Environ un tiers des personnes âgées vivant à domicile souffrent d'une chute chaque année. Les chutes les plus graves se produisent lorsque la personne est seule et incapable de se lever, ce qui entraîne un grand nombre de personnes âgées admis au service de gériatrique et un taux de mortalité malheureusement élevé. Le système PAL (Personally Assisted Living) apparaît comme une des solutions de ce problème. Ce système d’intelligence ambiante permet aux personnes âgées de vivre dans un environnement intelligent et pro-actif. Le travail de cette thèse s’inscrit dans le cadre de suivi des personnes âgées avec un maintien à domicile, la reconnaissance quotidienne des activités et le système automatique de détection des chutes à l'aide d'un ensemble de capteurs non intrusifs qui accorde l'intimité et le confort aux personnes âgées. En outre, une méthode de fusion tolérante aux fautes est proposée en utilisant un formalisme purement informationnel: filtre informationnel d’une part, et outils de la théorie de l’information d’autre part. Des résidus basés sur la divergence de Kullback-Leibler sont utilisés. Via un seuillage adéquat, ces résidus conduisent à la détection et à l’exclusion des défauts capteurs. Les algorithmes proposés ont été validés avec plusieurs scénarii différents contenant les différentes activités: marcher, s’asseoir, debout, se coucher et tomber. Les performances des méthodes développées ont montré une sensibilité supérieure à 94% pour la détection de chutes de personnes et plus de 92% pour la discrimination entre les différentes ADL (Activités de la vie quotidienne). / About one third of home-dwelling older people suffer a fall each year. The most painful falls occur when the person is alone and unable to get up, resulting in huge number of elders which are associated with institutionalization and high morbidity-mortality rate. The PAL (Personally Assisted Living) system appears to be one of the solutions of this problem. This ambient intelligence system allows elderly people to live in an intelligent and pro-active environment. This thesis describes the ongoing work of in-home elder tracking, activities daily living recognition, and automatic fall detection system using a set of non-intrusive sensors that grants privacy and comfort to the elders. In addition, a fault-tolerant fusion method is proposed using a purely informational formalism: information filter on the one hand, and information theory tools on the other hand. Residues based on the Kullback-Leibler divergence are used. Using an appropriate thresholding, these residues lead to the detection and the exclusion of sensors faults. The proposed algorithms were validated with many different scenarios containing the different activities: walking, sitting, standing, lying down, and falling. The performances of the developed methods showed a sensitivity of more than 94% for the fall detection of persons and more than 92% for the discrimination between the different ADLs (Activities of the daily life).

Speciation – the process by which new species arise – is of fundamental importance in the biological sciences. The means by which new species arise, and the relationship among living species, has been a topic that has captivated both lay and scientific observers for centuries. In recent years, the study of speciation has enjoyed increased attention, resulting in significant advances in our understanding of how species form. Although our understanding of the processes that contribute to speciation has increased dramatically in recent years, our knowledge of how reproductive barriers accumulate as speciation proceeds is still limited. Thus, studies that evaluate trait divergence and its consequences at early verses late stages of divergence can provide valuable insight into the speciation process. Chapter 1 of my dissertation focuses on the role of animal personality in the speciation process. Animal personality – defined as consistent individual differences in behavioral tendencies – has been identified as a key player in several ecological and evolutionary processes, yet the role of personality in speciation remains unexplored. In this chapter I discuss the ways by which personality can contribute to a suite of reproductive barriers and drive the speciation process. Chapters 2 through 5 provide a case study evaluating how selection acts on traits at early and late stages of speciation, using the Neotropical Livebearing fish genus Brachyrhaphis as a model system. Brachyrhaphis is ideally suited for this research because several species pairs and population pairs within species occur in similarly divergent selective regimes. I first present results from a field demographic study that shows that the strength of divergent selection acting on life-history traits in populations from divergent predation environments diminishes as speciation proceeds. I then show that population pairs at different stages of divergence are evolving similar morphological patterns along parallel trajectories. At both early and late stages of divergence, populations from environments with dense predator populations have a body shape that appears to be optimized for burst-speed swimming, and important component of predator escape. In contrast, populations from environments lacking predators have a body shape optimized for endurance swimming ability, which is important in environments where competition for foods and mates is high. Next, I show that populations from divergent predation environments do indeed differ in their swimming abilities according to our predictions, reflecting a population level trade-off between burst and endurance swimming ability. Although population level trade-offs were strong, I found no evidence of within population level trade-offs, suggesting that populations have arrived at novel solutions to between population trade-offs that were not present within ancestral populations. Finally, I show that these specialized swimming modes are locally adaptive, and that divergent ecology selects against immigrants, effectively reducing gene flow between populations from divergent environments. Together, these studies provide a valuable glimpse into the repeatability and predictability of trait divergence at different stages of speciation.

Model selection criteria frequently arise from constructing estimators of discrepancy measures used to assess the disparity between the data generating model and a fitted approximating model. The widely known Akaike information criterion (AIC) results from utilizing Kullback's directed divergence (KDD) as the targeted discrepancy. Under appropriate conditions, AIC serves as an asymptotically unbiased estimator of KDD. The directed divergence is an asymmetric measure of separation between two statistical models, meaning that an alternate directed divergence may be obtained by reversing the roles of the two models in the definition of the measure. The sum of the two directed divergences is Kullback's symmetric divergence (KSD). A comparison of the two directed divergences indicates an important distinction between the measures. When used to evaluate fitted approximating models that are improperly specified, the directed divergence which serves as the basis for AIC is more sensitive towards detecting overfitted models, whereas its counterpart is more sensitive towards detecting underfitted models. Since KSD combines the information in both measures, it functions as a gauge of model disparity which is arguably more balanced than either of its individual components. With this motivation, we propose three estimators of KSD for use as model selection criteria in the setting of generalized linear models: KICo, KICu, and QKIC. These statistics function as asymptotically unbiased estimators of KSD under different assumptions and frameworks. As with AIC, KICo and KICu are both justified for large-sample maximum likelihood settings; however, asymptotic unbiasedness holds under more general assumptions for KICo and KICu than for AIC. KICo serves as an asymptotically unbiased estimator of KSD in settings where the distribution of the response is misspecified. The asymptotic unbiasedness of KICu holds when the candidate model set includes underfitted models. QKIC is a modification of KICo. In the development of QKIC, the likelihood is replaced by the quasi-likelihood. QKIC can be used as a model selection tool when generalized estimating equations, a quasi-likelihood-based method, are used for parameter estimation. We examine the performance of KICo, KICu, and QKIC relative to other relevant criteria in simulation experiments. We also apply QKIC in a model selection problem for a randomized clinical trial investigating the effect of antidepressants on the temporal course of disability after stroke.

Dans cette thèse, nous proposons de nouvelles méthodes d'estimation et de test par optimisation des Divergences entre mesures pour des modèles paramétriques discrets ou continus, pour des modèles à rapport de densités semi-paramétriques et pour des modèles non paramétriques restreints par des contraintes linéaires. Les méthodes proposées sont basées sur une nouvelle représentation des Divergences entre mesures. Nous montrons que les méthodes du maximum de vraisemblance paramétrique et du maximum de vraisemblance empirique sont des cas particuliers correspondant au choix de la Divergence de Kullback-Leibler modifiée, et que le choix d'autres types de Divergences mène à des estimateurs ayant des propriétés similaires voire meilleurs dans certains cas. De nombreuses perspectives concernant le problème du choix de la Divergence sont notées.

This thesis investigates whether developments associated with globalization and regional integration have caused the levels of government support provided to agricultural producers in Canada and the United States to converge in a downward direction. The literature is sharply divided as to whether governments retain the ability to pursue an independent agricultural policy course. To shed light on this debate, the levels of government assistance payments made to farmers in six contiguous Canadian provinces and American states (Manitoba, Saskatchewan, Alberta, North Dakota, South Dakota, and Montana) are compared over the 1990-2001 period. This time-frame allows for sufficient periods both before and after the establishment of NAFTA and the WTO to study the effects of these developments on the relevant policy outcomes. After outlining the programs and policy changes that drove the shifts in levels of government support provided to farmers, the paper argues that although the levels of government payments made to farmers in the six sub-units converged in the mid-1990s, they diverged thereafter. The evidence drawn from this examination supports the contention that governments do possess considerable room to manoeuvre in the agricultural policy making arena and significant ability to chart an independent policy course.

Problems of estimating nonnegative functions from nonnegative data induced by nonnegative mappings are ubiquitous in science and engineering. We address such problems by minimizing an information-theoretic discrepancy measure, namely Csiszar's I-divergence, between the collected data and hypothetical data induced by an estimate. Our applications can be summarized along the following three lines: 1) Deautocorrelation: Deautocorrelation involves recovering a function from its autocorrelation. Deautocorrelation can be interpreted as phase retrieval in that recovering a function from its autocorrelation is equivalent to retrieving Fourier phases from just the corresponding Fourier magnitudes. Schulz and Snyder invented an minimum I-divergence algorithm for phase retrieval. We perform a numerical study concerning the convergence of their algorithm to local minima. X-ray crystallography is a method for finding the interatomic structure of a crystallized molecule. X-ray crystallography problems can be viewed as deautocorrelation problems from aliased autocorrelations, due to the periodicity of the crystal structure. We derive a modified version of the Schulz-Snyder algorithm for application to crystallography. Furthermore, we prove that our tweaked version can theoretically preserve special symmorphic group symmetries that some crystals possess. We quantify noise impact via several error metrics as the signal-to-ratio changes. Furthermore, we propose penalty methods using Good's roughness and total variation for alleviating roughness in estimates caused by noise. 2) Deautoconvolution: Deautoconvolution involves finding a function from its autoconvolution. We derive an iterative algorithm that attempts to recover a function from its autoconvolution via minimizing I-divergence. Various theoretical properties of our deautoconvolution algorithm are derived. 3) Linear inverse problems: Various linear inverse problems can be described by the Fredholm integral equation of the first kind. We address two such problems via minimum I-divergence methods, namely the inverse blackbody radiation problem, and the problem of estimating an input distribution to a communication channel (particularly Rician channels) that would create a desired output. Penalty methods are proposed for dealing with the ill-posedness of the inverse blackbody problem.

Divergence structures associated with the spectrum of precipitating systems in the subtropics and midlatitudes are not well documented. A mesoscale model (MM5) is employed to quantify the relative importance different baroclinic environments have on divergence profiles for common storm types in southeast Texas, a subtropical region. Divergence profiles averaged over a 100 x 100 nested grid with 3-km grid spacing are calculated from the model-derived wind fields for each storm. The divergence profiles simulated for selected storms are consistent with those calculated from an S-band radar using the velocity-azimuth display (VAD) technique. Divergence profiles from well-modeled storms vary in magnitude and structure across the spectrum of baroclinicities and storm types common in southeast Texas. Barotropic storms more characteristic of the Tropics generate the most elevated divergence (and thus diabatic heating) structures with the largest magnitudes. As the degree of baroclinicity increases, stratiform area fractions increase while the levels of non-divergence (LNDs) decrease. However, some weakly baroclinic storms contain stratiform area fractions and divergence profiles with magnitudes and LNDs that are similar to barotropic storms, despite having lower tropopause heights and less deep convection. Additional convection forms after the passage of some of the modeled barotropic and weakly baroclinic storms that contain elevated divergence signatures, circumstantially suggesting that heating at upper-levels may cause diabatic feedbacks that help drive regions of persistent convection in the subtropics. Applying a two-dimensional stratiform-convective separation algorithm to MM5 reflectivity data generates realistic stratiform and convective divergence signals. Stratiform regions in barotropic storms contain thicker, more elevated mid-level convergence structures with larger magnitudes than strongly baroclinic storms, while weakly baroclinic storms have LNDs that fall somewhere in between with magnitudes similar to barotropic storms. Divergence profiles within convective regions typically become more elevated as baroclinicity decreases, although variations in magnitude are less coherent. These simulations suggest that MM5 adequately captures mass field perturbations within convective and stratiform regions, the latter of which produces diabatic feedbacks capable of generating additional convection. As a result, future research determining the climatological dynamic response caused by divergence profiles in MM5 may be feasible.

Prior research has established that stocks with high dispersion of earnings forecasts or short interest are associated with low subsequent returns. Assuming dispersion of forecasts is a proxy for divergence of opinions and short interest is a proxy for short selling constraints, these results have been traditionally attributed to correction for overpricing created by binding short selling constraints. This argument is provided by Miller (1977), and states that prices reflect an optimistic view when investors with pessimistic views can not trade due to short selling constraints, and that the more opinions diverge, the more stocks become overpriced. I test whether dispersion of forecasts exacerbates overpricing, but find evidence contrary to Miller’s theory. When dispersion of forecasts increases, prices decrease. I offer an explanation based on analysts’ reluctance to quickly revise their forecasts downward. I show that some analysts’ sluggish response to bad news results in dispersion of forecasts. The inertia in downward forecast revisions also leads to market underreaction to bad news. Therefore, the negative relationship between dispersion and subsequent returns may be attributable to analysts’ sluggish response to bad news. I also examine the return predictability of firms with high short interest and low institutional ownership. Short interest seems to predict not only future stock returns but also future earnings news, especially for firms with lower institutional ownership. Therefore, the return predictability of short interest seems to be associated with value relevant information short sellers seem to have gathered.

The number of Pheasant-tailed Jacana (Hydrophasianus chirurgus) in Taiwan has been reduced and habitats decreased because of human activities in many years. From a conservation perspective, the genetic diversity of this bird became an important subject. The control region in mitochondrial DNA was used as a gene marker to investigate the genetic variation amoung populations of Hydrophasianus chirurgus from Taiwan, Goungdong, and Thailand. An 1182-bp nucleotide sequence was amplified from 34 individuals. Six variable sites and seven haplotypes were found in the control region, and the observed haplotypes were similar in all samples. Low genetic divergence and high degree of gene flow were estimated among three populations. However, this conclusion need more samples of individuals to be proved.

When a multicultural team is formed of say six individuals of different cultural backgrounds, there will be potential conflicts and greater varieties. However, there will be a ¡§normal¡¨ curve forms the range and permissible boundaries of a team. In concept, this normal distribution is the ¡§calm¡¨ state when the team is not active (norms). The potential is the range of team members¡¦ abilities/differences (divergences). To be able to reach the potential and perform is part of the team¡¦s goal (convergences & attributions). But to expect something more than expected is cultural synergy (break the original boundaries). The factors that will be considered as diverging forces are the differences that are born (already exists) when the team is formed. In order to model these cultural factors and estimate these cultural differences, Hofstede cultural dimensions are used. The factors that will be considered as converging forces are what each individual believe in such as perspective taking and self-leadership. These values are projected from the assessments of team individuals. The factors that will be considered as supporting forces (attribution factors) are how each member interacts with one another during the process. These are each individual behavior and personality. Therefore, from the perspective of divergence and convergence to see how cultural differences influence the teams and talk about their possible behaviors and reasons behind them is a conceptual way to look at the team. Based on the concept described above, the analysis of these different forces on multicultural teams is conducted. Using these factors, the paper explains/examines: l Cultural and individual values differences l Wish to base on the findings from the research to make helpful inferences on the learning and performance of multicultural teams. l Cultural divergent factors l Individual convergent factors l Individual attribution factors l Cultural synergy