Number of results to display per page
Search Results
2852. Bayesian estimation of mixtures with dynamic transitions and known component parameters
- Creator:
- Ivan, Suzdaleva, Evgenia, and Kárný, Miroslav
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- mixture model, Bayesian estimation, approximation, clustering, and classification
- Language:
- English
- Description:
- Probabilistic mixtures provide flexible "universal'' approximation of probability density functions. Their wide use is enabled by the availability of a range of efficient estimation algorithms. Among them, quasi-Bayesian estimation plays a prominent role as it runs "naturally'' in one-pass mode. This is important in on-line applications and/or extensive databases. It even copes with dynamic nature of components forming the mixture. However, the quasi-Bayesian estimation relies on mixing via constant component weights. Thus, mixtures with dynamic components and dynamic transitions between them are not supported. The present paper fills this gap. For the sake of simplicity and to give a better insight into the task, the paper considers mixtures with known components. A general case with unknown components will be presented soon.
- Rights:
- http://creativecommons.org/publicdomain/mark/1.0/ and policy:public
2853. Bayesian estimation of the hydraulic and solute transport properties of a small-scale unsaturated soil column
- Creator:
- Moreira, Paulo H. S., van Genuchte, Martinus Th., Orlande, Helcio R. B., and Cotta, Renato M.
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- Markov Chain Monte Carlo method, Metropolis-Hastings algorithm, hydraulic parameters, transport parameters, and soil column experiment
- Language:
- Slovak
- Description:
- In this study the hydraulic and solute transport properties of an unsaturated soil were estimated simultaneously from a relatively simple small-scale laboratory column infiltration/outflow experiment. As governing equations we used the Richards equation for variably saturated flow and a physical non-equilibrium dual-porosity type formulation for solute transport. A Bayesian parameter estimation approach was used in which the unknown parameters were estimated with the Markov Chain Monte Carlo (MCMC) method through implementation of the Metropolis-Hastings algorithm. Sensitivity coefficients were examined in order to determine the most meaningful measurements for identifying the unknown hydraulic and transport parameters. Results obtained using the measured pressure head and solute concentration data collected during the unsaturated soil column experiment revealed the robustness of the proposed approach.
- Rights:
- http://creativecommons.org/licenses/by-nc-sa/4.0/ and policy:public
2854. Bayesian nonparametric estimation of hazard rate in monotone Aalen model
- Creator:
- Timková, Jana
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- monotone Aalen model, Bayesian estimation, Gibbs sampler, and small sampler size
- Language:
- English
- Description:
- This text describes a method of estimating the hazard rate of survival data following monotone Aalen regression model. The proposed approach is based on techniques which were introduced by Arjas and Gasbarra \cite{gasbarra}. The unknown functional parameters are assumed to be a priori piecewise constant on intervals of varying count and size. The estimates are obtained with the aid of the Gibbs sampler and its variants. The performance of the method is explored by simulations. The results indicate that the method is applicable on small sample size datasets.
- Rights:
- http://creativecommons.org/publicdomain/mark/1.0/ and policy:public
2855. Bayesian reference analysis for proportional hazards model of random censorship with Weibull distribution
- Creator:
- Ajmal, Maria, Danish, Muhammad Yameen, and Tahira, Ayesha
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- Jeffreys prior method, reference prior method, random censorship model, Kaplan-Meier survival estimate, and Henze goodness-of-fit test
- Language:
- English
- Description:
- This article deals with the objective Bayesian analysis of random censorship model with informative censoring using Weibull distribution. The objective Bayesian analysis has a long history from Bayes and Laplace through Jeffreys and is reaching the level of sophistication gradually. The reference prior method of Bernardo is a nice attempt in this direction. The reference prior method is based on the Kullback-Leibler divergence between the prior and the corresponding posterior distribution and easy to implement when the information matrix exists in closed-form. We apply this method to Weibull random censorship model and compare it with Jeffreys and maximum likelihood methods. It is observed that the closed-form expressions for the Bayes estimators are not possible; we use importance sampling technique to obtain the approximate Bayes estimates. The behaviour of maximum likelihood and Bayes estimators is observed via extensive numerical simulation. The proposed methodology is used for the analysis of a real-life data for illustration and appropriateness of the model is tested by Henze goodness-of-fit test.
- Rights:
- http://creativecommons.org/licenses/by-nc-sa/4.0/ and policy:public
2856. Bayesian stopping rule in discrete parameter space with multiple local maxima
- Creator:
- Kárný, Miroslav
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- Bayesian estimation, global maximum, and model structure
- Language:
- English
- Description:
- The paper presents the stopping rule for random search for Bayesian model-structure estimation by maximising the likelihood function. The inspected maximisation uses random restarts to cope with local maxima in discrete space. The stopping rule, suitable for any maximisation of this type, exploits the probability of finding global maximum implied by the number of local maxima already found. It stops the search when this probability crosses a given threshold. The inspected case represents an important example of the search in a huge space of hypotheses so common in artificial intelligence, machine learning and computer science.
- Rights:
- http://creativecommons.org/publicdomain/mark/1.0/ and policy:public
2857. Bayesian Ying-Yang learning on orthogonal binary factor analysis
- Creator:
- Sun , Ke and Xu, Lei
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- Binary factor analysis, model selection, and Bayesian Ying-Yang learning
- Language:
- English
- Description:
- Binary Factor Analysis (BFA) aims to discover latent binary structures in high dimensional data. Parameter learning in BFA faces an exponential computational complexity and a large number of local optima. The model selection to determine the latent binary dimension is therefore difficult. Traditionally, it is implemented in two separate stages with two different objectives. First, parameter learning is performed for each candidate model scale to maximise the likelihood; then the optimal scale is selected to minimise a model selection criterion. Such a two-phase implementation suffers from huge computational cost and deteriorated learning performance on large scale structures. In contrast, the Bayesian Ying-Yang (BYY) harmony learning starts from a high dimensional model and automatically deducts the dimension during learning. This paper investigates model selection on a subclass of BFA called Orthogonal Binary Factor Analysis (OBFA). The Bayesian inference of the latent binary code is analytically solved, based on which a BYY machine is constructed. The harmony measure that serves as the objective function in BYY learning is more accurately estimated by recovering a regularisation term. Experimental comparison with the two-phase implementations shows superior performance of the proposed approach.
- Rights:
- http://creativecommons.org/publicdomain/mark/1.0/ and policy:public
2858. Bayle a Mandeville. Dvě rané konceptualizace společnosti ateistů
- Creator:
- Tomeček, Marek
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- Pierre Bayle, Bernard Mandeville, ateismus, slib, čest, atheism, promise, honour, Atheismus, Eid, and Ehre
- Language:
- Czech
- Description:
- Společnost složená z ateistů byla v raném novověku považována za nemožnou, neboť panovalo všeobecné přesvědčení, že na slovo ateisty se nedá spolehnout, protože se nebojí posmrtného trestu. Ateisté nemohou tedy dlouhodobě spolupracovat a vytvořit společnost. Jako první polemizoval s tímto přístupem Pierre Bayle, jeho žák Bernard Mandeville však o padesát let později jeho stanovisko odmítl. O upřímnosti argumentů vznášených v souvislosti s otázkou ateismu koncem sedmnáctého a počátkem osmnáctého století je však možné vždy pochybovat, protože ateismus byl v té době trestný postoj a nikdo se k němu veřejně nehlásil. Proto někteří ateisté psali z předstíraně teistických pozic a svými záměrně slabými argumenty, jimiž podporovali Boží existenci, víru naopak podrývali, jak ukazuje případ Anthonyho Collinse. Ovšem ateismus takových autorů není možné prokázat z jejich publikovaných textů, ale jedině z jiných dokumentů a vzpomínek jejich současníků. Právě takový metodologický přístup nám při analýze koncepcí Pierra Bayla a Bernarda Mandevilla umožní dospět k novým závěrům ohledně jejich představ o fungování náboženství ve společnosti., A society composed of atheists was thought impossible in early modern Europe. An atheist, it was believed, will not keep a promise since he or she does not fear divine retribution. Thus, atheists cannot cooperate in a long-term enterprise and form a viable society. Pierre Bayle was the first thinker to challenge this common assumption, though some fifty years later his follower Bernard Mandeville rejected his arguments. But the sincerity of such arguments is always questionable in the early modern period, it being illegal and punishable to publicly advocate atheism. Some atheists, as was demonstrated to be the case with Anthony Collins, wrote from contrived theistic positions, actually trying to undermine Christianity with purposefully weak arguments for the existence of God. But the atheism of such authors cannot be deduced from their published writings, only from other of their documents and from their contemporaries’ memoirs. Applying this methodological insight to Bayle and Mandeville will enable us to see their arguments for and against an atheistic society in a new light., and Eine aus Atheisten bestehende Gesellschaft galt in der frühen Neuzeit als ein Ding der Unmöglichkeit, da die allgemeine Überzeugung herrschte, auf das Wort eines Atheisten sei kein Verlass, weil dieser keine Angst vor einer Bestrafung nach dem Tod habe. Atheisten könnten also nicht langfristig kooperieren und eine Gesellschaft aufbauen. Als erster polemisierte Pierre Bayle mit diesem Ansatz, wobei sein Schüler Bernard Mandeville diesen Standpunkt fünfzig Jahre später ablehnte. Die Ehrlichkeit der Argumente im Zusammenhang mit der Frage des Atheismus Ende des 17. und Anfang des 18. Jahrhunderts kann jedoch in Zweifel gezogen werden, da Atheismus zu der Zeit unter Strafe stand und sich niemand öffentlich zum Atheismus bekannte. Deshalb schrieben manche Atheisten aus einer vorgetäuschten theistischen Position heraus und trugen mit absichtlich schwachen Argumenten für die Existenz Gottes zu einer Untergrabung des Glaubens bei, wie bei Anthony Collins zu sehen ist. Ein Atheismus kann bei diesen Autoren jedoch nicht anhand veröffentlichter Texte nachgewiesen werden; dies ist nur durch andere Dokumente sowie durch Erinnerungen ihrer Zeitgenossen möglich. Dieser methodologische Ansatz ermöglicht es uns, bei der Analyse der Konzepte Pierre Bayles und Bernard Mandevilles zu neuen Erkenntnissen hinsichtlich der Vorstellung dieser beiden Autoren bezüglich der Funktion der Religion in der Gesellschaft zu gelangen.
- Rights:
- http://creativecommons.org/licenses/by-nc-sa/4.0/ and policy:public
2859. Be star research by the HEROS group: results from the past decade
- Creator:
- Štefl, S. and Rivinius, Th.
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- spectroscopy, photometry, and Be stars
- Language:
- Czech
- Description:
- The progress in the investigation of Be stars during the past decade was enabled mainly thanks to high-resolution echelle spectrographs. Such instruments made possible to carry out multi-line studies of line profile variations and to search for correlations between photospheric and circumstellar phenomena. The Heros team was one of the most active in this field during the last decade. Here we summarize the most important achievements reached by the group.
- Rights:
- http://creativecommons.org/licenses/by-nc-sa/4.0/ and policy:public
2860. Beam reducery - optika pro diagnostiku širokých laserových svazků
- Creator:
- Stanke, Ladislav and Palatka, Miroslav
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- telescope design, laser beam diagnostics, Shack-Hartmann sensor, návrh teleskopu, diagnostika laserového svazku, and Shackův-Hartmannův senzor
- Language:
- Czech
- Description:
- This paper presents one of the possible designs for beam monitoring/ diagnostic telescope. The purpose of this catadioptric system is to attenuate and demagnify the input beam so it can be imaged on the Shack-Hartmann wavefront sensor or other optoelectronic device. These optical systems are used within the high power laser facilities to diagnose beam quality and possibly to correct wavefront errors by joint use with adaptive optics. One of the demands on the system presented here is to use stock optics, or low-cost custom optics. The aim is to image the beam on commercially available Shack-Hartmann sensor by Thorlabs. and Článek představuje jedno z možných řešení teleskopů určených pro diagnostiku a monitorování laserových svazků (beam diagnostics/monitoring telescope). Jedná se o katadioptrický systém, jehož účelem je utlumit a zmenšit vstupní svazek pro zobrazení na Shackův-Hartmannův senzor vlnoplochy, či jiný diagnostický optoelektronický prvek. Optické soustavy tohoto typu se využívají ve vysokovýkonových laserových centrech, kde slouží k posuzování kvality laserových svazků a jejich případné korekci s pomocí adaptivní optiky. Jedním z požadavků kladených na zde prezentovaný systém je možnost využití komerčně dostupných (stock) optických komponent nebo relativně levně vyrobitelných elementů. Cílem návrhu je zobrazení vstupního svazku na běžně dostupný Shackův-Hartmannův senzor dodávaný společností Thorlabs.
- Rights:
- http://creativecommons.org/licenses/by-nc-sa/4.0/ and policy:public