Density Estimation

This article generalizes the conditional stochastic kernel developed by for multiple and more general conditioning schemes using nonparametric conditional density estimation. We utilize this methodology to analyze conditional convergence in income for Brazilian municipalities between 1970 and 1991.

Density is an important property of ionic liquids (ILs) that is required for process and product design. A recent article by Gardas and Coutinho (2008) reports the extended density correlation of ILs in wide ranges of temperature and pressure. However, they validated the density correlation only for ILs based on the following cations: imidazolium, pyridinium, pyrrolidinium, and phosphonium. The objective

Stochastic volatility modelling of financial processes has become increasingly popular. The proposed models usually contain a stationary volatility process. We will motivate and review several nonparametric methods for estimation of the density of the volatility process. Both models based on discretely sampled continuous time processes and discrete time models will be discussed.

One of the central problems in modern biology is to identify the complete set of interactions among the proteins in a cell. The structural interaction of proteins and their domains in networks is one of the most basic molecular mechanisms for biological cells. Structural evidence indicates that, interacting pairs of close homologs usually interact in the same way. In this article, we make use of both homology and inter-domain linker region knowledge to predict interaction between protein pairs solely by amino acid sequence information. High quality core set of 150 yeast proteins obtained from the Database of Interacting Proteins (DIP) was considered to test the accuracy of the proposed method. The strongest prediction of the method reached over 70% accuracy. These results show great potential for the proposed method.

... a function that is assumed to have two continuous derivatives, adding the side condition guarantees positivity and produces, uniquely, the Epanechnikov kernel. ... It will be clear from the previous paragraphs that, in the problem of noise-free density estimation, the side constraints ...

At the planning of combined heat and power (CHP)-based micro-grid, its distributed energy resources (DER) capacity is to be selected and deployed in such a way that it becomes economically self-sufficient to cater all the loads of the system without utility's participation. Economic deployment of DERs is meant to select optimal locations, optimal sizes, and optimal technologies. Optimal locations and sizes, which are independent of CHP-based DERs types, are selected, here, by loss sensitivity index (LSI) and by loss minimization using particle swarm optimization (PSO) method, respectively. In a micro-grid, both fuel costs and NO x emissions are, mainly, dependent on types of DERs used. So the main focus of the present paper is to incorporate originality in ideas to evaluate how different optimal output sets of DER-mix, operating within their respective capacity limits, could share an electrical tracking demand, economically, among micro-turbines and diesel generators of various sizes, satisfying different heat demands, on the basis of multi-objective optimization compromising between fuel cost and emission in a 4-DER 14-bus radial micro-grid. Optimization is done using differential evolution (DE) technique under real power demand equality constraint, heat balance inequality constraint, and DER capacity limits constraint. DE results are compared with PSO.

In this paper, we consider a k-nearest neighbor kernel type estimator when the random variables belong in a Riemannian manifolds. We study asymptotic properties such as the consistency and the asymptotic distribution. A simulation study is also consider to evaluate the performance of the proposal. Finally, to illustrate the potential applications of the proposed estimator, we analyzed two real example where two different manifolds are considered.

Several studies have found that the peak in bird density in the atmosphere during nocturnal migration occurs before midnight, while the peak in vocalizations from migrating birds occurs after midnight, in the hours just before dawn. In a recent study, the patterns of calling from a single species of migrating birds correlated well with the patterns of density estimates of migrating birds. We test the null hypothesis that the patterns of reflectivity measurements and number of vocalizations during nocturnal migration are not related. We sampled radar data and nocturnal flight calls during spring and fall 2000 in northwestern South Carolina and southeastern New York. We analyzed changes in the hour-to-hour patterns of bird density and vocalizations for 556 hours on 58 nights. We also analyzed the night-tonight changes in the patterns of peak hour bird density and peak hour of vocalizations on 32 nights. We found that most of the hour-to-hour and night-tonight patterns of density and vocalization counts are significantly related and reject the null hypothesis. However, despite significant relationships between reflectivity measurements and vocalization counts, a great deal of variation in vocalization counts remains unexplained. These results suggest that factors other than bird density are responsible for the variation in vocalizing by migrating birds.

Sampling efficiency of two oyster fishing gears, patent tongs and an oyster dredge, were compared in reference to diver-harvested quadrats in Chesapeake Bay, which supports im portant harvests of eastem oyster Crassosrrea virginica. Mean densities ofspat (0$35 mm), small oysters (>35 mm to 75 mm), marketable oysterS (>75 mm), and all oysters (three size-groups combined) estimated from patent tong samples were not significantly different from those derived from diver-harvested quadrat samples. In contrast, the densities estimated from dredge samples were low, only 2-32% of the diver estimates. Accordingly, patent tongs are reeommended as the sampling gear for estimating eastem oyster stock abundance in the Maryland portion of Chesapeake Bay.

A Spatio-Temporal Analysis of Dolphinfish; Coryphaena (August 2008) Hippurus, Abundance in the Western Atlantic: Implications for Stock Assessment of a Data-Limited Pelagic Resource. Abstract of a dissertation at the University of Miami. Dissertation supervised by Professor David Die. No. of pages in text. (331) Dolphinfish (Coryphaena hippurus) is a pelagic species that is ecologically and commercially important in the western Atlantic region. This species has been linked to dominant oceanographic features such as sea surface temperature (SST) frontal regions.

We estimated carrying capacity for sea otters (Enhydra lutris) in the coastal waters of British Columbia, Canada, by characterizing habitat according to the complexity of nearshore intertidal and sub-tidal contours. We modeled the total area of complex habitat on the west coast of Vancouver Island by first calculating the complexity of the Checleset Bay-Kyuquot Sound (CB-KS) region, where sea otters have been at equilibrium since the mid-1990s. We then identified similarly complex areas on the west coast of Vancouver Island (WCVI model), and adapted the model to identify areas of similar complexity along the entire British Columbia coast (BC model). Using survey data from the CB-KS region, we calculated otter densities for the habitat predicted by the 2 models. The density estimates for CB-KS were 3.93 otters/km 2 and 2.53 otters/km 2 for the WCVI and BC models, respectively, and the resulting 2 estimates of west coast of Vancouver Island complex habitat carrying capacity were not significantly different (WCVI model: 5,123, 95% CI ¼ 3,337-7,104; BC model: 4,883, 95% CI ¼ 3,223-6,832). The BC model identified the region presently occupied by otters on the central British Columbia coast, but the amount of coast-wide habitat it predicted (5,862 km 2 ) was relatively small, and the associated carrying capacity estimate (14,831, 95% CI ¼ 9,790-20,751) was low compared to historical accounts. We suggest that our model captured a type of high-quality or optimum habitat prevalent on the west coast of Vancouver Island, typified by the CB-KS region, and that suitable sea otter habitat elsewhere on the coast must include other habitat characteristics. We therefore calculated a linear, coast-wide carrying capacity of 52,459 sea otters (95% CI ¼ 34,264-73,489)-a more realistic upper limit to sea otters in British Columbia. Our carrying capacity estimates are helping set population recovery targets for sea otters in Canada, and our habitat predictions represent a first step in Critical Habitat identification. This habitat-based approach to estimating carrying capacity is likely suitable for other nonmigratory, density-dependent species.

This paper introduces a new stochastic process, a collection of U-statis-tics indexed by a family of symmetric kemels. Conditions are found for the uniform almost-sure convergence of a sequence of such processes. Rates of convergence are obtained. An application to cross-validation ...

With the rapid development of automated visual analysis, visual analysis systems have become a popular research topic in the field of computer vision and automated analysis. Visual analysis systems can assist humans to detect anomalous events (e.g., fighting, walking alone on the grass, etc). In general, the existing methods for visual anomaly detection are usually based on an autoencoder architecture, i.e., reconstructing the current frame or predicting the future frame. Then, the reconstruction error is adopted as the evaluation metric to identify whether an input is abnormal or not. The flaws of the existing methods are that abnormal samples can also be reconstructed well. In this paper, inspired by the human memory ability, we propose a novel deep neural network (DNN) based model termed cognitive memory-augmented network (CMAN) for the visual anomaly detection problem. The proposed CMAN model assumes that the visual analysis system imitates humans to remember normal samples and then distinguishes abnormal events from the collected videos. Specifically, in the proposed CMAN model, we introduce a memory module that is able to simulate the memory capacity of humans and a density estimation network that can learn the data distribution. The reconstruction errors and the novelty scores are used to distinguish abnormal events from videos. In addition, we develop a two-step scheme to train the proposed model so that the proposed memory module and the density estimation network can cooperate to improve performance. Comprehensive experiments evaluated on various popular benchmarks show the superiority and effectiveness of the proposed CMAN model for visual anomaly detection comparing with the state-of-the-arts methods. The implementation code of our CMAN method can be accessed at https://github.com/CMAN-code/CMAN_pytorch.

We present a new non-uniform sampling method for the accurate estimation of mutual information in multi-modal brain image rigid registration. Most existing density estimators used for mutual information computation incorrectly assume that the intensity of each voxel is independent from its neighborhood. Our method uses the 3D Fast Discrete Curvelet Transform to reduce the sampled voxels' interdependency by sampling voxels that are less dependent on their neighborhood, and thus provide a more accurate estimation of the mutual information and a more accurate registration. The main advantages of our method over other non-uniform sampling schemes are that: (1) it provides more accurate estimation of the image statistics with fewer samples; (2) it is less sensitive to the variability of anatomical structures shapes, orientations, and sizes, and; (3) it yields more accurate registration results. Extensive evaluation on 1000 synthetic registrations between T1 and T2-weighted clinical MRI images and 20 real clinical registrations of brain CT images to Proton Density (PD) and T1 and T2-weighted MRI images from the public RIRE database show the effectiveness of our method. Our method has the lowest mean registration errors recorded to date for CT-MR image registration in the RIRE website for methods tested on more than five datasets. These results indicate that our sampling scheme can be used to achieve more accurate multi-modal registration required for image guided therapy and surgery.

We analyze the computer vision task of pixel-level background subtraction. We present recursive equations that are used to constantly update the parameters of a Gaussian mixture model and to simultaneously select the appropriate number of components for each pixel. We also present a simple non-parametric adaptive density estimation method. The two methods are compared with each other and with some previously proposed algorithms.

Aim: Reliable estimates of population density are fundamental to wildlife conservation and management. Although the leopard cat is the most common and widespread wild felid in China, little is known about the ecology and population biology of this species in the country. Using spatially explicit capture-recapture (SERC) modelling derived from extensive camera-trapping data, we estimated the population density and activity patterns of leopard cats in a well-protected private nature reserve in southern China.

Methods: Between June 2020 and May 2021, we conducted a camera-trap survey across a pre-determined grid system in Kadoorie Farm and Botanic Garden (KFBG), Hong Kong. KFBG was established on a barren hillside following sustained anthropogenic disturbances. After six decades of protection, secondary forest currently covers approximately 80% of the site. We deployed a total of 19 camera trap stations across our small 1.5 km2 study area, with two opposite-facing cameras at each station to obtain images of both flanks of leopard cats. The consecutive 12-month survey yielded 113 independent capture events of the leopard cat, of which 61 events were clear enough to facilitate individual identification. Based on closed population assumptions for capture-recapture models, we also divided the 12-month survey into six two-month sampling periods, and estimated the population density for each sampling period using Maximum Likelihood SECR modelling. We also examined activity kernel densities to estimate the difference in diel activity patterns between wet and dry seasons.

Results: Our analyses revealed that results from two sampling periods were robust and precise enough (i.e., low standard error and narrow 95% confidence intervals) to estimate leopard cat density. We estimated leopard density between June-July 2020 as D = 0.64 ± 0.31 (0.26–1.55) individuals/km2, and between February-March 2021 as D = 0.87 ± 0.48 (0.31–2.40) individuals/km2, which are among the highest density estimates for this species reported in any region. We also found that the diel activity pattern of leopard cats in the study site is arrhythmic during the wet season, but became more nocturnal-crepuscular during the dry season, though they also exhibited some diurnal activity. Kernel density analyses however suggested no significant differences in diel activity patterns occurred between wet and dry seasons. 

Conclusions: Our study provides important early data on the population density of leopard cats in southern mainland China, the results of which allow for comparisons with other studies elsewhere using capture-recapture modelling approaches. We further demonstrate the utility of SECR methods for estimating population density over short and long sampling periods across necessarily small sampling areas. We further provide practical recommendations for conducting camera trap surveys to enhance the success rates of individual identification and “recapture” of leopard cats. In accordance with the conclusion of other studies, our results show that leopard cats are highly adaptable, exhibit great plasticity in daily activity, and thrive well in human-modified landscapes.

Underwater visual censuses are the most commonly used methods to estimate the density of reef fish populations and assemblages. One basic assumption is that the observer will always detect fish in the same way from one sampling unit to the next, implying that, on average, the spatial distribution pattern of fish abundance or occurrence remains the same from one transect to the next (H 0 ). The present work tested H 0 using data from 730 transects covering two regions (New Caledonia and French Polynesia), 604 species and 504 000 fish. Within transect variations in reef fish abundance and occurrence were studied according to site factors (region, reef type), life-history traits (adult size, home range, schooling behaviour, color, pattern, swimming speed, level in the water column, inquisitiveness, crypticity), and observations characteristics (distance of observation, size of the observed fishes, number of fishes within an observation, observer identity). Two general trends were detected: 1at the start of transects, both fish occurrence and abundance were higher than the values expected under H 0 ; 2a similar trend was also observed at the end of transects, but at a much lower magnitude. These effects were observed with varying degrees of magnitude for all regions, reef types and observers, varied significantly according to three life-history traits (size, home range, and behaviour), but were not influenced by species richness or abundance. These results indicate that datasets gathered from transects of various lengths cannot be pooled without correction. They also shed light on some of the known differences between transects and point counts.

We describe a technique for comparing distributions without the need for density estimation as an intermediate step. Our approach relies on mapping the distributions into a reproducing kernel Hilbert space. Applications of this technique can be found in two-sample tests, which are used for determining whether two sets of observations arise from the same distribution, covariate shift correction, local learning, measures of independence, and density estimation.

1. Distance sampling is a widely used technique for estimating the size or density of biological populations. Many distance sampling designs and most analyses use the software Distance. 2. We briefly review distance sampling and its assumptions, outline the history, structure and capabilities of Distance, and provide hints on its use. 3. Good survey design is a crucial prerequisite for obtaining reliable results. Distance has a survey design engine, with a built-in geographic information system, that allows properties of different proposed designs to be examined via simulation, and survey plans to be generated. 4. A first step in analysis of distance sampling data is modelling the probability of detection. Distance contains three increasingly sophisticated analysis engines for this: conventional distance sampling, which models detection probability as a function of distance from the transect and assumes all objects at zero distance are detected; multiple-covariate distance sampling, which allows covariates in addition to distance; and mark-recapture distance sampling, which relaxes the assumption of certain detection at zero distance. 5. All three engines allow estimation of density or abundance, stratified if required, with associated measures of precision calculated either analytically or via the bootstrap. 6. Advanced analysis topics covered include the use of multipliers to allow analysis of indirect surveys (such as dung or nest surveys), the density surface modelling analysis engine for spatial and habitat modelling, and information about accessing the analysis engines directly from other software. 7. Synthesis and applications. Distance sampling is a key method for producing abundance and density estimates in challenging field conditions. The theory underlying the methods continues to expand to cope with realistic estimation situations. In step with theoretical developments, stateof-the-art software that implements these methods is described that makes the methods accessible to practising ecologists.

A Spatio-Temporal Analysis of Dolphinfish; Coryphaena (August 2008) Hippurus, Abundance in the Western Atlantic: Implications for Stock Assessment of a Data-Limited Pelagic Resource. Abstract of a dissertation at the University of Miami. Dissertation supervised by Professor David Die. No. of pages in text. (331) Dolphinfish (Coryphaena hippurus) is a pelagic species that is ecologically and commercially important in the western Atlantic region. This species has been linked to dominant oceanographic features such as sea surface temperature (SST) frontal regions.

We review the current state of nonparametric Bayesian inference. The discussion follows a list of important statistical inference problems, including density estimation, regression, survival analysis, hierarchical models and model validation. For each inference problem we review relevant nonparametric Bayesian models and approaches including Dirichlet process (DP) models and variations, Pólya trees, wavelet based models, neural network models, spline regression, CART, dependent DP models and model validation with DP and Pólya tree extensions of parametric models.

Excel spreadsheet FYSCONST#2.0.xls calculates the physical food properties Density, Thermal Conductivity, Specific Heat, and Thermal Diffusivity, of an unfrozen or a (partly) frozen food.
Required input: the food product composition in mass% of protein, mass% of fat, mass% of carbohydrates, mass% of fiber, mass% of ash, mass% of unfrozen water and mass% of ice; also the actual food temperature has to be supplied.
For (partly) frozen foods, a separate spreadsheet section calculates the mass% of both ice and unfrozen water, based on composition and initial freezing point, by applying the TCHIGEOV equation. For many foods, table 3 lists this initial freezing point, together with the mass% of the main food components.
All equations used in FYSCONST#2.0.xls, and their sources, are presented.
On validation, the physical food properties, calculated by FYSCONST#2.0.xls, were (almost) exactly equal to those of food products, reported by Ibarz & Barbosa-Cánovas (2005: 319-320), by R. Paul Singh in Heldman & Lund (1992: 253), and by ASHRAE (2006: 9-6).
6 extensively worked examples explain how to use both the spreadsheets FYSCONS#2.0.xls, and the  Tchigeov equation.

The ISO 9001 (2000) define "Quality" as the ability of a set of inherent properties and characteristics of a product, system or process to fulfill requirements of customers and other interested parties. The "Plan de Calidad de Obra (PCO)" is an instrument that follows to get the necessary quality in Civil Works contracts. Graphical documentation generated during construction project elaboration or even during Civil Engineering works execution with planes, makes obligatory a meticulous treatment of this information that results transcendental in the consecution of the definitive products (projects or works) quality objective. In this work it's shown the principal graphical documentation procedures defined in the PCO attending to the edition, modification, distribution, storage, and other relevant aspects related to graphical information.

We consider the asymptotic behavior of posterior distributions and Bayes estimators based on observations which are required to be neither independent nor identically distributed. We give general results on the rate of convergence of the posterior measure relative to distances derived from a testing criterion. We then specialize our results to independent, nonidentically distributed observations, Markov processes, stationary Gaussian time series and the white noise model. We apply our general results to several examples of infinite-dimensional statistical models including nonparametric regression with normal errors, binary regression, Poisson regression, an interval censoring model, Whittle estimation of the spectral density of a time series and a nonlinear autoregressive model. POSTERIOR CONVERGENCE RATES 193 dressed by Amewou-Atisso, Ghosal, Ghosh and Ramamoorthi [1] and Choudhuri, Ghosal and Roy . The main purpose of the present paper is to obtain a theorem on rates of convergence of posterior distributions in a general framework not restricted to the setup of i.i.d. observations. We specialize this theorem to several classes of non-i.i.d. models including i.n.i.d. observations, Gaussian time series, Markov processes and the white noise model. The theorem applies in every situation where it is possible to test the true parameter versus balls of alternatives with exponential error probabilities and it is not restricted to any particular structure on the joint distribution. The existence of such tests has been proven in many special cases by Le Cam and Birgé , who used them to construct estimators with optimal rates of convergence, determined by the (local) metric entropy or "Le Cam dimension" of the model. Our main theorem uses the same metric entropy measure of the complexity of the model and combines this with a measure of prior concentration around the true parameter to obtain a bound on the posterior rate of convergence, generalizing the corresponding result of Ghosal, Ghosh and van der Vaart . We apply these results to obtain posterior convergence rates for linear regression, nonparametric regression, binary regression, Poisson regression, interval censoring, spectral density estimation and nonlinear autoregression. van der Meulen, van der Vaart and van Zanten have extended the approach of this paper to several types of diffusion models.

Data analysis sometimes requires the relaxation of parametric assumptions in order to gain modeling flexibility and robustness against mis-specification of the probability model. In the Bayesian context, this is accomplished by placing a prior distribution on a function space, such as the space of all probability distributions or the space of all regression functions. Unfortunately, posterior distributions ranging over function spaces are highly complex and hence sampling methods play a key role. This paper provides an introduction to a simple, yet comprehensive, set of programs for the implementation of some Bayesian nonparametric and semiparametric models in R, DPpackage. Currently, DPpackage includes models for marginal and conditional density estimation, receiver operating characteristic curve analysis, interval-censored data, binary regression data, item response data, longitudinal and clustered data using generalized linear mixed models, and regression data using generalized additive models. The package also contains functions to compute pseudo-Bayes factors for model comparison and for eliciting the precision parameter of the Dirichlet process prior, and a general purpose Metropolis sampling algorithm. To maximize computational efficiency, the actual sampling for each model is carried out using compiled C, C++ or Fortran code.

In many modern experimental settings, observations are obtained in the form of functions, and interest focuses on inferences on a collection of such functions. Some examples are conductivitytemperature-depth (CTD) data in oceanography, dose-response models in epidemiology and time-course microarray experiments in biology and medicine. In this paper we propose a hierarchical model that allows us to simultaneously estimate multiple curves nonparametrically by using dependent Dirichlet Process mixtures of Gaussians to characterize the joint distribution of predictors and outcomes. Function estimates are then induced through the conditional distribution of the outcome given the predictors. The resulting approach allows for flexible estimation and clustering, while borrowing information across curves. We also show that the function estimates we obtain are consistent on the space of integrable functions. As an illustration, we consider an application to the analysis of CTD data in the north Atlantic.

(EN ESPAÑOL): En este trabajo detallamos el procedimiento metodológico para la realización de mapas que nos permitan analizar la evolución de la densidad del poblamiento antiguo en un territorio. Nos centraremos concretamente en el cálculo basado en la estimación de la densidad de núcleo (KDE). En este tipo de análisis es muy importante seleccionar un ancho de banda (h) óptimo, para cuyo cálculo existen dos estrategias: una que baraja criterios cualitativos y otra centrada en procedimientos cuantitativos. Tras valorar los pros y los contras de cada una de estas estrategias, proponemos una tercera opción que consiste en combinar ambos criterios. Para ejemplificar esta propuesta metodológica hemos tomado como caso de estudio varias zonas del Bajo Guadalquivir (SO de
España) en las que se han documentado yacimientos arqueológicos datados entre los siglos II y IV d.C.

(IN ENGLISH): In this paper we reflect on the different concepts and issues required to make density maps that allow the ancient settlements in a territory to be studied. We will focus on the kernel density estimation (KDE). In this
type of analysis, it is important to select an optimum bandwidth (h) and there are two strategies for this purpose: one that considers qualitative criteria and another that focuses on quantitative criteria. After evaluating each of these strategies, we propose a third option that consists of combining both criteria. Following a series of statistical calculations, a minimum and maximum value can be determined for the bandwidth, using this interval as a qualitative testing range. To exemplify this methodological proposal with a practical case, a series of density maps have been drawn up based on the known Roman sites in the Lower Guadalquivir Basin (SW Spain) between the 2nd and 4th centuries AD.

-Un problème inverse de conduction de la chaleur non linéaire est résolu en utilisant une formulation du filtre de Kalman basée sur une approche statistique et étendue aux systèmes non linéaires. L'évolution temporelle d'une densité de flux de chaleur surfacique a été reconstruite à partir d'une simulation numérique qui nous a permis d'étudier l'influence de certains paramètres qui conditionnent le fonctionnement du filtre sur le résultat de l'estimation. Un choix convenable de ces paramètres, guidé par l'observation du comportement du filtre, conduit à une solution qui demeure stable en présence de données bruitées mais qui est légèrement déphasée par rapport à la fonction exacte. Ce déphasage dépend notamment de la localisation de la mesure de la température interne nécessaire pour l'inversion et de l'erreur sur le modèle associée à la représentation de la densité de flux de chaleur par une fonction constante par morceaux. L'application du filtre de Kalman étendu avec des mesures de températures réelles enregistrées à partir d'un dispositif expérimental a montré que cette technique s'adapte parfaitement au caractère aléatoire des erreurs de mesure. Les résultats obtenus sont validés avec la méthode inverse de retour à la surface proposée par Raynaud et Bransier et sont en bon accord avec la densité de flux de chaleur estimée avec cette deuxième méthode. © 2000 Éditions scientifiques et médicales Elsevier SAS problème inverse non linéaire / conduction de chaleur / filtre de Kalman étendu / estimation / simulation numérique / dispositif expérimental Abstract-An extended version of the discrete Kalman filter applied to a nonlinear inverse heat conduction problem. A nonlinear inverse heat conduction problem is resolved by using a formulation of the Kalman filter based on a statistical approach and extended to nonlinear systems. The time evolution of a surface heat flux density is reconstructed from a numerical simulation which allowed us to analyse the influence of some parameters, that condition the running of the filter, on the estimation result. A suitable choice of these parameters, guided by the filter behaviour observations, leads to a solution that remains stable when using noisy data, but that is slightly time-lagged compared to the exact function. This time-lag depends on the location of the interior temperature measurement needed for the inversion and on the model error caused by the approximation of the heat flux with a piece-wise constant function. The application of the extended Kalman filter with real measurements recorded from an experimental setup , shows that this technique fits the stochastic structure of experimental measurements. The provided results are validated by using the Raynaud's and Bransier's inverse method and are in good agreement with the heat flux density estimated with this method.

The electrical networks are receiving more deployments of Distributed Energy Resources (DERs). In order to control the impact of DERs on existing networks, it is proposed to divide them into more manageable smaller sets which are called 'microgrids'. Unlike conventional utility grids, microgrids include generators, storage devices and loads at all levels of the system. Power generation, distribution and consumption levels are not discrete and power flow may occur at any direction. At any point in time, the microgrid may become isolated from the utility grid and continue its operation under islanding conditions. Furthermore, some microgrids may have changing structures with alternative paths and the coupling point for a device or a part of the microgrid may change due to the altering conditions.

The aim of this thesis is to investigate the applicability of a novel image synthesis technique based on Monte Carlo particle transport to daylight simulation. Many materials used in daylight simulation are specifically designed to redirect light, and as such give rise to complex effects such as caustics. The photon map technique was chosen for its efficent handling of these effects. To assess its ability to produce physically correct results which can be applied to lighting simulation, a validation was carried out based on analytical case studies and on simple experimental setups. As prerequisite to validation, the photon map´s inherent bias/noise tradeoff is investigated. This tradeoff depends on the density estimate bandwidth used in the reconstruction of the illumination. The error analysis leads to the development of a bias compensating operator which adapts the bandwidth according to the estimated bias in the reconstructed illumination.

We consider the model Zi = Xi + εi, for i.i.d. Xi's and εi's and independent sequences (Xi) i∈N and (εi) i∈N . The density fε of ε1 is assumed to be known, whereas the one of X1, denoted by g, is unknown. Our aim is to estimate linear functionals of g, ψ, g for a known function ψ. We propose a general estimator of ψ, g and study the rate of convergence of its quadratic risk as a function of the smoothness of g, fε and ψ. Different contexts with dependent data, such as stochastic volatility and AutoRegressive Conditionally Heteroskedastic models, are also considered. An estimator which is adaptive to the smoothness of unknown g is then proposed, following a method studied by Laurent et al. (Preprint (2006)) in the Gaussian white noise model. We give upper bounds and asymptotic lower bounds of the quadratic risk of this estimator. The results are applied to adaptive pointwise deconvolution, in which context losses in the adaptive rates are shown to be optimal in the minimax sense. They are also applied in the context of the stochastic volatility model.

We consider nonparametric estimation of an object such as a probability density or a regression function. Can such an estimator achieve the minimax rate of convergence on suitable function spaces, while, at the same time, when "plugged-in", estimate efficiently (at a rate of n −1/2 with the best constant) many functionals of the object? For example, can we have a density estimator whose definite integrals are efficient estimators of the cumulative distribution function? We show that this is impossible for very large sets, e.g., expectations of all functions bounded by M < ∞.

A significant increase in photovoltaic (PV) system installations is expected to come on line in the near future and as the penetration level of PV increases, the effect of PV may no longer be considered minimal. One of the most important attributions of additional PV is what effect this may have on protection systems. Protection engineers design protection systems to safely eliminate faults from the electric power system. One of the new technologies recently introduced into the electric power system are distributed energy resources (DER). Currently, inverterbased DER contributes very little to the power balance on all but a few utility distribution systems. As DER become prevalent in the distribution system, equipment rating capability and coordination of protection systems merit a closer investigation.

A new procedure is proposed for deriving variable bandwidths in univariate kernel density estimation, based upon likelihood cross-validation and an analysis of a Bayesian graphical model. The procedure admits bandwidth selection which is flexible in terms of the amount of smoothing required. In addition, the basic model can be extended to incorporate local smoothing of the density estimate. The method is shown to perform well in both theoretical and practical situations, and we compare our method with those of Abramson (The Annals of Statistics 10: 1217-1223) and Sain and Scott (Journal of the American Statistical Association 91: 1525-1534). In particular, we note that in certain cases, the Sain and Scott method performs poorly even with relatively large sample sizes. We compare various bandwidth selection methods using standard mean integrated square error criteria to assess the quality of the density estimates. We study situations where the underlying density is assumed both known and unknown, and note that in practice, our method performs well when sample sizes are small. In addition, we also apply the methods to real data, and again we believe our methods perform at least as well as existing methods.

A four parameter generalization of the Weibull distribution capable of modeling a bathtubshaped hazard rate function is defined and studied. The beauty and importance of this distribution lies in its ability to model monotone as well as non-monotone failure rates, which are quite common in lifetime problems and reliability. The new distribution has a number of well-known lifetime special sub-models, such as the Weibull, extreme value, exponentiated Weibull, generalized Rayleigh and modified Weibull distributions, among others. We derive two infinite sum representations for its moments. The density of the order statistics is obtained. The method of maximum likelihood is used for estimating the model parameters. Also, the observed information matrix is obtained. Two applications are presented to illustrate the proposed distribution.

Metapopulation approach to assess survival of Oncifelis guigna in fragmented forests of central Chile: A theoretical model. Aproximación metapoblacional para determinar la sobrevivencia de Oncifelis guigna en bosques fragmentados de Chile central: un modelo teórico _______________________ 217 GENOWAYS, H.H. and R.M. TIMM. The Xenarthrans of Nicaragua. Los Xenarthra de Nicaragua _____________________________________________________________________________ 231 GRAIPEL, M.E.; P.R.M. MILLER e L. GLOCK. Padrão de atividade de Akodon montensis e Oryzomys russatus na reserva Volta Velha, Santa Catarina, sul do Brasil. Activity patterns of Akodon montensis and Oryzomys russatus in Volta Velha Reserve, Santa Catarina, southern Brazil ____ 255 JARAMILLO FAYAD, J.C.; J. PÉREZ TORRES y D.M. SARMIENTO. Cambios del comportamiento como respuesta a la supresión de alimento suplementario en una población semicautiva de Saimiri sciureus (mono ardilla). Behavioral changes as a response to artificial food reduction in a semicaptive population of Saimiri sciureus (squirrel monkey) ________________________________ 261 MERINO, M.L. and B.N. CARPINETTI. Feral pig Sus scrofa population estimates in Bahía Samborombón Conservation Area, Buenos Aires province, Argentina. Estimación poblacional del chancho cimarrón Sus scrofa en el Área de Conservación Bahía Samborombón, provincia de Buenos Aires, Argentina ______________________________________________________________________________ 269 TRAVAINI, A.; J. PEREIRA, R. MARTÍNEZ-PECK y S.C. ZAPATA. Monitoreo de zorros colorados (Pseudalopex culpaeus) y grises (Pseudalopex griseus) en Patagonia: diseño y comparación de dos métodos alternativos. Monitoring Culpeo (Pseudalopex culpaeus) and Gray foxes (Pseudalopex griseus) in Patagonia: Design and comparison between two alternative methods ______________ 277 UBILLA, M. and A. RINDERKNECHT. A Late Miocene Dolichotinae (Mammalia, Rodentia, Caviidae) from Uruguay, with comments about the relationships of some related fossil species. Un Dolichotinae (Mammalia, Rodentia, Caviidae) del Mioceno tardío de Uruguay, con comentario sobre las afinidades de especies fósiles relacionadas ________________________________________________ 293 VELAZCO, P.M. y S. SOLARI. Taxonomía de Platyrrhinus dorsalis y Platyrrhinus lineatus (Chiroptera: Phyllostomidae) en Perú. Taxonomy of Platyrrhinus dorsalis and Platyrrhinus lineatus (Chiroptera: Phyllostomidae) in Peru ________________________________________________________________ 303 DISTRIBUCIÓN, HISTORIA NATURAL Y CONSERVACIÓN DE MAMÍFEROS NEOTROPICALES / DISTRIBUTION, NATURAL HISTORY, AND CONSERVATION OF NEOTROPICAL MAMMALS JEREZ, S. DEL V. y M. HALLOY. El oso hormiguero, Myrmecophaga tridactyla: crecimiento e independización de una cría. The anteater, Myrmecophaga tridactyla: Growth and independization of an infant ___________________________________________________________________________ 323 KALCOUNIS-RÜPPELL, M.C.; T.J. BROWN, P.T. HANDFORD, and R.A. OJEDA. Preliminary notes on bat activity and echolocation in Northwestern Argentina. Notas preliminares sobre actividad y ecolocación en murciélagos del Noroeste argentino ______________________________________ 331 RESÚMENES DE TESIS -DISSERTATION ABSTRACTS PROVENSAL, M.C. Age and density in the population regulation of Calomys vensuta (Rodentia: Muridae) ______________________________________________________________________________ 341 VARGAS CADEMARTORI, C. Reproductive biology and daily and seasonal abundance patterns of Delomys dorsalis (Hensel, 1872) -Cricetidae, Sigmodontinae-in an area of mixed forest with conifers, Rio Grande do Sul State. Brazil __________________________________________________ 342

We formulate conditions for convergence of Laws of Large Numbers and show its links with of parts mathematical analysis such as summation theory, convergence of orthogonal series. We present also applications of Law of Large Numbers such as Stochastic Approximation, Density and Regression Estimation, Identification.