To obtain a better understanding of the pharmacokinetic and/or pharmacodynamic characteristics of an investigated treatment, clinical data is often analysed with nonlinear mixed effects modelling. The developed models can be used to design future clinical trials or to guide individualised drug treatment. Missing data is a frequently encountered problem in analyses of clinical data, and to not venture the predictability of the developed model, it is of great importance that the method chosen to handle the missing data is adequate for its purpose. The overall aim of this thesis was to develop methods for handling missing data in the context of nonlinear mixed effects models and to compare strategies for handling missing data in order to provide guidance for efficient handling and consequences of inappropriate handling of missing data. In accordance with missing data theory, all missing data can be divided into three categories; missing completely at random (MCAR), missing at random (MAR) and missing not at random (MNAR). When data are MCAR, the underlying missing data mechanism does not depend on any observed or unobserved data; when data are MAR, the underlying missing data mechanism depends on observed data but not on unobserved data; when data are MNAR, the underlying missing data mechanism depends on the unobserved data itself. Strategies and methods for handling missing observation data and missing covariate data were evaluated. These evaluations showed that the most frequently used estimation algorithm in nonlinear mixed effects modelling (first-order conditional estimation), resulted in biased parameter estimates independent on missing data mechanism. However, expectation maximization (EM) algorithms (e.g. importance sampling) resulted in unbiased and precise parameter estimates as long as data were MCAR or MAR. When the observation data are MNAR, a proper method for handling the missing data has to be applied to obtain unbiased and precise parameter estimates, independent on estimation algorithm. The evaluation of different methods for handling missing covariate data showed that a correctly implemented multiple imputations method and full maximum likelihood modelling methods resulted in unbiased and precise parameter estimates when covariate data were MCAR or MAR. When the covariate data were MNAR, the only method resulting in unbiased and precise parameter estimates was a full maximum likelihood modelling method where an extra parameter was estimated, correcting for the unknown missing data mechanism's dependence on the missing data. This thesis presents new insight to the dynamics of missing data in nonlinear mixed effects modelling. Strategies for handling different types of missing data have been developed and compared in order to provide guidance for efficient handling and consequences of inappropriate handling of missing data.

<div>Multi-target tracking (MTT) is the problem to simultaneously estimate the number of targets and their states or trajectories. Numerous techniques have been developed for over 50 years, with a multitude of applications in many fields of study; however, there are two most widely used approaches to MTT: i) data association-based traditional algorithms; and ii) finite set statistics (FISST)-based data association free Bayesian multi-target filtering algorithms. Most data association-based traditional filters mainly use a statistical or simple model of the feature without explicitly considering the correlation between the target behavior</div><div>and feature characteristics. The inaccurate model of the feature can lead to divergence of the estimation error or the loss of a target in heavily cluttered and/or low signal-to-noise ratio environments. Furthermore, the FISST-based data association free Bayesian multi-target filters can lose estimates of targets frequently in harsh environments mainly</div><div>attributed to insufficient consideration of uncertainties not only measurement origin but also target's maneuvers.</div><div>To address these problems, three main approaches are proposed in this research work: i) new feature models (e.g., target dimensions) dependent on the target behavior</div><div>(i.e., distance between the sensor and the target, and aspect-angle between the longitudinal axis of the target and the axis of sensor line of sight); ii) new Gaussian mixture probability hypothesis density (GM-PHD) filter which explicitly considers the uncertainty in the measurement origin; and iii) new GM-PHD filter and tracker with jump Markov system models. The effectiveness of the analytical findings is demonstrated and validated with illustrative target tracking examples and real data collected from the surveillance radar.</div>

[pt] As técnicas de estimação de movimento utilizadas nos padrões de compressão de vídeo proporcionam a utilização mais eficiente dos recursos de transmissão e armazenamento, através da redução do número de bits necessários para representar um sinal de vídeo e da conservação da qualidade do conteúdo que está sendo processado. O objetivo dessa dissertação de Mestrado é propor um novo algoritmo capaz de reduzir a grande complexidade computacional envolvida nestas técnicas, mantendo a qualidade do sinal reconstruído. Dessa maneira, apresenta-se um algoritmo AUMHS (Adaptive Unsymmetrical-cross Multi-Hexagon-grid Search) o qual traz como principais modificações ao algoritmo UMHS (Unsymmetrical-cross Multi-Hexagon-grid Search) a implementação de uma medida de movimento que classifica as cenas de uma seqüência de vídeo de acordo com o movimento detectado para posterior adequação dos parâmetros de estimação de movimento e de outros parâmetros do codificador. Como resultado apresenta-se um ganho expressivo na velocidade de processamento, e conseqüente redução do custo computacional, conservando-se a qualidade obtida pelos principais algoritmos da literatura. O algoritmo foi implementado no codificador do padrão H.264/AVC onde realizou-se análises comparativas de desempenho com os algoritmos UMHS e FSA através da medição de parâmetros como PSNR (Peak Signal to Noise Ratio), tempo de processamento do codificador, tempo de processamento do módulo de estimação de movimento, taxa de bits utilizada e avaliação subjetiva informal. / [en] The motion estimation techniques used by the video compression standards provide an efficient utilization of the transmission and storage resources, through the reduction of the number of bits required to represent a video signal and the conservation of the content quality that is being processed. The objective of this work is to propose a new algorithm capable of reducing the great computational complexity involved in the motion estimation techniques, keeping the quality of the reconstructed signal. In this way, we present an algorithm called AUMHS (Adaptive Unsymmetrical-cross Multi-Hexagon-grid Search) which brings as main modifications relative to the UMHS (Unsymmetrical-cross Multi-Hexagon-grid Search) the implementation of a movement measure that can classify the scenes of a video sequence according to the motion detected for posterior adequacy of the motion estimation and others coder parameters. As result we present an expressive gain in the processing speed, and consequent computational cost reduction, conserving the same quality of the main algorithms published in the literature. The algorithm was implemented in the H.264/AVC coder in order to proceed with comparative analysis of perfomance together with the UMHS and FSA algorithms, measuring parameters as PSNR (Peak Signal you the Noise Ratio), coding processing time, motion estimation time, bit rate, and informal subjective evaluation.

Abstract The focus of this thesis is to study direction of arrival (DoA) estimation algorithms for reconfigurable leaky-wave antennas and advanced antenna arrays. Directional antennas can greatly improve the spectrum reuse, interference avoidance, and object and people localization. DoA estimation algorithms have also been shown to be useful for applications such as positioning for user tracking and location-based services in wireless local area networks (WLANs). The main goal is to develop novel DoA estimation algorithms for both advanced antenna arrays and composite right/left-handed (CRLH) leaky-wave antennas (LWAs). The thesis introduces novel modifications to existing DoA estimation algorithms and shows how these can be modified for real-time DoA estimation using both antenna types. Three modified DoA estimation algorithms for CRLH-LWAs are presented: 1) modified multiple signal classification (MUSIC), 2) power pattern cross-correlation (PPCC), and 3) adjacent power pattern ratio (APPR). Additionally, the APPR algorithm is also applied to advanced antenna arrays. The thesis also presents improvements to the modified MUSIC and APPR algorithms. The complexity of the algorithms is reduced by selecting a smaller number of received signals from different directions. The results show that the selection of the radiation patterns is very important and that the proposed algorithms can successfully estimate the DoA, even in a real-world environment. Based on the results, this thesis provides a good starting point for future research of DoA estimation algorithms to enhance the performance of future-generation wireless networks and the accuracy of localization. / Tiivistelmä Tässä väitöskirjassa tutkitaan suunnanestimointialgoritmeja uudelleen konfiguroituville vuotoaaltoantenneille (LWA, leaky wave antenna) ja kehittyneille antenniryhmille. Suuntaavilla antenneilla voidaan parantaa huomattavasti spektrin uudelleen käyttöä ja esineiden ja ihmisten sijaintipaikannusta sekä pienentää häiriöitä. Suunnanestimointialgoritmit ovat myös osoittautuneet hyödylliseksi esimerkiksi seuranta- ja sijaintipaikannuspalvelusovelluksille langattomissa lähiverkoissa. Työn päätavoite on kehittää uusia suunnanestimointialgoritmeja sekä kehittyneille antenniryhmille että vuotoaaltoantenneille (composite right/left-handed (CRLH) LWA). Työssä osoitetaan, miten olemassa olevia suunnanestimointialgoritmeja voidaan muokata uudella tavalla, jotta ne soveltuisivat molemmille antennityypeille reaaliaikaiseen suunnanestimointiin. Vuotoaaltoantennille on kehitetty kolme erilaista suunnanestimointialgoritmia: 1) muunneltu MUSIC- (multiple signal classification), 2) säteilykyvioiden tehojen ristikorrelaatio- (PPCC, power pattern cross correlation) ja 3) vierekkäisten säteilykuvioiden tehosuhdealgoritmi (APPR, adjacent power pattern ratio). APPR-algoritmia on myös käytetty kehittyneelle antenniryhmälle. Työssä esitetään myös parannuksia muunnelluille MUSIC- ja APPR-algoritmeille. Algoritmien kompleksisuutta voidaan pienentää valitsemalla vähemmän vastaanotettuja signaaleja. Tulokset osoittavat, että signaalien valinta on hyvin tärkeää ja ehdotetut algoritmit estimoivat onnistuneesti saapuvan signaalin suunnan todellisessa mittausympäristössä. Yhteenvetona voidaan sanoa, että tämä väitöstyö on hyvä lähtökohta suunnanestimointialgoritmitutkimukselle, jonka tavoitteena on parantaa tulevien sukupolvien langattomien verkkojen suorituskykyä ja paikannuksen tarkkuutta.

<div>Intelligent machines, and more broadly, intelligent systems, are becoming increasingly common in the everyday lives of humans. Nonetheless, despite significant advancements in automation, human supervision and intervention are still essential in almost all sectors, ranging from manufacturing and transportation to disaster-management and healthcare. These intelligent machines<i> interact and collaborate</i> with humans in a way that demands a greater level of trust between human and machine. While a lack of trust can lead to a human's disuse of automation, over-trust can result in a human trusting a faulty autonomous system which could have negative consequences for the human. Therefore, human trust should be <i>calibrated </i>to optimize these human-machine interactions. This calibration can be achieved by designing human-aware automation that can infer human behavior and respond accordingly in real-time.</div><div><br></div><div>In this dissertation, I present a probabilistic framework to model and calibrate a human's trust and workload dynamics during his/her interaction with an intelligent decision-aid system. More specifically, I develop multiple quantitative models of human trust, ranging from a classical state-space model to a classification model based on machine learning techniques. Both models are parameterized using data collected through human-subject experiments. Thereafter, I present a probabilistic dynamic model to capture the dynamics of human trust along with human workload. This model is used to synthesize optimal control policies aimed at improving context-specific performance objectives that vary automation transparency based on human state estimation. I also analyze the coupled interactions between human trust and workload to strengthen the model framework. Finally, I validate the optimal control policies using closed-loop human subject experiments. The proposed framework provides a foundation toward widespread design and implementation of real-time adaptive automation based on human states for use in human-machine interactions.</div>