A system for vessel characterization aimed at detecting deep vein thrombosis (DVT) in the lower limbs has been developed and evaluated using ultrasound image processing, location and force sensors measurements, blood flow information and a protocol based on the current clinical standard, compression ultrasound. The goal is to provide an objective and repeatable system to measure DVT in a rapid and standardized manner, as this has been suggested in the literature as an approach to improve overall detection of the disease. The system uses a spatial Kalman filter-based algorithm with an elliptical model in the measurement equation to detect vessel contours in transverse ultrasound images and estimate ellipse parameters, and temporal constant velocity Kalman filters for tracking vessel location in real-time. The vessel characterization also comprises building a 3-D vessel model and performing compression and blood flow assessments to calculate measures that indicate the possibility of DVT in a vessel. A user interface designed for assessing a vessel for DVT was also developed. The system and components were implemented and tested in simulations, laboratory settings, and clinical settings. Contour detection results are good, with mean and rms errors ranging from 1.47-3.64 and 3.69-9.67 pixels, respectively, in simulated and patient images, and parameter estimation errors of 5%. Experiments showed errors of 3-5 pixels for the tracking approaches. The measures for DVT were evaluated, independently and integrated in the system. The complete system was evaluated, with sensitivity of 67-100% and specificity of 50-89.5%. System learnability and memorability were evaluated in a separate user study, with good results. Contributions include a segmentation approach using a full parameter ellipse model in an extended Kalman filter, incorporating multiple measurements, an alternate sampling method for faster parameter convergence and application-specific initialization, and a tracking approach that includes a sub-sampled sum of absolutes similarity calculation and a method to detect vessel bifurcations using flow data. Further contributions include an integrated system for DVT detection that can combine ultrasound B-mode, colour flow and elastography images for vessel characterization, a system interface design focusing on usability that was evaluated with medical professionals, and system evaluations through multiple patient studies.

Στη παρούσα διπλωματική εργασία ασχολούμαστε με την ανάπτυξη τεχνικών για υλοποίηση ενός κατανεμημένου φίλτρου Kalman σε ένα Δίκτυο Αισθητήρων (WSN). Τα δίκτυα αυτά έχουν γνωρίσει τα τελευταία χρόνια ραγδαία ανάπτυξη λόγω των εξαιρετικά πολλών εφαρμογών τους σε διάφορα πεδία της ανθρώπινης δραστηριότητας. Το πρόβλημα που πραγματευόμαστε εδώ είναι η προσπάθεια εκτίμησης της κατάστασης μιας στοχαστικής διαδικασίας που επιτηρείται-παρακολουθείται απο το δίκτυο. Οι κόμβοι-αισθητήρες που συναπαρτίζουν αυτά τα δίκτυα έχουν συνήθως περιορίσμενες δυνατότητες ¨αίσθησης¨, πράγμα που σημαίνει ότι κάθε μεμονωμένος κόμβος αδυνατεί να παράξει μια καλή εκτίμηση της κατάστασης. Διάφορες τεχνικές εχούν προταθεί για την επίλυση τέτοιου είδους προβλημάτων όπως το κεντρικό Φίλτρο Kalman ή διάφορες αποκεντρωμένες προσεγγίσεις, οι οποιές είχαν όμως υψηλό υπολογιστικό κόστος και τις καθιστούσαν πρακτικά μη υλοποιήσιμες, ειδικά για δίκτυα με μεγάλο αριθμό κόμβων. Έτσι στη παρούσα εργασία , χρησιμοποιώντας ως εργαλείο την θεώρια των αλγορίθμων ¨Κοινής Συμφωνίας¨ (Consensus Algorithms) , κατασκευάζουμε Αλγορίθμους χαμήλης πολυπλοκότητας, για την υλοποίηση ενός Kατανεμημένου Φίλτρου Kalman, θεωρώντας ότι όλοι οι κόμβοι είναι ομότιμοι (peer-to-peer αρχιτεκτονικές), κάθε κόμβος επικοινωνεί μόνο με τους γειτονικούς του και δεν υπάρχουν Fusion Centers. Παρουσιάζουμε έτσι τρεις διαφορετικούς επαναληπτικούς αλγορίθμους βασιζομένων σε δύο διαφορετικές λογικές και τέλος προσομοιώνουμε και αξιολογούμε την επίδοση καθενός από αυτούς. / In this thesis we deal with the development of techniques for implementing a distributed Kalman filter in a sensor network (WSN). Ιn recent years these networks have experienced rapid growth, due to the numerous applications in various fields of human activity. The problem we discuss here is the attempt to estimate the state of a stochastic process which is monitored by nodes-sensors. The nodes that constitute these networks usually have limited “sense” capabilities, which means that each node is unable to produce a good estimate of the state, using only its own measurements. Various techniques have been proposed to solve this kind of problems, such as the Central Kalman Filter or several decentralized approaches, which did have a high computational cost that renders them impractical, especially for networks with a high number of nodes. Thus, in the present work, , we construct low complexity algorithms for the implementation of a Distirbuted Kalman Filter, using as a tool the theory of Consensus Algorithms and assuming that all nodes are peers (peer-to-peer architectures), each node communicates only with its neighboring and no Fusion Centers exist. Τhus, we present three different iterative algorithms based on two different approaches and finally simulate and evaluate the performance of each of them.

Este trabalho apresenta um modelo matemático para a inferência do estado emocional de um usuário ou interlocutor com base em suas expressões faciais. O modelo apresentado consiste em dois estágios básicos, responsáveis pelo tratamento de sinais e sua integração, respectivamente. No primeiro estágio, filtros de Kalman independentes são utilizados para o processamento paralelo dos sinais relativos às expressões faciais emocionais. O estágio de integração, por sua vez, aplica os sinais filtrados a um sistema no qual uma partícula desliza sobre uma superfície a qual representa os estados e transições emocionais. O estado emocional do interlocutor é inferido, quadro a quadro, por meio da inspeção da posição instantânea da partícula. Uma heurística de simulação-otimização baseada em recozimento simulado (simulated annealing), é introduzida a fim de automatizar o processo de ajuste dos parâmetros do modelo em conformidade com o algoritmo de detecção de expressões faciais escolhido. O modelo proposto foi validado utilizando-se um corpus contendo 51 vídeos. Os resultados são comparados à classificação realizada por um grupo de voluntários, correspondendo a esta em 92% dos casos. / This work presents a mathematical model for emotional state inference based solely on facial expressions. The presented model consists of two basic steps, which are responsible for signal processing and its integration, respectively. During the former, independent Kalman filters are employed for parallel processing of emotional facial expression related signals. The later step, integration, applies those filtered signals to a system where a massless particle slides along a surface representing the emotional states of interest and its transitions. The subjects emotional state is inferred from the particles instantaneous position at each frame. A simulation-optimization heuristic based on simulated annealing is introduced as for fully automatic parameter tuning technique, which allows for easily coupling between the proposed model and different facial expression detection algorithms. The proposed model is validated against 51 multimodal emotional videos. The results are compared to human-based classification and a 92% agreement rate is observed.

No Brasil a exploração do petróleo está crescendo cada vez mais principalmente com as atividades offshore devido às constantes descobertas de novas jazidas em alto mar. Isto cria a necessidade de embarcações que garantam operações mais seguras o que pode ser obtido com aquelas dotadas de sistemas de posicionamento dinâmico. O projeto de um sistema de posicionamento dinâmico não é simples sob o ponto de vista de controle já que é um sistema não-linear multivariável sobreatuado; e não é barato devido aos elevados custos de implementação. Portanto, para se projetar adequadamente este tipo de sistema é imprescindível a elaboração de meios para ensaiar toda a estrutura real em desenvolvimento num tanque de provas utilizando modelos em escala. Neste trabalho é mostrado o projeto, construção e testes da eletrônica embarcada de um aparato experimental para ensaios de veículos oceânicos em tanque de provas, cujo projeto baseou-se em aspectos técnicos importantes para seu bom funcionamento como a descentralização dos processamentos necessários, a comunicação sem fio robusta com um console central responsável pelo processamento de todos os algoritmos do controlador superior e a preocupação com a compatibilidade eletromagnética do sistema. O console central consiste de uma interface de comunicação com o usuário e dos blocos de controle que são o filtro de Kalman, o controlador e o alocador de empuxos. Nos ensaios o desempenho da eletrônica é averiguado experimentalmente e os excelentes resultados obtidos mostram que o modelo responde de acordo com os comandos do controlador, principalmente com relação aos controles localizados para cada motor de propulsor contribuindo assim para o bom comportamento do conjunto. / In Brazil the exploration of oil is increasing mainly with the offshore activities due to the new found deposits. This situation requires more safety vessels which can be achieved using dynamic positioning systems. As a dynamic positioning system is a multivariable non linear and overactuated system, its design is not simple; and it is also not cheap due to high implementation costs. Therefore, the development of experimental environments to adequately study and design this type of system is essential. This work shows the embedded electronic project and assembly of an experimental setup in order to test floating vessel models. The project was developed based on important technical aspects to guarantee a good performance like processing decentralization, robust wireless communication with a central console responsible by the all control algorithms and the concern with electromagnetic compatibility of the system. The central console is composed by a human interface, control and Kalman filter structures and a thruster allocation algorithm. The performance of the electronic structure is verified experimentally during the tests and the excellent results show that the model works, in accordance to the controller commands, mainly related to local thruster control which contributes to the good system behavior

Orientador: Jose C. Geromel / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Elétrica e de Computação / Made available in DSpace on 2018-08-09T14:56:40Z (GMT). No. of bitstreams: 1 Martins_RafaeldeCastroDuarte_M.pdf: 331846 bytes, checksum: 23104cfddf85c27b47361e2f3ba52327 (MD5) Previous issue date: 2007 / Resumo: Neste trabalho, é proposto um novo método para o projeto de filtros robustos em norma H2, que consiste na utilização de uma combinação linear dos filtros de Kalman obtidos para os vértices do politopo de incertezas. Para esta classe de filtros, são obtidos problemas, expressos na forma de LMIs, para a determinação dos coeficientes que produzem o melhor filtro robusto. Inicialmente, uma sub-classe de sistemas politópicos é considerada e, em seguida, os resultados são generalizados para sistemas a tempo contínuo e discreto com incertezas paramétricas politópicas. São definidos limitantes inferior e superior para a norma do erro de estimação que permitem avaliar a qualidade do filtro proposto. Sua ordem é geralmente maior que a do sistema em estudo, o que contribui para melhorar o seu desempenho / Abstract: In this work, a new method to H2robust filtrer design is proposed. A convex combination of Kalman filters, calculated in each vertex of the uncertainty polytope, is used to synthesize the robust filter. For this model, the best one is calculated through a convex programming problem, expressed in terms of LMIs. Inicially a sub-class of polytopic systems is considerated and later it is widened to cope with both continuous and discrete time systems subject to polytopic parameter uncertainty. Lower and upper bounds of the estimation error norm are defined in order to evaluate the quality of the proposed filter. Its order generally is greater than the order of the plant, which contributes to reduce conservatism / Mestrado / Automação / Mestre em Engenharia Elétrica

A system for vessel characterization aimed at detecting deep vein thrombosis (DVT) in the lower limbs has been developed and evaluated using ultrasound image processing, location and force sensors measurements, blood flow information and a protocol based on the current clinical standard, compression ultrasound. The goal is to provide an objective and repeatable system to measure DVT in a rapid and standardized manner, as this has been suggested in the literature as an approach to improve overall detection of the disease. The system uses a spatial Kalman filter-based algorithm with an elliptical model in the measurement equation to detect vessel contours in transverse ultrasound images and estimate ellipse parameters, and temporal constant velocity Kalman filters for tracking vessel location in real-time. The vessel characterization also comprises building a 3-D vessel model and performing compression and blood flow assessments to calculate measures that indicate the possibility of DVT in a vessel. A user interface designed for assessing a vessel for DVT was also developed. The system and components were implemented and tested in simulations, laboratory settings, and clinical settings. Contour detection results are good, with mean and rms errors ranging from 1.47-3.64 and 3.69-9.67 pixels, respectively, in simulated and patient images, and parameter estimation errors of 5%. Experiments showed errors of 3-5 pixels for the tracking approaches. The measures for DVT were evaluated, independently and integrated in the system. The complete system was evaluated, with sensitivity of 67-100% and specificity of 50-89.5%. System learnability and memorability were evaluated in a separate user study, with good results. Contributions include a segmentation approach using a full parameter ellipse model in an extended Kalman filter, incorporating multiple measurements, an alternate sampling method for faster parameter convergence and application-specific initialization, and a tracking approach that includes a sub-sampled sum of absolutes similarity calculation and a method to detect vessel bifurcations using flow data. Further contributions include an integrated system for DVT detection that can combine ultrasound B-mode, colour flow and elastography images for vessel characterization, a system interface design focusing on usability that was evaluated with medical professionals, and system evaluations through multiple patient studies. / Applied Science, Faculty of / Electrical and Computer Engineering, Department of / Graduate

A Field Programmable Gate Array (FPGA)-based Polymorphic Faddeev Systolic Array (PolyFSA) architecture is proposed to accelerate an Extended Kalman Filter (EKF) algorithm. A system architecture comprising a software processor as the host processor, a hardware controller, a cache-based memory sub-system, and the proposed PolyFSA as co-processor, is presented. PolyFSA-based system architecture is implemented on a Xilinx Virtex 4 family of FPGAs. Results indicate significant speed-ups for the proposed architecture when compared against a space-based software processor. This dissertation proposes a comprehensive architecture analysis that is comprised of (i) error analysis, (ii) performance analysis, and (iii) area analysis. Results are presented in the form of 2-D pareto plots (area versus error, area versus time) and a 3-D plot (area versus time versus error). These plots indicate area savings obtained by varying any design constraints for the PolyFSA architecture. The proposed performance model can be reused to estimate the execution time of EKF on other conventional hardware architectures. In this dissertation, the performance of the proposed PolyFSA is compared against the performance of two conventional hardware architectures. The proposed architecture outperforms the other two in most test cases.

In this dissertation, we present generalized techniques which allow for the tracking and classification of vehicles by tracking various Point(s) of Interest (PoI) on a vehicle. Tracking the various PoI allows for the composition of those points into 3D geometries which are unique to a given vehicle type. We demonstrate this technique using passive, simulated image based sensor measurements and three separate inertial track formulations. We demonstrate the capability to classify the 3D geometries in multiple transform domains (PCA & LDA) using Minimum Euclidean Distance, Maximum Likelihood and Artificial Neural Networks. Additionally, we demonstrate the ability to fuse separate classifiers from multiple domains via Bayesian Networks to achieve ensemble classification.

No description available.

Time series analysis is a statistical technique used to analyze sequential data points collected or recorded over time. While traditional models such as autoregressive models and moving average models have performed sufficiently for time series analysis, the advent of artificial neural networks has provided models that have suggested improved performance. In this research, we provide a custom neural network; a shift encoder that can capture the intricate temporal patterns of time series data. We then compare the sparse matrix of the shift encoder to the parameters of the autoregressive model and observe the similarities. We further explore how we can replace the state matrix in a state-space model with the sparse matrix of the shift encoder.