Esta tese de doutorado apresenta um modelo de especificação, textual e grafico, para sistemas transacionais em banco de dados (ER/T+) e, também, um modelo de implementação desta especificação. Sugere uma técnica de proceduralização de especificações declarativas, usando um grafo de dependencia de fluxos de dados para estabelecer a relação de precedecia entre os fluxos do diagrama da linguagem gráfica de especificação. Apresenta, também, os mecanismos de execução da linguagem de especificação proposta e as regras de mapeamento da linguagem de especificação, em seus aspectos estruturais (dados) e comportamentais (transações), para correspondentes construções na linguagem de implementação (C e SQL). Adicionalmente, são discutidos aspectos de otimização de consultas no âmbito da linguagem de especificação de transações e, também, aspectos de aninhamento de consultas para combinar diversos fluxos do diagrama ER/T+ em expressões complexas de consultas SQL. / This Ph.D thesis presents a graphic and textual specification model for database transactions systems (ER/T+) and, also, an implementation model for this specification. Suggest a proceduralization technique for declarative specifications using a data flow dependency graph to establish a precedence relation between the diagram flows of the graphics specification language. Furthermore it presents the execution mechanism of the proposal specification language and the behavioral and structural rules for mapping the specification language into corresponding implementation language (C and SQL) constructions. Additionaly, are discussed query optimization aspects for transaction specification language and aspects of nested queries to combine various ER/T+ diagram flows into complex SQL query expressions

This research presents a novel framework for automatic chroma keying and the optimizations for real-time and stereoscopic 3D processing. It first simulates the process of human perception on isolating foreground elements in a given scene by perceptual analysis, and then predicts foreground colours and alpha map based on the analysis results and the restored clean background plate rather than direct sampling. Besides, an object level depth map is generated through stereo matching on a carefully determined feature map. In addition, three prototypes on different platforms have been implemented according to their hardware capability based on the proposed framework. To achieve real-time performance, the entire procedures are optimized for parallel processing and data paths on the GPU, as well as heterogeneous computing between GPU and CPU. The qualitative comparisons between results generated by the proposed algorithm and other existing algorithms show that the proposed one is able to generate more acceptable alpha maps and foreground colours especially in those regions that contain translucencies and details. And the quantitative evaluations also validate our advantages in both quality and speed.

La agricultura es una de las actividades económicas más importantes en el Perú llegando a tener una gran variedad de cultivos de exportación. Pero a nivel nacional, solo unas cuantas han logrado la Denominación de Origen, como es el caso del grano seco de pallar en la región Ica. Este reconocimiento, junto con su alto valor nutricional, ha permitido duplicar su producción y exportación en los últimos 10 años. Sin embargo, la inadecuada forma en que se realiza una de las etapas principales, la selección del grano por calidad, trae problemas como imprecisiones en la calidad final del lote, repeticiones del proceso y, ya que este es un proceso manual, genera fatiga en el personal que ejecuta las operaciones. Las causas del problema están relacionadas con el actual procedimiento subjetivo y la no existencia de tecnología adecuada. Por ello, en este estudio se desarrolla un sistema mecatrónico que permite la selección automática de pallares cuyos criterios de selección se toman de la Norma Técnica Peruana para exportación de pallar, la NTP 205.019: 2015. De esta forma, se alcanza mantener un proceso objetivo, estandarizado, de mayor precisión y de reducido trabajo manual utilizando tecnologías modernas. El producto final es un prototipo automatizado con fabricación modular que clasifica los granos de pallar seco (aceptado o rechazado) utilizando algoritmos de procesamiento de imágenes y luego descarta los granos defectuosos mediante preactuadores neumáticos. Además, se utilizan transportadores vibratorios para movilizar a los granos de acuerdo a la necesidad. Finalmente, el hardware y software son implementados conforme a estándares y buenas prácticas de automatización industrial. / Agriculture is one of the most important economic activities in Peru, having a great variety of export crops. But only a few have achieved the Denomination of Origin at the national level, as is the case of the dry lima bean in the Ica region. This recognition, together with its high nutritional value, has allowed its production and exportation to double in the last 10 years. However, the inadequate way in which one of the main stages is carried out, the grain sorting by quality, brings problems such as inaccuracies in the final quality of the batch, repetitions of the process and, since this is a manual process, fatigue in the personnel. The causes of the problem are related to limited technology and the current subjective procedure. Therefore, in this study a mechatronic system is developed that allows the automatic lima beans sorting whose criteria are based on the Peruvian Technical Standard for lima beans export, the NTP 205.019: 2015. In this way, an objective process would be maintained, standardized, with reduced manual labor using modern technologies. The final product is an automated prototype with modular manufacturing that sorts dry lima beans (accepted or rejected) using image processing algorithms and then discards the defective ones using pneumatic actuators. In addition, vibratory conveyors are used to move the grains according to need. Finally, the hardware and software are implemented according to standards and good industrial automation practices. / Tesis

Introduction : Au sein de la population vieillissante, les chutes à domicile représentent une problématique importante (1 personne âgée/3 chute au moins 1 fois/année). Pour détecter automatiquement les chutes en respectant la vie privée, une technologie novatrice a été développée : la vidéosurveillance intelligente. Objectif : Explorer la perception et la réceptivité des personnes âgées concernant l’introduction de cette nouvelle technologie, à domicile. Méthodologie : Trente personnes âgées ont participé à une entrevue structurée (devis mixte). Une analyse de contenu (données qualitatives) et des analyses descriptives (données quantitatives) ont été effectuées puis combinées. Résultats : 93,4% des participants sont favorables (ou partiellement) à la vidéosurveillance intelligente et 43,3% l’utiliserait pour le sentiment de sécurité et la confidentialité procurés. Conclusion : Le contexte de vie des personnes âgées influence leur perception et réceptivité envers la vidéosurveillance intelligente. Il s’agit maintenant d’évaluer cette technologie dans divers milieux de vie. / Backgroung: Among the elderly, at-home falls are a significant problem (on average, 1 elder/3 falls at least 1/year). In order to automatically detect falls while maintaining privacy, an innovative technology was developed: an intelligent videomonitoring system. Objective: To explore the perception and receptivity of the elderly regarding the introduction of this new technology at home. Methodology: Using a mixed methods design, 30 elderly underwent a structured interview. A content analysis (qualitative data) and descriptive analyses (quantitative data) were executed and then combined. Findings: 93.4% of the participants were favorable (or partially) to the intelligent videomonitoring system and 43.3% would use it for the sense of security and the privacy provided. Conclusion: The living situation of the elderly influences their perception and receptivity regarding an intelligent videomonitoring system. The next step will be to evaluate this new technology in various living environments.

Introduction : Au sein de la population vieillissante, les chutes à domicile représentent une problématique importante (1 personne âgée/3 chute au moins 1 fois/année). Pour détecter automatiquement les chutes en respectant la vie privée, une technologie novatrice a été développée : la vidéosurveillance intelligente. Objectif : Explorer la perception et la réceptivité des personnes âgées concernant l’introduction de cette nouvelle technologie, à domicile. Méthodologie : Trente personnes âgées ont participé à une entrevue structurée (devis mixte). Une analyse de contenu (données qualitatives) et des analyses descriptives (données quantitatives) ont été effectuées puis combinées. Résultats : 93,4% des participants sont favorables (ou partiellement) à la vidéosurveillance intelligente et 43,3% l’utiliserait pour le sentiment de sécurité et la confidentialité procurés. Conclusion : Le contexte de vie des personnes âgées influence leur perception et réceptivité envers la vidéosurveillance intelligente. Il s’agit maintenant d’évaluer cette technologie dans divers milieux de vie. / Backgroung: Among the elderly, at-home falls are a significant problem (on average, 1 elder/3 falls at least 1/year). In order to automatically detect falls while maintaining privacy, an innovative technology was developed: an intelligent videomonitoring system. Objective: To explore the perception and receptivity of the elderly regarding the introduction of this new technology at home. Methodology: Using a mixed methods design, 30 elderly underwent a structured interview. A content analysis (qualitative data) and descriptive analyses (quantitative data) were executed and then combined. Findings: 93.4% of the participants were favorable (or partially) to the intelligent videomonitoring system and 43.3% would use it for the sense of security and the privacy provided. Conclusion: The living situation of the elderly influences their perception and receptivity regarding an intelligent videomonitoring system. The next step will be to evaluate this new technology in various living environments.

Les images multi-spectrales présentent l’avantage de fournir des informations complémentaires permettant de lever des ambigüités. Le défi est cependant comment exploiter ces informations multi-spectrales efficacement. Dans cette thèse, nous nous focalisons sur la fusion des images multi-spectrales en extrayant des attributs les plus pertinents en vue d’obtenir la meilleure segmentation possible avec le moindre coût de calcul possible. La classification par le Support Vector Machine (SVM), combinée avec une méthode de sélection d’attributs, est proposée. Le critère de sélection est défini par la séparabilité des noyaux de classe. S’appuyant sur cette classification SVM, un cadre pour suivre l’évolution est proposé. Il comprend les étapes suivantes : apprentissage des tumeurs cérébrales et sélection des attributs à partir du premier examen IRM (imagerie par résonance magnétique) ; segmentation automatique des tumeurs dans de nouvelles images en utilisant une classification basée sur le SVM multi-noyaux ; affiner le contour des tumeurs par une technique de croissance de région ; effectuer un éventuel apprentissage adaptatif. L’approche proposée a été évaluée sur 13 patients avec 24 examens, y compris 72 séquences IRM et 1728 images. En comparant avec le SVM traditionnel, Fuzzy C-means, le réseau de neurones, et une méthode d’ensemble de niveaux, les résultats de segmentation et l’analyse quantitative de ces résultats démontrent l’efficacité de l’approche proposée. / Multi-spectral images have the advantage of providing complementary information to resolve some ambiguities. But, the challenge is how to make use of the multi-spectral images effectively. In this thesis, our study focuses on the fusion of multi-spectral images by extracting the most useful features to obtain the best segmentation with the least cost in time. The Support Vector Machine (SVM) classification integrated with a selection of the features in a kernel space is proposed. The selection criterion is defined by the kernel class separability. Based on this SVM classification, a framework to follow up brain tumor evolution is proposed, which consists of the following steps: to learn the brain tumors and select the features from the first magnetic resonance imaging (MRI) examination of the patients; to automatically segment the tumor in new data using a multi-kernel SVM based classification; to refine the tumor contour by a region growing technique; and to possibly carry out an adaptive training. The proposed system was tested on 13 patients with 24 examinations, including 72 MRI sequences and 1728 images. Compared with the manual traces of the doctors as the ground truth, the average classification accuracy reaches 98.9%. The system utilizes several novel feature selection methods to test the integration of feature selection and SVM classifiers. Also compared with the traditional SVM, Fuzzy C-means, the neural network and an improved level set method, the segmentation results and quantitative data analysis demonstrate the effectiveness of our proposed system.