Future sea level rise associated to global warming is one of the greatest societal and environmental challenges of tomorrow. A large part of the contribution comes from glaciers and ice sheets discharging ice and meltwater into the ocean and the recent worldwide increase is worrying. Future predictions of sea level rise try to encompass the complex processes of ice dynamics through glacier modelling but there are still large uncertainties due to the lack of observations or too coarse parameterisation, particularly for processes occurring at the glacier interfaces with the bed (sliding) and with the ocean (calving). This thesis focuses on modelling these processes from two marine-terminating glaciers in Svalbard, Kronebreen and Tunabreen. By inverting three years of high temporal resolution time-series of surface velocities on Kronebreen, basal properties are retrieved with the ice flow model Elmer/Ice in Paper I. Results suggest that surface melt during the summer greatly influences the dynamics of the following season and that sliding laws for such glaciers should be adapted to local and global processes changing in space and time. The subglacial drainage system, fed by the surface melt, is modelled in Paper II during two melting seasons. Results show different configurations of efficient and inefficient drainage systems between years and the importance of using a sliding law dependent on spatio-temporal changes in effective pressure. The interaction with the ocean is incorporated in Paper III by combining a series of models, including an ice flow model, a plume model and a particle model for discrete calving and compares the output with observations. Results show the importance of glacier geometry, sliding and undercutting on calving rate and location. However, more observations and analytic methods are needed. Time-lapse imagery placed in front of Tunabreen have been deployed and a method of automatic detection for iceberg calving is presented in Paper IV. Results show the influence of the rising plume in calving and the front destabilisation of the local neighbourhood.

Ce travail de thèse s’inscrit dans le domaine de l’informatique affective et plus précisément de l’intelligence artificielle et de l’exploration d’architecture. L’objectif de ce travail est de concevoir un système complet de détection des émotions en utilisant des signaux physiologiques. Ce travail se place donc à l’intersection de l’informatique pour la définition d’algorithme de détection des émotions et de l’électronique pour l’élaboration d’une méthodologie d’exploration d’architecture et pour la conception de nœuds de capteurs. Dans un premier temps, des algorithmes de détection multimodale et instantanée des émotions ont été définis. Deux algorithmes de classification KNN puis SVM, ont été implémentés et ont permis d’obtenir un taux de reconnaissance des émotions supérieurs à 80%. Afin de concevoir un tel système alimenté sur pile, un modèle analytique d’estimation de la consommation à haut niveau d’abstraction a été proposé et validé sur une plateforme réelle. Afin de tenir compte des contraintes utilisateurs, un outil de conception et de simulation d’architecture d’objets connectés pour la santé a été développé, permettant ainsi d’évaluer les performances des systèmes avant leur conception. Une architecture logicielle/matérielle pour la collecte et le traitement des données satisfaisant les contraintes applicatives et utilisateurs a ainsi été proposée. Doté de cette architecture, des expérimentations ont été menées pour la Mnémothérapie musicale. EMOTICA est un système complet de détection des émotions utilisant des signaux physiologiques satisfaisant les contraintes d’architecture, d’application et de l’utilisateur. / This thesis work is part of the field of affective computing and more specifically artificial intelligence and architectural exploration. The goal of this work is to design a complete system of emotions detection using physiological signals. This work is therefore situated at the intersection of computer science for the definition of algorithm of detection of emotions and electronics for the development of an architecture exploration methodology for the design of sensor nodes. At first, algorithms for multimodal and instantaneous detection of emotions were defined. Two algorithms of classification KNN then SVM, were implemented and made it possible to obtain a recognition rate of the emotions higher than 80%. To design such a battery-powered system, an analytical model for estimating the power consumption at high level of abstraction has been proposed and validated on a real platform. To consider user constraints, a connected object architecture design and simulation tool for health has been developed, allowing the performance of systems to be evaluated prior to their design. Then, we used this tool to propose a hardware/software architecture for the collection and the processing of the data satisfying the architectural and applicative constraints. With this architecture, experiments have been conducted for musical Mnemotherapy. EMOTICA is a complete system for emotions detection using physiological signals satisfying the constraints of architecture, application and user.

This Ph.D. dissertation processes and analyzes signals from the neonatal intensive care units (NICUs) for the study of maturity, systemic infection (sepsis) and the influence of immunization in the premature newborn. A special attention is payed to the electroencephalography and the breathing signal. The former is often contaminated by several sources of noise, thus methods based on the signals decomposition and optimal noise cancellation, adapted to the characteristics of the immature EEG, were proposed and evaluated objectively on real and simulated signals. By means of the EEG and delta burst analysis, detected automatically by a proposed classifier, infant's maturation and the effects of vaccination are studied. Concerning the second signal, breathing, non-linear and fractal methods are adapted to evaluate maturity and sepsis. A robustness study of estimation methods is also conducted, showing that the Hurst exponent, estimated on respiratory variability signals, is a good detector of infection.

Nous abordons, dans cette thèse, une étude sur les représentations continues de mots (en anglais word embeddings) appliquées à la détection automatique des erreurs dans les transcriptions de la parole. Notre étude se concentre sur l’utilisation d’une approche neuronale pour améliorer la détection automatique des erreurs dans les transcriptions automatiques, en exploitant les word embeddings. L’exploitation des embeddings repose sur l’idée que la détection d’erreurs consiste à trouver les possibles incongruités linguistiques ou acoustiques au sein des transcriptions automatiques. L’intérêt est donc de trouver la représentation appropriée du mot qui permet de capturer des informations pertinentes pour pouvoir détecter ces anomalies. Notre contribution dans le cadre de cette thèse porte sur plusieurs axes. D’abord, nous commençons par une étude préliminaire dans laquelle nous proposons une architecture neuronale capable d’intégrer différents types de descripteurs, y compris les embeddings. Ensuite, nous nous focalisons sur une étude approfondie des représentations continues de mots. Cette étude porte d’une part sur l’évaluation de différents types d’embeddings linguistiques puis sur leurs combinaisons. D’autre part, elle s’intéresse aux embeddings acoustiques de mots. Puis, nous présentons une étude sur l’analyse des erreurs de classifications, qui a pour objectif de percevoir les erreurs difficiles à détecter.Finalement, nous exploitons les embeddings linguistiques et acoustiques ainsi que l’information fournie par notre système de détections d’erreurs dans plusieurs cadres applicatifs. / My thesis concerns a study of continuous word representations applied to the automatic detection of speech recognition errors. Our study focuses on the use of a neural approach to improve ASR errors detection, using word embeddings. The exploitation of continuous word representations is motivated by the fact that ASR error detection consists on locating the possible linguistic or acoustic incongruities in automatic transcriptions. The aim is therefore to find the appropriate word representation which makes it possible to capture pertinent information in order to be able to detect these anomalies. Our contribution in this thesis concerns several initiatives. First, we start with a preliminary study in which we propose a neural architecture able to integrate different types of features, including word embeddings. Second, we propose a deep study of continuous word representations. This study focuses on the evaluation of different types of linguistic word embeddings and their combination in order to take advantage of their complementarities. On the other hand, it focuses on acoustic word embeddings. Then, we present a study on the analysis of classification errors, with the aim of perceiving the errors that are difficult to detect. Perspectives for improving the performance of our system are also proposed, by modeling the errors at the sentence level. Finally, we exploit the linguistic and acoustic embeddings as well as the information provided by our ASR error detection system in several downstream applications.

Ce mémoire de thèse porte sur le traitement et l'analyse des signaux issus des unités de soins intensifs néonatales (USIN) pour l'étude de la maturité, de l'infection généralisée et de l'influence de l'immunisation chez le nouveau-né prématuré. Une attention particulière est portée sur l'électroencéphalographie et le signal de respiration. Pour le premier, ce signal est souvent bruité en USIN et des méthodes de décomposition du signal et d'annulation optimale du bruit, adaptées aux particularités des EEG immatures, ont été proposées et évaluées objectivement sur signaux réels et simulés. L'analyse de l'EEG et des bouffées delta, repérées automatiquement par un classificateur proposé, ont permis d'étudier la maturation et les effets de la vaccination. Pour la seconde modalité, la respiration, des méthodes non-linéaires et fractales sont retenues et adaptées pour évaluer la maturité et l'infection généralisée. Une étude de robustesse des méthodes d'estimation est menée et on montre que l'exposant de Hurst, estimé sur des signaux de variabilité respiratoire, est un bon détecteur de l'infection. / This Ph.D. dissertation processes and analyzes signals from the neonatal intensive care units (NICUs) for the study of maturity, systemic infection (sepsis) and the influence of immunization in the premature newborn. A special attention is payed to the electroencephalography and the breathing signal. The former is often contaminated by several sources of noise, thus methods based on the signals decomposition and optimal noise cancellation, adapted to the characteristics of the immature EEG, were proposed and evaluated objectively on real and simulated signals. By means of the EEG and delta burst analysis, detected automatically by a proposed classifier, infant's maturation and the effects of vaccination are studied. Concerning the second signal, breathing, non-linear and fractal methods are adapted to evaluate maturity and sepsis. A robustness study of estimation methods is also conducted, showing that the Hurst exponent, estimated on respiratory variability signals, is a good detector of infection.

Opioid overdose is a growing epidemic plaguing the United States. Overdose related death has risen from 16,849 in 1999 to 69,029 in 2018. Almost 7 out of 10 of these deaths were due to opioids with 47% being caused by fentanyl or other synthetic opioids. There is a strong need to reduce the amount of overdose-related deaths. Indirect methods should be a first priority, and include counseling and care. For some individuals, this treatment option is unavailable because the drug user may not have the desire or economic means to pursue it. In this case, a more direct preventative approach is needed. This paper presents a novel method of detecting poor peripheral oxygenation, a biomarker linked to opioid overdose. A wristwatch near-infrared spectroscopy device (NIRS) was developed. SPICE simulations were conducted to confirm proper operation of electrical systems. The device was fabricated on a printed circuit board and mounted to a 3D printed enclosure. Absorbance of green, red and infrared (IR) light were measured. Additionally, peripheral capillary oxygen saturation (SpO2) modulation index and changes in concentration of oxyhemoglobin and deoxyhemoglobin were calculated from raw data. A brachial occlusion test was performed to mimic the effects of opioid overdose on peripheral oxygenation. A statistically significant difference (p < 0.05) was observed between pre-occlusion and during-occlusion groups in two subjects for measurement of peak-to-peak values of green raw data, red raw data, IR raw data, oxyhemoglobin concentration change, and deoxyhemoglobin concentration change. Peak-to-peak was observed as a consistent indicator of poor peripheral oxygenation and could serve as a useful metric in the detection of opioid overdose.

In my thesis I go about principles and methods of security systems, then I go about analysis of avalaible types of security systems (EPS, EZS and CCTV). I have written about their possibile use in design security building. I have described levels of project documentation and its different parts including process service of production a project documentation for security system. I used all knowledges in the end of my thesis, when I designed and integrated security system for a special building.

[ES] La endoscopia capsular (CE) es una ampliamente utilizada alternativa mínimamente invasiva a la endoscopia tradicional, que permite la visualización de todo el intestino delgado, mientras no es posible hacerlo fácilmente con los procedimientos más invasivos. Sin embargo, esos métodos tradicionales aún suelen ser la primera opción de tratamiento, ya que todavía existen desafíos importantes en el campo de la CE, incluyendo el tiempo necesario para el diagnóstico por vídeo después del procedimiento, el hecho de que la cápsula no se puede controlar activamente, la falta de consenso sobre una buena preparación del paciente y el coste alto. En esta tesis doctoral, nuestro objetivo es extraer más información de los procedimientos de endoscopía por cápsula para ayudar a aliviar estos problemas desde una perspectiva que parece estar subrepresentada en la investigación actual. Primero, como el objetivo principal en esta tesis, pretendemos desarrollar un método de evaluación de la limpieza en procedimientos de CE automático y objetivo para asistir la investigación médica en métodos de preparación de los pacientes. Específicamente, a pesar de que una preparación adecuada del paciente pueda ayudar a obtener una mejor visibilidad, los estudios sobre el método más efectivo son contradictorios debido a la ausencia de tal método. Por lo tanto, pretendemos proporcionar un método de ese tipo, capaz de presentar la limpieza en una escala intuitiva, con una novedosa arquitectura relativamente ligera de una red neuronal convolucional en su núcleo. Entrenamos este modelo en un conjunto de datos extensivo de más de 50,000 parches de imágenes, obtenidos de 35 procedimientos CE diferentes, y lo comparamos con métodos de clasificación del estado del arte. A partir de la clasificación, desarrollamos un método para automáticamente estimar las probabilidades a nivel de píxel y deducir los puntos en la escala de la evaluación de la limpieza a través de umbrales aprendidos. Después, validamos nuestro método en un entorno clínico en 30 videos de CE obtenidos nuevamente, comparando las puntuaciones resultantes con las asignadas de forma independiente por especialistas humanos. Obtuvimos la mayor precisión de clasificación para el método propuesto (95,23%), con tiempos de predicción promedios significativamente más bajos que para el segundo mejor método. En la validación, encontramos un acuerdo aceptable con dos especialistas humanos en comparación con el acuerdo interhumano, mostrando su validez como método de evaluación objetivo. Adicionalmente, otro objetivo de este trabajo es detectar automáticamente el túnel y ubicar el túnel en cada fotograma. Para este objetivo, entrenamos un modelo basado en R-CNN, concretamente el detector ligero YOLOv3, en un total de 1385 fotogramas, extraídos de procedimientos de CE de 10 pacientes diferentes. De tal manera, alcanzamos una precisión del 86,55% y una recuperación del 88,79% en nuestro conjunto de datos de test. Ampliando este objetivo, también pretendemos visualizar la motilidad intestinal de una manera análoga a una manometría intestinal tradicional, basada únicamente en la técnica mínimamente invasiva de CE. Para esto, alineamos los fotogramas con similar orientación y derivamos los parámetros adecuados para nuestro método de segmentación de las propiedades del rectángulo delimitador del túnel. Finalmente, calculamos el tamaño relativo del túnel para construir un equivalente de una manometría intestinal a partir de información visual. Desde que concluimos nuestro trabajo, nuestro método para la evaluación automática de la limpieza se ha utilizado en un estudio a gran escala aún en curso, en el que participamos activamente. Mientras gran parte de la investigación se centra en la detección automática de patologías, como tumores, pólipos y hemorragias, esperamos que nuestro trabajo pueda hacer una contribución significativa para extraer más información de la CE también en otras áreas frecuentemente subestimadas. / [CA] L'endoscòpia capsular (CE) és una àmpliament utilitzada alternativa mínimament invasiva a l'endoscòpia tradicional, que permet la visualització de tot l'intestí prim, mentre no és possible fer-lo fàcilment amb els procediments més invasius. No obstant això, aqueixos mètodes tradicionals encara solen ser la primera opció de tractament, ja que encara existeixen desafiaments importants en el camp de la CE, incloent el temps necessari per al diagnòstic per vídeo després del procediment, el fet que la càpsula no es pot controlar activament, la falta de consens sobre una bona preparació del pacient i el cost alt. En aquesta tesi doctoral, el nostre objectiu és extraure més informació dels procediments de endoscopía per càpsula per a ajudar a alleujar aquests problemes des d'una perspectiva que sembla estar subrepresentada en la investigació actual. Primer, com l'objectiu principal en aquesta tesi, pretenem desenvolupar un mètode d'avaluació de la neteja en procediments de CE automàtic i objectiu per a assistir la investigació mèdica en mètodes de preparació dels pacients. Específicament, a pesar que una preparació adequada del pacient puga ajudar a obtindre una millor visibilitat, els estudis sobre el mètode més efectiu són contradictoris a causa de l'absència de tal mètode. Per tant, pretenem proporcionar un mètode d'aqueix tipus, capaç de presentar la neteja en una escala intuïtiva, amb una nova arquitectura relativament lleugera d'una xarxa neuronal convolucional en el seu nucli. Entrenem aquest model en un conjunt de dades extensiu de més de 50,000 pegats d'imatges, obtinguts de 35 procediments CE diferents, i el comparem amb mètodes de classificació de l'estat de l'art. A partir de la classificació, desenvolupem un mètode per a automàticament estimar les probabilitats a nivell de píxel i deduir els punts en l'escala de l'avaluació de la neteja a través de llindars apresos. Després, validem el nostre mètode en un entorn clínic en 30 vídeos de CE obtinguts novament, comparant les puntuacions resultants amb les assignades de manera independent per especialistes humans. Vam obtindre la major precisió de classificació per al mètode proposat (95,23%), amb temps de predicció mitjanes significativament més baixos que per al segon millor mètode. En la validació, trobem un acord acceptable amb dos especialistes humans en comparació amb l'acord interhumà, mostrant la seua validesa com a mètode d'avaluació objectiu. Addicionalment, un altre objectiu d'aquest treball és detectar automàticament el túnel i situar el túnel en cada fotograma. Per a aquest objectiu, entrenem un model basat en R-CNN, concretament el detector lleuger YOLOv3, en un total de 1385 fotogrames, extrets de procediments de CE de 10 pacients diferents. De tal manera, aconseguim una precisió del 86,55% i una recuperació del 88,79% en el nostre conjunt de dades de test. Ampliant aquest objectiu, també pretenem visualitzar la motilitat intestinal d'una manera anàloga a una manometría intestinal tradicional, basada únicament en la tècnica mínimament invasiva de CE. Per a això, alineem els fotogrames amb similar orientació i derivem els paràmetres adequats per al nostre mètode de segmentació de les propietats del rectangle delimitador del túnel. Finalment, calculem la grandària relativa del túnel per a construir un equivalent d'una manometría intestinal a partir d'informació visual. Des que concloem el nostre treball, el nostre mètode per a l'avaluació automàtica de la neteja s'ha utilitzat en un estudi a gran escala encara en curs, en el qual participem activament. Mentre gran part de la investigació se centra en la detecció automàtica de patologies, com a tumors, pòlips i hemorràgies, esperem que el nostre treball puga fer una contribució significativa per a extraure més informació de la CE també en altres àrees sovint subestimades. / [EN] Capsule endoscopy (CE) is a widely used, minimally invasive alternative to traditional endoscopy that allows visualisation of the entire small intestine, whereas more invasive procedures cannot easily do this. However, those traditional methods are still commonly the first choice of treatment for gastroenterologists as there are still important challenges surrounding the field of CE. Among others, these include the time consuming video diagnosis following the procedure, the fact that the capsule cannot be actively controlled, lack of consensus on good patient preparation and the high cost. In this doctoral thesis, we aim to extract more information from capsule endoscopy procedures to aid in alleviating these issues from a perspective that appears to be under-represented in current research. First, and as the main objective in this thesis, we aim to develop an objective, automatic cleanliness evaluation method in CE procedures to aid medical research in patient preparation methods. Namely, even though adequate patient preparation can help to obtain a cleaner intestine and thus better visibility in the resulting videos, studies on the most effective preparation method are conflicting due to the absence of such a method. Therefore, we aim to provide such a method, capable of presenting results on an intuitive scale, with a relatively light-weight novel convolutional neural network architecture at its core. We trained this model on an extensive data set of over 50,000 image patches, collected from 35 different CE procedures, and compared it with state-of-the-art classification methods. From the patch classification results, we developed a method to automatically estimate pixel-level probabilities and deduce cleanliness evaluation scores through automatically learnt thresholds. We then validated our method in a clinical setting on 30 newly collected CE videos, comparing the resulting scores to those independently assigned by human specialists. We obtained the highest classification accuracy for the proposed method (95.23%), with significantly lower average prediction times than for the second-best method. In the validation of our method, we found acceptable agreement with two human specialists compared to interhuman agreement, showing its validity as an objective evaluation method. Additionally, we aim to automatically detect and localise the tunnel in each frame, in order to help determine the capsule orientation at any given time. For this purpose, we trained an R-CNN based model, namely the light-weight YOLOv3 detector, on a total of 1385 frames, extracted from CE procedures of 10 different patients, achieving a precision of 86.55% combined with a recall of 88.79% on our test set. Extending on this, we additionally aim to visualise intestinal motility in a manner analogous to a traditional intestinal manometry, solely based on the minimally invasive technique of CE, through aligning the frames with similar orientation and using the bounding box parameters to derive adequate parameters for our tunnel segmentation method. Finally, we calculate the relative tunnel size to construct an equivalent of an intestinal manometry from visual information. Since we concluded our work, our method for automatic cleanliness evaluation has been used in a still on-going, large-scale study, with in which we actively participate. While much research focuses on automatic detection of pathologies, such as tumors, polyps and bleedings, we hope our work can make a significant contribution to extract more information from CE also in other areas that are often overlooked. / Noorda, RA. (2022). Clearing the Way in Capsule Endoscopy with Deep Learning and Computer Vision [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/183752 / TESIS

Imagine a world where someone’s personal information is constantly compromised, where federal government entities AKA Big Brother always knows what anyone is Googling, who an individual is texting, and their emoticons on Twitter. Government entities have been doing this for years; they never cared if they were breaking the law or their moral compass of human dignity. Every day the Federal government blatantly siphons data with programs from the original ECHELON to the new series like PRISM and Xkeyscore so they can keep their tabs on issues that are none of their business; namely, the personal lives of millions. Our allies are taking note; some are learning our bad habits, from Government Communications Headquarters’ (GCHQ) mass shadowing sharing plan to America’s Russian inspiration, SORM. Some countries are following the United States’ poster child pose of a Brave New World like order of global events. Others like Germany are showing their resolve in their disdain for the rise of tyranny. Soon, these new found surveillance troubles will test the resolve of the American Constitution and its nation’s strong love and tradition of liberty. Courts are currently at work to resolve how current concepts of liberty and privacy apply to the current conditions facing the privacy of society. It remains to be determined how liberty will be affected as well; liberty for the United States of America, for the European Union, the Russian Federation and for the people of the World in regards to the extent of privacy in today’s blurred privacy expectations.