellites, i.e., between two different imaging modalities acquired by two heterogeneous sensors, giving for the same scene two images encoded differently and depending on the nature of the sensor used for each acquisition. The two (or multiple) multimodal satellite images are acquired and coregistered at two different dates, usually before and after an event. In this study, we propose new models belonging to different categories of multimodal change detection in remote sensing imagery. As a first contribution, we present a new constraint scenario expressed on every pair of pixels existing in the before and after image change. A second contribution of our work is to propose a spatio-temporal textural gradient operator expressed with complementary norms and also a new filtering strategy of the difference map resulting from this operator. Another contribution consists in constructing an observation field from a pair of pixels and to infer a solution maximum a posteriori sense. A fourth contribution is proposed which consists to build a common feature space for the two heterogeneous images. Our fifth contribution lies in the modeling of patterns of change by anomalies and on the analysis of reconstruction errors which we propose to learn a non-supervised model from a training base consisting only of patterns of no-change in order that the built model reconstruct the normal patterns (non-changes) with a small reconstruction error. In the sixth contribution, we propose a pairwise learning architecture based on a pseudosiamese CNN network that takes as input a pair of data instead of a single data and constitutes two partly uncoupled CNN parallel network streams (descriptors) followed by a decision network that includes fusion layers and a loss layer in the sense of the entropy criterion. The proposed models are enough flexible to be used effectively in the monomodal change detection case. / Cette recherche a pour objet l’étude de la détection de changements temporels entre deux (ou plusieurs) images satellitaires multimodales, i.e., avec deux modalités d’imagerie différentes acquises par deux capteurs hétérogènes donnant pour la même scène deux images encodées différemment suivant la nature du capteur utilisé pour chacune des prises de vues. Les deux (ou multiples) images satellitaires multimodales sont prises et co-enregistrées à deux dates différentes, avant et après un événement. Dans le cadre de cette étude, nous proposons des nouveaux modèles de détection de changement en imagerie satellitaire multimodale semi ou non supervisés. Comme première contribution, nous présentons un nouveau scénario de contraintes exprimé sur chaque paire de pixels existant dans l’image avant et après changement. Une deuxième contribution de notre travail consiste à proposer un opérateur de gradient textural spatio-temporel exprimé avec des normes complémentaires ainsi qu’une nouvelle stratégie de dé-bruitage de la carte de différence issue de cet opérateur. Une autre contribution consiste à construire un champ d’observation à partir d’une modélisation par paires de pixels et proposer une solution au sens du maximum a posteriori. Une quatrième contribution est proposée et consiste à construire un espace commun de caractéristiques pour les deux images hétérogènes. Notre cinquième contribution réside dans la modélisation des zones de changement comme étant des anomalies et sur l’analyse des erreurs de reconstruction dont nous proposons d’apprendre un modèle non-supervisé à partir d’une base d’apprentissage constituée seulement de zones de non-changement afin que le modèle reconstruit les motifs de non-changement avec une faible erreur. Dans la dernière contribution, nous proposons une architecture d’apprentissage par paires de pixels basée sur un réseau CNN pseudo-siamois qui prend en entrée une paire de données au lieu d’une seule donnée et est constituée de deux flux de réseau (descripteur) CNN parallèles et partiellement non-couplés suivis d’un réseau de décision qui comprend de couche de fusion et une couche de classification au sens du critère d’entropie. Les modèles proposés s’avèrent assez flexibles pour être utilisés efficacement dans le cas des données-images mono-modales.

<p>The main accomplishments of this research are </p> <p>(1) developed a high fidelity computational methodology based on large eddy simulation to capture lean blowout (LBO) behaviors of different fuels; </p> <p>(2) developed fundamental insights into the combustion processes leading to the flame blowout and fuel composition effects on the lean blowout limits; </p> <p>(3) developed artificial intelligence-based models for early detection of the onset of the lean blowout in a realistic complex combustor. </p> <p>The methodologies are demonstrated by performing the lean blowout (LBO) calculations and statistical analysis for a conventional (A-2) and an alternative bio-jet fuel (C-1).</p> <p>High-performance computing methodology is developed based on the large eddy simulation (LES) turbulence models, detailed chemistry and flamelet based combustion models. This methodology is employed for predicting the combustion characteristics of the conventional fuels and bio-derived alternative jet fuels in a realistic gas turbine engine. The uniqueness of this methodology is the inclusion of as-it-is combustor hardware details such as complex hybrid-airblast fuel injector, thousands of tiny effusion holes, primary and secondary dilution holes on the liners, and the use of highly automated on the fly meshing with adaptive mesh refinement. The flow split and mesh sensitivity study are performed under non-reacting conditions. The reacting LES simulations are performed with two combustion models (finite rate chemistry and flamelet generated manifold models) and four different chemical kinetic mechanisms. The reacting spray characteristics and flame shape are compared with the experiment at the near lean blowout stable condition for both the combustion models. The LES simulations are performed by a gradual reduction in the fuel flow rate in a stepwise manner until a lean blowout is reached. The computational methodology has predicted the fuel sensitivity to lean blowout accurately with correct trends between the conventional and alternative bio-jet fuels. The flamelet generated manifold (FGM) model showed 60% reduction in the computational time compared to the finite rate chemistry model. </p> <p>The statistical analyses of the results from the high fidelity LES simulations are performed to gain fundamental insights into the LBO process and identify the key markers to predict the incipient LBO condition in swirl-stabilized spray combustion. The bio-jet fuel (C-1) exhibits significantly larger CH₂O concentrations in the fuel-rich regions compared to the conventional petroleum fuel (A-2) at the same equivalence ratio. It is observed from the analysis that the concentration of formaldehyde increases significantly in the primary zone indicating partial oxidation as we approach the LBO limit. The analysis also showed that the temperature of the recirculating hot gases is also an important parameter for maintaining a stable flame. If this temperature falls below a certain threshold value for a given fuel, the evaporation rates and heat release rated decreases significantly and consequently leading to the global extinction phenomena called lean blowout. The present study established the minimum recirculating gas temperature needed to maintain a stable flame for the A-2 and C-1 fuels. </p> The artificial intelligence (AI) models are developed based on high fidelity LES data for early identification of the incipient LBO condition in a realistic gas turbine combustor under engine relevant conditions. The first approach is based on the sensor-based monitoring at the optimal probe locations within a realistic gas turbine engine combustor for quantities of interest using the Support Vector Machine (SVM). Optimal sensor locations are found to be in the flame root region and were effective in detecting the onset of LBO ~20ms ahead of the event. The second approach is based on the spatiotemporal features in the primary zone of the combustor. A convolutional autoencoder is trained for feature extraction from the mass fraction of the OH ( data for all time-steps resulting in significant dimensionality reduction. The extracted features along with the ground truth labels are used to train the support vector machine (SVM) model for binary classification. The LBO indicator is defined as the output of the SVM model, 1 for unstable and 0 for stable. The LBO indicator stabilized to the value of 1 approximately 30 ms before complete blowout.

<p> This thesis presents work and simulations containing the use of Artificial Intelligence for real-time perception and real-time anomaly detection using the computer and sensors onboard an Unmanned Aerial Vehicle. One goal of this research is to develop a highly accurate, high-performance computer vision system that can then be used as a framework for object detection, obstacle avoidance, motion estimation, 3D reconstruction, and vision-based GPS denied path planning. The method developed and presented in this paper integrates software and hardware techniques to reach optimal performance for real-time operations. </p> <p>This thesis also presents a solution to real-time anomaly detection using neural networks to further the safety and reliability of operations for the UAV. Real-time telemetry data from different sensors are used to predict failures before they occur. Both these systems together form the framework behind the Intelligent UAV platform, which can be rapidly adopted for different varieties of use cases because of its modular nature and on-board suite of sensors. </p>

Proteins are considered the primary actors in living organisms. Proteins mainly perform their functions by interacting with other proteins. Protein-protein interactions underpin various biological activities such as metabolic cycles, signal transduction, and immune response. PPI identification has been addressed by various experimental methods such as the yeast two-hybrid, mass spectrometry, and protein microarrays, to mention a few. However, due to the sheer number of proteins, experimental methods for finding interacting and non-interacting protein pairs are time-consuming and costly. Therefore a sequence-based framework called ProtInteract is developed to predict protein-protein interaction. ProtInteract comprises two components: first, a novel autoencoder architecture that encodes each protein's primary structure to a lower-dimensional vector while preserving its underlying sequential pattern by extracting uncorrelated attributes and more expressive descriptors. This leads to faster training of the second network, a deep convolutional neural network (CNN) that receives encoded proteins and predicts their interaction. Three different scenarios formulate the prediction task. In each scenario, the deep CNN predicts the class of a given encoded protein pair. Each class indicates different ranges of confidence scores corresponding to the probability of whether a predicted interaction occurs or not. The proposed framework features significantly low computational complexity and relatively fast response. The present study makes two significant contributions to the field of protein-protein interaction (PPI) prediction. Firstly, it addresses the computational challenges posed by the high dimensionality of protein datasets through the use of dimensionality reduction techniques, which extract highly informative sequence attributes. Secondly, the proposed framework, ProtInteract, utilises this information to identify the interaction characteristics of a protein based on its amino acid configuration. ProtInteract encodes the protein's primary structure into a lower-dimensional vector space, thereby reducing the computational complexity of PPI prediction. Our results provide evidence of the proposed framework's accuracy and efficiency in predicting protein-protein interactions.

Deep learning for safe autonomous transport is rapidly emerging. Fast and robust perception for autonomous vehicles will be crucial for future navigation in urban areas with high traffic and human interplay. Previous work focuses on extracting full image depth maps, or finding specific road features such as lanes. However, in urban environments lanes are not always present, and sensors such as LiDAR with 3D point clouds provide a quite sparse depth perception of road with demanding algorithmic approaches. In this thesis we derive a novel convolutional neural network that we call AutoNet. It is designed as an encoder-decoder network for pixel-wise depth estimation of an urban drivable free-space road, using only a monocular camera, and handled as a supervised regression problem. AutoNet is also constructed as a classification network to solely classify and segment the drivable free-space in real- time with monocular vision, handled as a supervised classification problem, which shows to be a simpler and more robust solution than the regression approach. We also implement the state of the art neural network ENet for comparison, which is designed for fast real-time semantic segmentation and fast inference speed. The evaluation shows that AutoNet outperforms ENet for every performance metrics, but shows to be slower in terms of frame rate. However, optimization techniques are proposed for future work, on how to advance the frame rate of the network while still maintaining the robustness and performance. All the training and evaluation is done on the Cityscapes dataset. New ground truth labels for road depth perception are created for training with a novel approach of fusing pre-computed depth maps with semantic labels. Data collection with a Scania vehicle is conducted, mounted with a monocular camera to test the final derived models. The proposed AutoNet shows promising state of the art performance in regards to road depth estimation as well as road classification. / Deep learning för säkra autonoma transportsystem framträder mer och mer inom forskning och utveckling. Snabb och robust uppfattning om miljön för autonoma fordon kommer att vara avgörande för framtida navigering inom stadsområden med stor trafiksampel. I denna avhandling härleder vi en ny form av ett neuralt nätverk som vi kallar AutoNet. Där nätverket är designat som en autoencoder för pixelvis djupskattning av den fria körbara vägytan för stadsområden, där nätverket endast använder sig av en monokulär kamera och dess bilder. Det föreslagna nätverket för djupskattning hanteras som ett regressions problem. AutoNet är även konstruerad som ett klassificeringsnätverk som endast ska klassificera och segmentera den körbara vägytan i realtid med monokulärt seende. Där detta är hanterat som ett övervakande klassificerings problem, som även visar sig vara en mer simpel och mer robust lösning för att hitta vägyta i stadsområden. Vi implementerar även ett av de främsta neurala nätverken ENet för jämförelse. ENet är utformat för snabb semantisk segmentering i realtid, med hög prediktions- hastighet. Evalueringen av nätverken visar att AutoNet utklassar ENet i varje prestandamätning för noggrannhet, men visar sig vara långsammare med avseende på antal bilder per sekund. Olika optimeringslösningar föreslås för framtida arbete, för hur man ökar nätverk-modelens bildhastighet samtidigt som man behåller robustheten.All träning och utvärdering görs på Cityscapes dataset. Ny data för träning samt evaluering för djupskattningen för väg skapas med ett nytt tillvägagångssätt, genom att kombinera förberäknade djupkartor med semantiska etiketter för väg. Datainsamling med ett Scania-fordon utförs även, monterad med en monoculär kamera för att testa den slutgiltiga härleda modellen. Det föreslagna nätverket AutoNet visar sig vara en lovande topp-presterande modell i fråga om djupuppskattning för väg samt vägklassificering för stadsområden.