To see the other types of publications on this topic, follow the link: Maximum entropy markov model.
Dissertations / Theses on the topic 'Maximum entropy markov model'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Maximum entropy markov model.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Wang, Chao. "Exploiting non-redundant local patterns and probabilistic models for analyzing structured and semi-structured data." Columbus, Ohio : Ohio State University, 2008. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=osu1199284713.
Full text
2
Bury, Thomas. "Collective behaviours in the stock market: a maximum entropy approach." Doctoral thesis, Universite Libre de Bruxelles, 2014. http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/209341.
Full textAbstract:
Scale invariance, collective behaviours and structural reorganization are crucial for portfolio management (portfolio composition, hedging, alternative definition of risk, etc.). This lack of any characteristic scale and such elaborated behaviours find their origin in the theory of complex systems. There are several mechanisms which generate scale invariance but maximum entropy models are able to explain both scale invariance and collective behaviours.<p>The study of the structure and collective modes of financial markets attracts more and more attention. It has been shown that some agent based models are able to reproduce some stylized facts. Despite their partial success, there is still the problem of rules design. In this work, we used a statistical inverse approach to model the structure and co-movements in financial markets. Inverse models restrict the number of assumptions. We found that a pairwise maximum entropy model is consistent with the data and is able to describe the complex structure of financial systems. We considered the existence of a critical state which is linked to how the market processes information, how it responds to exogenous inputs and how its structure changes. The considered data sets did not reveal a persistent critical state but rather oscillations between order and disorder.<p>In this framework, we also showed that the collective modes are mostly dominated by pairwise co-movements and that univariate models are not good candidates to model crashes. The analysis also suggests a genuine adaptive process since both the maximum variance of the log-likelihood and the accuracy of the predictive scheme vary through time. This approach may provide some clue to crash precursors and may provide highlights on how a shock spreads in a financial network and if it will lead to a crash. The natural continuation of the present work could be the study of such a mechanism.<br>Doctorat en Sciences économiques et de gestion<br>info:eu-repo/semantics/nonPublished
3
Chan, Oscar. "Prosodic features for a maximum entropy language model." University of Western Australia. School of Electrical, Electronic and Computer Engineering, 2008. http://theses.library.uwa.edu.au/adt-WU2008.0244.
Full textAbstract:
A statistical language model attempts to characterise the patterns present in a natural language as a probability distribution defined over word sequences. Typically, they are trained using word co-occurrence statistics from a large sample of text. In some language modelling applications, such as automatic speech recognition (ASR), the availability of acoustic data provides an additional source of knowledge. This contains, amongst other things, the melodic and rhythmic aspects of speech referred to as prosody. Although prosody has been found to be an important factor in human speech recognition, its use in ASR has been limited. The goal of this research is to investigate how prosodic information can be employed to improve the language modelling component of a continuous speech recognition system. Because prosodic features are largely suprasegmental, operating over units larger than the phonetic segment, the language model is an appropriate place to incorporate such information. The prosodic features and standard language model features are combined under the maximum entropy framework, which provides an elegant solution to modelling information obtained from multiple, differing knowledge sources. We derive features for the model based on perceptually transcribed Tones and Break Indices (ToBI) labels, and analyse their contribution to the word recognition task. While ToBI has a solid foundation in linguistic theory, the need for human transcribers conflicts with the statistical model's requirement for a large quantity of training data. We therefore also examine the applicability of features which can be automatically extracted from the speech signal. We develop representations of an utterance's prosodic context using fundamental frequency, energy and duration features, which can be directly incorporated into the model without the need for manual labelling. Dimensionality reduction techniques are also explored with the aim of reducing the computational costs associated with training a maximum entropy model. Experiments on a prosodically transcribed corpus show that small but statistically significant reductions to perplexity and word error rates can be obtained by using both manually transcribed and automatically extracted features.
4
Camiola, Vito Dario. "Subbands model for semiconductors based on the Maximum Entropy Principle." Doctoral thesis, Università di Catania, 2013. http://hdl.handle.net/10761/1313.
Full textAbstract:
In this thesis a double-gate MOSFET is simulated with an energy-transport subband model and an energy-transport model is derived for a nanoscale MOSFET.
Regarding the double-gate MOSFET the model is formulated starting from the moment system derived from the Schroedinger-Poisson-Boltzmann equations. The system is closed on the basis of the maximum entropy principle and includes scattering of electrons with acoustic and non-polar optical phonons. The proposed
expression of the entropy combines quantum effects and semiclassical transport by weighting the contribution of each sub band with the square modulus of the envelope functions arising from the Schroedinger-Poisson system. The simulations show that the model is able to capture the relevant confining and transport features and asses the robustness of the numerical scheme.\\
The model for the MOSFET takes into account the presence of both 3D and 2D electron gas included along with the quantization in the transversal direction with respect to the oxide at the gate which gives raise to a sub band decomposition of the electron energy.\\
Both intra and inter scattering between the 2D and the 3D electron gas are considered. In particular, a fictitious transition from the 3D to the 2D electrons and vice versa is introduced.
5
Sekhi, Ikram. "Développement d'un alphabet structural intégrant la flexibilité des structures protéiques." Thesis, Sorbonne Paris Cité, 2018. http://www.theses.fr/2018USPCC084/document.
Full textAbstract:
L’objectif de cette thèse est de proposer un Alphabet Structural (AS) permettant une caractérisation fine et précise des structures tridimensionnelles (3D) des protéines, à l’aide des chaînes de Markov cachées (HMM) qui permettent de prendre en compte la logique issue de l’enchaînement des fragments structuraux en intégrant l’augmentation des conformations 3D des structures protéiques désormais disponibles dans la banque de données de la Protein Data Bank (PDB). Nous proposons dans cette thèse un nouvel alphabet, améliorant l’alphabet structural HMM-SA27,appelé SAFlex (Structural Alphabet Flexibility), dans le but de prendre en compte l’incertitude des données (données manquantes dans les fichiers PDB) et la redondance des structures protéiques. Le nouvel alphabet structural SAFlex obtenu propose donc un nouveau modèle d’encodage rigoureux et robuste. Cet encodage permet de prendre en compte l’incertitude des données en proposant trois options d’encodages : le Maximum a posteriori (MAP), la distribution marginale a posteriori (POST)et le nombre effectif de lettres à chaque position donnée (NEFF). SAFlex fournit également un encodage consensus à partir de différentes réplications (chaînes multiples, monomères et homomères) d’une même protéine. Il permet ainsi la détection de la variabilité structurale entre celles-ci. Les avancées méthodologiques ainsi que l’obtention de l’alphabet SAFlex constituent les contributions principales de ce travail de thèse. Nous présentons aussi le nouveau parser de la PDB (SAFlex-PDB) et nous démontrons que notre parser a un intérêt aussi bien sur le plan qualitatif (détection de diverses erreurs)que quantitatif (rapidité et parallélisation) en le comparant avec deux autres parsers très connus dans le domaine (Biopython et BioJava). Nous proposons également à la communauté scientifique un site web mettant en ligne ce nouvel alphabet structural SAFlex. Ce site web représente la contribution concrète de cette thèse alors que le parser SAFlex-PDB représente une contribution importante pour le fonctionnement du site web proposé. Cette caractérisation précise des conformations 3D et la prise en compte de la redondance des informations 3D disponibles, fournies par SAFlex, a en effet un impact très important pour la modélisation de la conformation et de la variabilité des structures 3D, des boucles protéiques et des régions d’interface avec différents partenaires, impliqués dans la fonction des protéines<br>The purpose of this PhD is to provide a Structural Alphabet (SA) for more accurate characterization of protein three-dimensional (3D) structures as well as integrating the increasing protein 3D structure information currently available in the Protein Data Bank (PDB). The SA also takes into consideration the logic behind the structural fragments sequence by using the hidden Markov Model (HMM). In this PhD, we describe a new structural alphabet, improving the existing HMM-SA27 structural alphabet, called SAFlex (Structural Alphabet Flexibility), in order to take into account the uncertainty of data (missing data in PDB files) and the redundancy of protein structures. The new SAFlex structural alphabet obtained therefore offers a new, rigorous and robust encoding model. This encoding takes into account the encoding uncertainty by providing three encoding options: the maximum a posteriori (MAP), the marginal posterior distribution (POST), and the effective number of letters at each given position (NEFF). SAFlex also provides and builds a consensus encoding from different replicates (multiple chains, monomers and several homomers) of a single protein. It thus allows the detection of structural variability between different chains. The methodological advances and the achievement of the SAFlex alphabet are the main contributions of this PhD. We also present the new PDB parser(SAFlex-PDB) and we demonstrate that our parser is therefore interesting both qualitative (detection of various errors) and quantitative terms (program optimization and parallelization) by comparing it with two other parsers well-known in the area of Bioinformatics (Biopython and BioJava). The SAFlex structural alphabet is being made available to the scientific community by providing a website. The SAFlex web server represents the concrete contribution of this PhD while the SAFlex-PDB parser represents an important contribution to the proper function of the proposed website. Here, we describe the functions and the interfaces of the SAFlex web server. The SAFlex can be used in various fashions for a protein tertiary structure of a given PDB format file; it can be used for encoding the 3D structure, identifying and predicting missing data. Hence, it is the only alphabet able to encode and predict the missing data in a 3D protein structure to date. Finally, these improvements; are promising to explore increasing protein redundancy data and obtain useful quantification of their flexibility
6
Eruygur, Hakki Ozan. "Impacts Of Policy Changes On Turkish Agriculture: An Optimization Model With Maximum Entropy." Phd thesis, METU, 2006. http://etd.lib.metu.edu.tr/upload/12607740/index.pdf.
Full textAbstract:
Turkey moves towards integration with EU since 1963. The membership will
involve full liberalization of trade in agricultural products with EU. The impact
of liberalization depends on the path of agricultural policies in Turkey and the
EU. On the other hand, agricultural protection continues to be the most
controversial issue in global trade negotiations of World Trade Organization
(WTO). To evaluate the impacts of policy scenarios, an economic modeling
approach based on non-linear mathematical programming is appropriate. This
thesis analyzes the impacts of economic integration with the EU and the
potential effects of the application of a new WTO agreement in 2015 on
Turkish agriculture using an agricultural sector model. The basic approach is
Maximum Entropy based Positive Mathematical Programming of Heckelei and
Britz (1999). The model is based on a static optimization algorithm. Following
an economic integration with EU, the net export of crops declines and can not
tolerate the boom in net import of livestock products. Overall welfare affect is
small. Consumers benefit from declining prices. Common Agricultural Policy
(CAP) supports are determinative for the welfare of producers. WTO
simulation shows that a 15 percent reduction in Turkey&rsquo<br>s binding WTO tariff
commitments will increase net meat imports by USD 250 million.
7
Piggott, Stephen. "Multiple model control and maximum entropy control of flexible structures, implementation and evaluation." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1999. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape8/PQDD_0020/MQ58721.pdf.
Full text
8
Hogg, David W. (David Wardell). "The principle of maximum entropy production in a simple model of a convection cell." Thesis, Massachusetts Institute of Technology, 1992. http://hdl.handle.net/1721.1/26841.
Full text
9
Selvaraj, Bellarmin N. "A Reasoning Mechanism in the Probabilistic Data Model Based on the Maximum Entropy Formalism." NSUWorks, 1999. http://nsuworks.nova.edu/gscis_etd/828.
Full textAbstract:
A desirable feature of a database system is its ability to reason with probabilistic information. This dissertation proposes a model for the process of reasoning with probabilistic information in databases. A probabilistic data model has been chosen as the framework for this study and the information theoretical aspects of the Maximum Entropy Formalism as the inference engine. This formalism, although semantically interesting, offers major complexity problems. Probabilistic data models generally assume some knowledge of the uncertainty space, and the Maximum Entropy Formalism finds the least commitment probability distribution within the uncertainty space. This dissertation is an investigation of how successfully the entropy principle could be applied to probabilistic data. The Boolean logic and weighted queries when applied to probabilistic databases have certain pros and cons. A query logic based on the combined advantages of both the Boolean logic and weighted queries would be a desirable alternative. The proposed model based on the Maximum Entropy Formalism meets the foregoing desiderata of making the query language more expressive.
Probabilistic data models generally deal with tuple-level probabilities whereas the proposed model has the ability to handle attribute-level probabilities. This model also has the ability to guess the unknown joint probability distributions. Three techniques to compute the probability distributions were studied in this dissertation: (1) a brute-force, iterative algorithm, (2) a heuristic algorithm, and (3) a simulation approach. The performance characteristics of these algorithms were examined and conclusions were drawn about the potentials and limitations of the proposed model in probabilistic database applications.
Traditionally, the probabilistic solution proposed by the Maximum Entropy Formalism is arrived at by solving nonlinear simultaneous equations for the aggregate factors of the nonlinear terms. The proposed heuristic approach and simulation technique were shown to have the highly desirable property of tractability. Further research is needed to improve the accuracy of the heuristic and make it more attractive.
Although the proposed model and algorithms are applicable to tables with a few probabilistic attributes, say two or three, the complexity of extending the model to a large number of probabilistic attributes still remains unsolved as it falls in the realm of NP-hard problems.
10
Pesheva, Nina Christova. "A mean-field method for driven diffusive systems based on maximum entropy principle." Diss., Virginia Polytechnic Institute and State University, 1989. http://hdl.handle.net/10919/54398.
Full textAbstract:
Here, we propose a method for generating a hierarchy of mean-field approximations to study the properties of the driven diffusive Ising model at nonequilibrium steady state. In addition, the present study offers a demonstration of the practical application of the information theoretic methods to a simple interacting nonequilibrium system. The application of maximum entropy principle to the system, which is in contact with a heat reservoir, leads to a minimization principle for the generalized Helmholtz free energy. At every level of approximation the latter is expressed in terms of the corresponding mean—field variables. These play the role of variational parameters. The rate equations for the mean-field variables, which incorporate the dynamics of the system, serve as constraints to the minimization procedure.
The method is applicable to high temperatures as well to the low temperature phase coexistence regime and also has the potential for dealing with first-order phase transitions. At low temperatures the free energy is nonconvex and we use a Maxwell construction to find the relevant information for the system.
To test the method we carry out numerical calculations at the pair level of approximation for the 2-dimensional driven diffusive Ising model on a square lattice with attractive interactions. The results reproduce quite well all the basic properties of the system as reported from Monte Carlo simulations.<br>Ph. D.
11
Vera, Ruiz Victor. "Recoding of Markov Processes in Phylogenetic Models." Thesis, The University of Sydney, 2014. http://hdl.handle.net/2123/13433.
Full textAbstract:
Under a Markov model of evolution, lumping the state space (S) into fewer groups has been historically used to focus on specific types of substitutions or to reduce compositional heterogeneity and saturation. However, working with reduced state spaces (S’) may yield misleading results unless the Markovian property is kept. A Markov process X(t) is lumpable if the reduced process X’(t) of S’ is Markovian. The aim of this Thesis is to develop a test able to detect if a given X(t) is lumpable with respect to a given S’. This test should allow flexibility to any possible non-trivial S’ and should not depend on evolutionary assumptions such as stationarity, homogeneity or reversibility (SHR conditions) over a phylogenetic tree. We developed three tests for lumpability for SHR Markovian processes on two taxa and compared them: one using an ad hoc statistic based on an index that is evaluated using a bootstrap approximation of its distribution; one based on a test proposed specifically for Markov chains; and one using a likelihood-ratio (LR) test. We show that the LR test is more powerful than the other two tests, and that it can be applied in all pairs of taxa for binary trees with more than two taxa under SHR conditions. Then, we generalized the LR test for cases where the SHR conditions may not hold. We show that the distribution of this test statistic approximates a chi square with a number of degrees of freedom equal to the number of different rate matrices in the tree by two. In all cases, we show that if X(t) is lumpable, the obtained estimates for X’(t) agree with the obtained estimates for X(t), whereas, if X(t) is not lumpable, these estimates can differ substantially. We conclude that lumping S may result in biased phylogenetic estimates if the original X(t) is not lumpable. Accordingly, testing for lumpability should be done prior to any phylogenetic analysis of recoded data.
12
Ali, Akbar Soltan Reza. "Enhancements in Markovian Dynamics." Diss., Virginia Tech, 2012. http://hdl.handle.net/10919/77345.
Full textAbstract:
Many common statistical techniques for modeling multidimensional dynamic data sets can be seen as variants of one (or multiple) underlying linear/nonlinear model(s). These statistical techniques fall into two broad categories of supervised and unsupervised learning. The emphasis of this dissertation is on unsupervised learning under multiple generative models. For linear models, this has been achieved by collective observations and derivations made by previous authors during the last few decades. Factor analysis, polynomial chaos expansion, principal component analysis, gaussian mixture clustering, vector quantization, and Kalman filter models can all be unified as some variations of unsupervised learning under a single basic linear generative model. Hidden Markov modeling (HMM), however, is categorized as an unsupervised learning under multiple linear/nonlinear generative models. This dissertation is primarily focused on hidden Markov models (HMMs).
On the first half of this dissertation we study enhancements on the theory of hidden Markov modeling. These include three branches: 1) a robust as well as a closed-form parameter estimation solution to the expectation maximization (EM) process of HMMs for the case of elliptically symmetrical densities; 2) a two-step HMM, with a combined state sequence via an extended Viterbi algorithm for smoother state estimation; and 3) a duration-dependent HMM, for estimating the expected residency frequency on each state. Then, the second half of the dissertation studies three novel applications of these methods: 1) the applications of Markov switching models on the Bifurcation Theory in nonlinear dynamics; 2) a Game Theory application of HMM, based on fundamental theory of card counting and an example on the game of Baccarat; and 3) Trust modeling and the estimation of trustworthiness metrics in cyber security systems via Markov switching models.
As a result of the duration dependent HMM, we achieved a better estimation for the expected duration of stay on each regime. Then by robust and closed form solution to the EM algorithm we achieved robustness against outliers in the training data set as well as higher computational efficiency in the maximization step of the EM algorithm. By means of the two-step HMM we achieved smoother probability estimation with higher likelihood than the standard HMM.<br>Ph. D.
13
Lai, John. "A hidden Markov model and relative entropy rate approach to vision-based dim target detection for UAV sense-and-avoid." Thesis, Queensland University of Technology, 2010. https://eprints.qut.edu.au/34462/1/John_Lai_Thesis.pdf.
Full textAbstract:
Uninhabited aerial vehicles (UAVs) are a cutting-edge technology that is at the forefront of aviation/aerospace research and development worldwide. Many consider their current military and defence applications as just a token of their enormous potential. Unlocking and fully exploiting this potential will see UAVs in a multitude of civilian applications and routinely operating alongside piloted aircraft. The key to realising the full potential of UAVs lies in addressing a host of regulatory, public relation, and technological challenges never encountered be- fore. Aircraft collision avoidance is considered to be one of the most important issues to be addressed, given its safety critical nature. The collision avoidance problem can be roughly organised into three areas: 1) Sense; 2) Detect; and 3) Avoid. Sensing is concerned with obtaining accurate and reliable information about other aircraft in the air; detection involves identifying potential collision threats based on available information; avoidance deals with the formulation and execution of appropriate manoeuvres to maintain safe separation. This thesis tackles the detection aspect of collision avoidance, via the development of a target detection algorithm that is capable of real-time operation onboard a UAV platform. One of the key challenges of the detection problem is the need to provide early warning. This translates to detecting potential threats whilst they are still far away, when their presence is likely to be obscured and hidden by noise. Another important consideration is the choice of sensors to capture target information, which has implications for the design and practical implementation of the detection algorithm. The main contributions of the thesis are: 1) the proposal of a dim target detection algorithm combining image morphology and hidden Markov model (HMM) filtering approaches; 2) the novel use of relative entropy rate (RER) concepts for HMM filter design; 3) the characterisation of algorithm detection performance based on simulated data as well as real in-flight target image data; and 4) the demonstration of the proposed algorithm's capacity for real-time target detection. We also consider the extension of HMM filtering techniques and the application of RER concepts for target heading angle estimation. In this thesis we propose a computer-vision based detection solution, due to the commercial-off-the-shelf (COTS) availability of camera hardware and the hardware's relatively low cost, power, and size requirements. The proposed target detection algorithm adopts a two-stage processing paradigm that begins with an image enhancement pre-processing stage followed by a track-before-detect (TBD) temporal processing stage that has been shown to be effective in dim target detection. We compare the performance of two candidate morphological filters for the image pre-processing stage, and propose a multiple hidden Markov model (MHMM) filter for the TBD temporal processing stage. The role of the morphological pre-processing stage is to exploit the spatial features of potential collision threats, while the MHMM filter serves to exploit the temporal characteristics or dynamics. The problem of optimising our proposed MHMM filter has been examined in detail. Our investigation has produced a novel design process for the MHMM filter that exploits information theory and entropy related concepts. The filter design process is posed as a mini-max optimisation problem based on a joint RER cost criterion. We provide proof that this joint RER cost criterion provides a bound on the conditional mean estimate (CME) performance of our MHMM filter, and this in turn establishes a strong theoretical basis connecting our filter design process to filter performance. Through this connection we can intelligently compare and optimise candidate filter models at the design stage, rather than having to resort to time consuming Monte Carlo simulations to gauge the relative performance of candidate designs. Moreover, the underlying entropy concepts are not constrained to any particular model type. This suggests that the RER concepts established here may be generalised to provide a useful design criterion for multiple model filtering approaches outside the class of HMM filters. In this thesis we also evaluate the performance of our proposed target detection algorithm under realistic operation conditions, and give consideration to the practical deployment of the detection algorithm onboard a UAV platform. Two fixed-wing UAVs were engaged to recreate various collision-course scenarios to capture highly realistic vision (from an onboard camera perspective) of the moments leading up to a collision. Based on this collected data, our proposed detection approach was able to detect targets out to distances ranging from about 400m to 900m. These distances, (with some assumptions about closing speeds and aircraft trajectories) translate to an advanced warning ahead of impact that approaches the 12.5 second response time recommended for human pilots. Furthermore, readily available graphic processing unit (GPU) based hardware is exploited for its parallel computing capabilities to demonstrate the practical feasibility of the proposed target detection algorithm. A prototype hardware-in- the-loop system has been found to be capable of achieving data processing rates sufficient for real-time operation. There is also scope for further improvement in performance through code optimisations. Overall, our proposed image-based target detection algorithm offers UAVs a cost-effective real-time target detection capability that is a step forward in ad- dressing the collision avoidance issue that is currently one of the most significant obstacles preventing widespread civilian applications of uninhabited aircraft. We also highlight that the algorithm development process has led to the discovery of a powerful multiple HMM filtering approach and a novel RER-based multiple filter design process. The utility of our multiple HMM filtering approach and RER concepts, however, extend beyond the target detection problem. This is demonstrated by our application of HMM filters and RER concepts to a heading angle estimation problem.
14
Sarlak, Nermin. "Evaluation And Modeling Of Streamflow Data: Entropy Method, Autoregressive Models With Asymmetric Innovations And Artificial Neural Networks." Phd thesis, METU, 2005. http://etd.lib.metu.edu.tr/upload/3/12606135/index.pdf.
Full textAbstract:
In the first part of this study, two entropy methods under different distribution assumptions are examined on a network of stream gauging stations located in Kizilirmak Basin to rank the stations according to their level of importance. The stations are ranked by using two different entropy methods under different distributions. Thus, showing the effect of the distribution type on both entropy methods is aimed.
In the second part of this study, autoregressive models with asymmetric innovations and an artificial neural network model are introduced. Autoregressive models (AR) which have been developed in hydrology are based on several assumptions. The normality assumption for the innovations of AR models is investigated in this study. The main reason of making this assumption in the autoregressive models established is the difficulties faced in finding the model parameters under the distributions other than the normal distributions. From this point of view, introduction of the modified maximum likelihood procedure developed by Tiku et. al. (1996) in estimation of the autoregressive model parameters having non-normally distributed residual series, in the area of hydrology has been aimed. It is also important to consider how the autoregressive model parameters having skewed distributions could be estimated.
Besides these autoregressive models, the artificial neural network (ANN) model was also constructed for annual and monthly hydrologic time series due to its advantages such as no statistical distribution and no linearity assumptions.
The models considered are applied to annual and monthly streamflow data obtained from five streamflow gauging stations in Kizilirmak Basin. It is shown that AR(1) model with Weibull innovations provides best solutions for annual series and AR(1) model with generalized logistic innovations provides best solution for monthly as compared with the results of artificial neural network models.
15
Molloy, Timothy Liam. "Online hidden Markov model parameter estimation and minimax robust quickest change detection in uncertain stochastic processes." Thesis, Queensland University of Technology, 2015. https://eprints.qut.edu.au/88476/1/Timothy_Molloy_Thesis.pdf.
Full textAbstract:
Stochastic (or random) processes are inherent to numerous fields of human endeavour including engineering, science, and business and finance. This thesis presents multiple novel methods for quickly detecting and estimating uncertainties in several important classes of stochastic processes. The significance of these novel methods is demonstrated by employing them to detect aircraft manoeuvres in video signals in the important application of autonomous mid-air collision avoidance.
16
Do, Hoan. "Parameter Recovery for the Four-Parameter Unidimensional Binary IRT Model: A Comparison of Marginal Maximum Likelihood and Markov Chain Monte Carlo Approaches." Ohio University / OhioLINK, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1616202942083398.
Full text
17
Doluweera, D. G. Sumith Pradeepa. "Effect of Weak Inhomogeneities in High Temperature Superconductivity." University of Cincinnati / OhioLINK, 2008. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1227215152.
Full text
18
De, bortoli Valentin. "Statistiques non locales dans les images : modélisation, estimation et échantillonnage." Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPASN020.
Full textAbstract:
Dans cette thèse, on étudie d'un point de vueprobabiliste deux statistiques non locales dans les images : laredondance spatiale et les moments de certaines couches de réseauxde neurones convolutionnels. Plus particulièrement, on s'intéresse àl'estimation et à la détection de la redondance spatiale dans lesimages naturelles et à l'échantillonnage de modèles d'images souscontraintes de moments de sorties de réseaux deneurones.On commence par proposer une définition de la redondance spatialedans les images naturelles. Celle-ci repose sur une analyseGestaltiste de la notion de similarité ainsi que sur un cadrestatistique pour le test d'hypothèses via la méthode acontrario. On développe un algorithme pour identifier cetteredondance dans les images naturelles. Celui-ci permet d'identifierles patchs similaires dans une image. On utilise cette informationpour proposer de nouveaux algorithmes de traitement d'image(débruitage, analyse de périodicité).Le reste de cette thèse est consacré à la modélisation et àl'échantillonnage d'images sous contraintes non locales. Les modèlesd'images considérés sont obtenus via le principe de maximumd'entropie. On peut alors déterminer la distribution cible sur lesimages via une procédure de minimisation. On aborde ce problème enutilisant des outils issus de l'optimisationstochastique.Plus précisément, on propose et analyse un nouvel algorithme pourl'optimisation stochastique : l'algorithme SOUL (StochasticOptimization with Unadjusted Langevin). Dans cette méthodologie, legradient est estimé par une méthode de Monte Carlo par chaîne deMarkov (ici l'algorithme de Langevin non ajusté). Les performancesde cet algorithme repose sur les propriétés de convergenceergodiques des noyaux de Markov associés aux chaînes de Markovutilisées. On s'intéresse donc aux propriétés de convergencegéométrique de certaines classes de modèles fonctionnelsautorégressifs. On caractérise précisément la dépendance des taux deconvergence de ces modèles vis à vis des constantes du modèle(dimension, régularité,convexité...).Enfin, on applique l'algorithme SOUL au problème de synthèse detexture par maximum d'entropie. On étudie les liens qu'entretientcette approche avec d'autres modèles de maximisation d'entropie(modèles macrocanoniques, modèles microcanoniques). En utilisant desstatistiques de moments de sorties de réseaux de neuronesconvolutionnels on obtient des résultats visuels comparables à ceux del'état de l'art<br>In this thesis we study two non-localstatistics in images from a probabilistic point of view: spatialredundancy and convolutional neural network features. Moreprecisely, we are interested in the estimation and detection ofspatial redundancy in naturalimages. We also aim at sampling images with neural network constraints.We start by giving a definition of spatial redundancy in naturalimages. This definition relies on two concepts: a Gestalt analysisof the notion of similarity in images, and a hypothesis testingframework (the a contrario method). We propose an algorithm toidentify this redundancy in natural images. Using this methodologywe can detect similar patches in images and, with this information,we propose new algorithms for diverse image processing tasks(denoising, periodicity analysis).The rest of this thesis deals with sampling images with non-localconstraints. The image models we consider are obtained via themaximum entropy principle. The target distribution is then obtainedby minimizing an energy functional. We use tools from stochasticoptimization to tackle thisproblem.More precisely, we propose and analyze a new algorithm: the SOUL(Stochastic Optimization with Unadjusted Langevin) algorithm. Inthis methodology, the gradient is estimated using Monte Carlo MarkovChains methods. In the case of the SOUL algorithm we use an unadjustedLangevin algorithm. The efficiency of the SOUL algorithm is relatedto the ergodic properties of the underlying Markov chains. Thereforewe are interested in the convergence properties of certain class offunctional autoregressive models. We characterize precisely thedependency of the convergence rates of these models with respect totheir parameters (dimension, smoothness,convexity).Finally, we apply the SOUL algorithm to the problem ofexamplar-based texture synthesis with a maximum entropy approach. Wedraw links between our model and other entropy maximizationprocedures (macrocanonical models, microcanonical models). Usingconvolutional neural network constraints we obtain state-of-the artvisual results
19
Le, Tien-Thinh. "Modélisation stochastique, en mécanique des milieux continus, de l'interphase inclusion-matrice à partir de simulations en dynamique moléculaire." Thesis, Paris Est, 2015. http://www.theses.fr/2015PESC1172/document.
Full textAbstract:
Dans ce travail, nous nous intéressons à la modélisation stochastique continue et à l'identification des propriétés élastiques dans la zone d'interphase présente au voisinage des hétérogénéités dans un nano composite prototypique, composé d'une matrice polymère modèle renforcée par une nano inclusion de silice. Des simulations par dynamique moléculaire (DM) sont tout d'abord conduites afin d'extraire certaines caractéristiques de conformation des chaînes proches de la surface de l'inclusion, ainsi que pour estimer, par des essais mécaniques virtuels, des réalisations du tenseur apparent associé au domaine de simulation. Sur la base des résultats obtenus, un modèle informationnel de champ aléatoire est proposé afin de modéliser les fluctuations spatiales du tenseur des rigidités dans l'interphase. Les paramètres du modèle probabiliste sont alors identifiés par la résolution séquentielle de deux problèmes d'optimisation inverses (l'un déterministe et associé au modèle moyen, l'autre stochastique et lié aux paramètres de dispersion et de corrélation spatiale) impliquant une procédure d'homogénéisation numérique. On montre en particulier que la longueur de corrélation dans la direction radiale est du même ordre de grandeur que l'épaisseur de l'interphase, indiquant ainsi la non-séparation des échelles. Enfin, la prise en compte, par un modèle de matrices aléatoires, du bruit intrinsèque généré par les simulations de DM (dans la procédure de calibration) est discutée<br>This work is concerned with the stochastic modeling and identification of the elastic properties in the so-called interphase region surrounding the inclusions in nanoreinforced composites. For the sake of illustration, a prototypical nanocomposite made up with a model polymer matrix filled by a silica nanoinclusion is considered. Molecular Dynamics (MD) simulations are first performed in order to get a physical insight about the local conformation of the polymer chains in the vicinity of the inclusion surface. In addition, a virtual mechanical testing procedure is proposed so as to estimate realizations of the apparent stiffness tensor associated with the MD simulation box. An information-theoretic probabilistic representation is then proposed as a surrogate model for mimicking the spatial fluctuations of the elasticity field within the interphase. The hyper parameters defining the aforementioned model are subsequently calibrated by solving, in a sequential manner, two inverse problems involving a computational homogenization scheme. The first problem, related to the mean model, is formulated in a deterministic framework, whereas the second one involves a statistical metric allowing the dispersion parameter and the spatial correlation lengths to be estimated. It is shown in particular that the spatial correlation length in the radial direction is roughly equal to the interphase thickness, hence showing that the scales under consideration are not well separated. The calibration results are finally refined by taking into account, by means of a random matrix model, the MD finite-sampling noise
20
Theeranaew, Wanchat. "STUDY ON INFORMATION THEORY: CONNECTION TO CONTROL THEORY, APPROACH AND ANALYSIS FOR COMPUTATION." Case Western Reserve University School of Graduate Studies / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=case1416847576.
Full text
21
Rosário, Maria do Socorro Soares. "Um modelo de desagregação de encargos de produção variáveis da Base RICA por actividade." Master's thesis, Universidade de Évora, 2011. http://hdl.handle.net/10174/15123.
Full textAbstract:
A informação desagregada relativamente a factores de produção é um problema generalizado das ciências agrárias. Recorre-se à utilização de inquéritos directos e pessoais junto do agricultor, com recurso a amostras pequenas, que são dispendiosos e demorados. O uso de técnicas e métodos alternativos pode ser uma experiência válida para estimar os custos variáveis de produção com um menor encargo. A base de dados da Rede de Informação de Contabilidades Agrícolas (RICA) é uma fonte de informação útil para estudar aspectos da política agrícola, respeita o total dos custos por tipo de factor não sendo desagregada por actividade. A obtenção dos custos variáveis por actividade é extremamente importante para a gestão da exploração e para a análise da política agrícola.
Esta dissertação tem como principal objectivo estimar os coeficientes de afectação dos custos às actividades agrícolas, a partir da RICA: é desenvolvido um modelo de desagregação dos custos de factores de produção variáveis por actividade com base na teoria da máxima entropia, aplicado na região do Alentejo e usando os dados da base RICA de 2008.
Os resultados mostram que a utilização da teoria da entropia é uma opção adequada para a estimação de coeficientes de afectação dos custos dos factores de produção às actividades num contexto de informação incompleta. Os estimadores de entropia apresentam de um modo geral bons resultados do ponto de vista estatístico e econométrico, mas os modelos de Mínima Entropia Cruzada permitem obter resultados mais aderentes à realidade do que os modelos de Máxima Entropia Generalizada; ABSTRACT:The lack of disaggregated data on factors of production is a widespread problem in the agricultural sciences. Usually, to obtain such information we do direct and personal surveys, using small samples. As these surveys are expensive and time consuming, the use of alternative techniques and methods to estimate the variable costs of production, with significantly lower costs, may be a worthwhile experience. The Farm Accounting Data Network (FADN) is a very useful source of data for studying agricultural policy. However FADN data concerns total costs by type of cost, being not broken down by activity. The attainment of variable unit costs of production by activity is extremely important, not only from the standpoint of business management, but also in the context of agricultural policy analysis.
To mitigate the lack of information on input costs in agriculture, the main goal of this paper is to estimate good coefficients for allocating those costs to farming activities, from the FADN database. We develop a model based on the theory of maximum entropy to breakdown the input variable costs by activity. This model is applied in the context of the Alentejo agricultural region, using FADN 2008 data.
The results show that the use of theory of entropy is an appropriate method for the estimating of coefficients for allocation costs of factors of production activities in a context of incomplete information. The entropy estimators have generally good results in terms of statistical and models but the Minimum Cross Entropy model results allow more adherent to reality than the Generalized Maximum Entropy models.
22
Hendrick, Lindsey R. F. "Climate Change and Mountaintop Removal Mining: A MaxEnt Assessment of the Potential Dual Threat to West Virginia Fishes." VCU Scholars Compass, 2018. https://scholarscompass.vcu.edu/etd/5291.
Full textAbstract:
Accounts of species’ range shifts in response to climate change, most often as latitudinal shifts towards the poles or upslope shifts to higher elevations, are rapidly accumulating. These range shifts are often attributed to species ‘tracking’ their thermal niches as temperatures in their native ranges increase. Our objective was to estimate the degree to which climate change-driven shifts in water temperature may increase the exposure of West Virginia’s native freshwater fishes to mountaintop removal surface coal mining. Mid-century shifts in habitat suitability for nine non-game West Virginia fishes were projected via Maximum Entropy species distribution modeling, using a combination of physical habitat, historical climate conditions, and future climate data. Modeling projections for a high-emissions scenario (Representative Concentration Pathway 8.5) predict that habitat suitability will increase in high elevation streams for eight of nine species, with marginal increases in habitat suitability ranging from 46-418%. We conclude that many West Virginia fishes will be at risk of increased exposure to mountaintop removal surface coal mining if climate change continues at a rapid pace.
23
Lundquist, Anders. "Contributions to the theory of unequal probability sampling." Doctoral thesis, Umeå : Department of Mathematics and Mathematical Statistics, Umeå University, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-22459.
Full text
24
Wu, Hao. "Probabilistic Modeling of Multi-relational and Multivariate Discrete Data." Diss., Virginia Tech, 2017. http://hdl.handle.net/10919/74959.
Full textAbstract:
Modeling and discovering knowledge from multi-relational and multivariate
discrete data is a crucial task that arises in many research and application
domains, e.g. text mining, intelligence analysis, epidemiology, social science,
etc. In this dissertation, we study and address three problems involving the
modeling of multi-relational discrete data and multivariate multi-response count
data, viz. (1) discovering surprising patterns from multi-relational data, (2)
constructing a generative model for multivariate categorical data, and (3)
simultaneously modeling multivariate multi-response count data and estimating
covariance structures between multiple responses.
To discover surprising multi-relational patterns, we first study the ``where
do I start?'' problem originating from intelligence analysis. By studying nine
methods with origins in association analysis, graph metrics, and probabilistic
modeling, we identify several classes of algorithmic strategies that can supply
starting points to analysts, and thus help to discover interesting
multi-relational patterns from datasets. To actually mine for interesting
multi-relational patterns, we represent the multi-relational patterns as dense
and well-connected chains of biclusters over multiple relations, and model the
discrete data by the maximum entropy principle, such that in a statistically
well-founded way we can gauge the surprisingness of a discovered bicluster chain
with respect to what we already know. We design an algorithm for approximating
the most informative multi-relational patterns, and provide strategies to
incrementally organize discovered patterns into the background model. We
illustrate how our method is adept at discovering the hidden plot in multiple
synthetic and real-world intelligence analysis datasets. Our approach naturally
generalizes traditional attribute-based maximum entropy models for single
relations, and further supports iterative, human-in-the-loop, knowledge
discovery.
To build a generative model for multivariate categorical data, we apply the
maximum entropy principle to propose a categorical maximum entropy model such
that in a statistically well-founded way we can optimally use given prior
information about the data, and are unbiased otherwise. Generally, inferring the
maximum entropy model could be infeasible in practice. Here, we leverage the
structure of the categorical data space to design an efficient model inference
algorithm to estimate the categorical maximum entropy model, and we demonstrate
how the proposed model is adept at estimating underlying data distributions. We
evaluate this approach against both simulated data and US census datasets, and
demonstrate its feasibility using an epidemic simulation application.
Modeling data with multivariate count responses is a challenging problem due to
the discrete nature of the responses. Existing methods for univariate count
responses cannot be easily extended to the multivariate case since the
dependency among multiple responses needs to be properly accounted for. To model
multivariate data with multiple count responses, we propose a novel multivariate
Poisson log-normal model (MVPLN). By simultaneously estimating the regression
coefficients and inverse covariance matrix over the latent variables with an
efficient Monte Carlo EM algorithm, the proposed model takes advantages of
association among multiple count responses to improve the model prediction
accuracy. Simulation studies and applications to real world data are conducted
to systematically evaluate the performance of the proposed method in comparison
with conventional methods.<br>Ph. D.
25
Akin, Serdar. "Do Riksbanken produce unbiased forecast of the inflation rate? : and can it be improved?" Thesis, Stockholms universitet, Nationalekonomiska institutionen, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-58708.
Full textAbstract:
The focus of this paper is to evaluate if forecast produced by the Central Bank of Sweden (Riksbanken) for the 12 month change in the consumer price index is unbiased? Results shows that for shorter horizons (h < 12) the mean forecast error is unbiased but for longer horizons its negatively biased when inference is done by Maximum entropy bootstrap technique. Can the unbiasedness be improved by strict ap- pliance to econometric methodology? Forecasting with a linear univariate model (seasonal ARIMA) and a multivariate model Vector Error Correction model (VECM) shows that when controlling for the presence of structural breaks VECM outperforms both prediction produced Riksbanken and ARIMA. However Riksbanken had the best precision in their forecast, estimated as MSFE
26
Delattre, Maud. "Inférence statistique dans les modèles mixtes à dynamique Markovienne." Phd thesis, Université Paris Sud - Paris XI, 2012. http://tel.archives-ouvertes.fr/tel-00765708.
Full textAbstract:
La première partie de cette thèse est consacrée à l'estimation par maximum de vraisemblance dans les modèles mixtes à dynamique markovienne. Nous considérons plus précisément des modèles de Markov cachés à effets mixtes et des modèles de diffusion à effets mixtes. Dans le Chapitre 2, nous combinons l'algorithme de Baum-Welch à l'algorithme SAEM pour estimer les paramètres de population dans les modèles de Markov cachés à effets mixtes. Nous proposons également des procédures spécifiques pour estimer les paramètres individuels et les séquences d' états cachées. Nous étudions les propriétés de cette nouvelle méthodologie sur des données simulées et l'appliquons sur des données réelles de nombres de crises d' épilepsie. Dans le Chapitre 3, nous proposons d'abord des modèles de diffusion à effets mixtes pour la pharmacocin étique de population. Nous en estimons les paramètres en combinant l'algorithme SAEM a un filtre de Kalman étendu. Nous étudions ensuite les propriétés asymptotiques de l'estimateur du maximum de vraisemblance dans des modèles de diffusion observés sans bruit de mesure continûment sur un intervalle de temps fixe lorsque le nombre de sujets tend vers l'infini. Le Chapitre 4 est consacré a la s élection de covariables dans des modèles mixtes généraux. Nous proposons une version du BIC adaptée au contexte de double asymptotique où le nombre de sujets et le nombre d'observations par sujet tendent vers l'infini. Nous présentons quelques simulations pour illustrer cette procédure.
27
Elyoubi, Abderrahim. "Statistiques exhaustives en reconnaissance de formes." Rouen, 1995. http://www.theses.fr/1995ROUES058.
Full textAbstract:
Dans ce travail, nous avons développé une nouvelle approche des modèles de Markov. Le but visé à terme est son application en reconnaissance optique de l'écriture manuscrite. L'analyse faite est fondée sur le constat que les règles de grammaire définies sur un langage naturel agissent sur des séquences longues nécessitant l'emploi de chaines de Markov d'ordre k, élevé. L'augmentation en puissance de k du nombre des états rend un tel modèle pratiquement inapplicable. La méthode développée cherche à définir à partir d'une suite de variables aléatoires représentant les états d'un modèle de Markov d'ordre k, une chaîne de Markov à nombre d'états réduit, exhaustive et calculable de façon récursive. Cette chaîne, appelée chaîne induite de Markov, introduit les propriétés principales du système aléatoire. Elle envisage de regrouper les séquences des états à transitions égales. Une évolution compatible avec le regroupement est indispensable. Ainsi, les lois statistiques du phénomène étudié se déduisent de celles de la chaîne induite et de la suite des observations. En comparaison avec un modèle de Markov classique, un nouveau terme contenant les informations sur la structure des séquences des états apparaît dans la formule d'identification par modèle induit de Markov. Ce terme permet de mieux préciser l'estimation des états du modèle. La lecture automatique des nombres manuscrits en provenance de chèques est un cas qui se prête bien à l'application d'un modèle induit de Markov.
28
Kreacic, Eleonora. "Some problems related to the Karp-Sipser algorithm on random graphs." Thesis, University of Oxford, 2017. http://ora.ox.ac.uk/objects/uuid:3b2eb52a-98f5-4af8-9614-e4909b8b9ffa.
Full textAbstract:
We study certain questions related to the performance of the Karp-Sipser algorithm on the sparse Erdös-Rényi random graph. The Karp-Sipser algorithm, introduced by Karp and Sipser [34] is a greedy algorithm which aims to obtain a near-maximum matching on a given graph. The algorithm evolves through a sequence of steps. In each step, it picks an edge according to a certain rule, adds it to the matching and removes it from the remaining graph. The algorithm stops when the remining graph is empty. In [34], the performance of the Karp-Sipser algorithm on the Erdös-Rényi random graphs G(n,M = [<sup>cn</sup>/<sub>2</sub>]) and G(n, p = <sup>c</sup>/<sub>n</sub>), c > 0 is studied. It is proved there that the algorithm behaves near-optimally, in the sense that the difference between the size of a matching obtained by the algorithm and a maximum matching is at most o(n), with high probability as n → ∞. The main result of [34] is a law of large numbers for the size of a maximum matching in G(n,M = <sup>cn</sup>/<sub>2</sub>) and G(n, p = <sup>c</sup>/<sub>n</sub>), c > 0. Aronson, Frieze and Pittel [2] further refine these results. In particular, they prove that for c < e, the Karp-Sipser algorithm obtains a maximum matching, with high probability as n → ∞; for c > e, the difference between the size of a matching obtained by the algorithm and the size of a maximum matching of G(n,M = <sup>cn</sup>/<sub>2</sub>) is of order Θ<sub>log n</sub>(n<sup>1/5</sup>), with high probability as n → ∞. They further conjecture a central limit theorem for the size of a maximum matching of G(n,M = <sup>cn</sup>/<sub>2</sub>) and G(n, p = <sup>c</sup>/<sub>n</sub>) for all c > 0. As noted in [2], the central limit theorem for c < 1 is a consequence of the result of Pittel [45]. In this thesis, we prove a central limit theorem for the size of a maximum matching of both G(n,M = <sup>cn</sup>/<sub>2</sub>) and G(n, p = <sup>c</sup>/<sub>n</sub>) for c > e. (We do not analyse the case 1 ≤ c ≤ e). Our approach is based on the further analysis of the Karp-Sipser algorithm. We use the results from [2] and refine them. For c > e, the difference between the size of a matching obtained by the algorithm and the size of a maximum matching is of order Θ<sub>log n</sub>(n<sup>1/5</sup>), with high probability as n → ∞, and the study [2] suggests that this difference is accumulated at the very end of the process. The question how the Karp-Sipser algorithm evolves in its final stages for c > e, motivated us to consider the following problem in this thesis. We study a model for the destruction of a random network by fire. Let us assume that we have a multigraph with minimum degree at least 2 with real-valued edge-lengths. We first choose a uniform random point from along the length and set it alight. The edges burn at speed 1. If the fire reaches a node of degree 2, it is passed on to the neighbouring edge. On the other hand, a node of degree at least 3 passes the fire either to all its neighbours or none, each with probability 1/2. If the fire extinguishes before the graph is burnt, we again pick a uniform point and set it alight. We study this model in the setting of a random multigraph with N nodes of degree 3 and α(N) nodes of degree 4, where α(N)/N → 0 as N → ∞. We assume the edges to have i.i.d. standard exponential lengths. We are interested in the asymptotic behaviour of the number of fires we must set alight in order to burn the whole graph, and the number of points which are burnt from two different directions. Depending on whether α(N) » √N or not, we prove that after the suitable rescaling these quantities converge jointly in distribution to either a pair of constants or to (complicated) functionals of Brownian motion. Our analysis supports the conjecture that the difference between the size of a matching obtained by the Karp-Sipser algorithm and the size of a maximum matching of the Erdös-Rényi random graph G(n,M = <sup>cn</sup>/<sub>2</sub>) for c > e, rescaled by n<sup>1/5</sup>, converges in distribution.
29
Dupuis, Jérôme. "Analyse statistique bayesienne de modèles de capture-recapture." Paris 6, 1995. http://www.theses.fr/1995PA066077.
Full textAbstract:
Le modele statistique de base que nous considerons, consiste en n realisations simultanees et i. I. D. D'un processus d'interet ramene a une chaine de markov, avec donnees manquantes, non homogene, a espace d'etat fini comportant un unique etat absorbant. Alors que l'estimateur du maximum de vraisemblance est actuellement disponible l'analyse statistique bayesienne de ce modele de capture-recapture n'a pas encore ete abordee. L'estimation bayesienne des probabilites de survie et de mouvement du modele de base est realisee via l'algorithme de gibbs. Des conditions suffisantes de convergence de l'algorithme sont etablies. Puis nous developpons des tests afin d'apprehender les differentes sources d'heterogeneite (temporelle, individuelle et environnementale) du phenomene biologique represente par la chaine de markov. Le test d'homogeneite temporelle que nous construisons formule la question d'interet en terme de divergence acceptable entre la chaine initiale et sa projection (au sens de la distance de kullback) sur l'espace des chaines de markov homogenes. Nous developpons ensuite des tests formules en terme d'independance conditionnelle permettant de mettre en evidence un effet differe d'un processus auxiliaire (variable aleatoire discrete environnementale ou individuelle, dependant ou non du temps) sur le processus d'interet. Enfin, pour la premiere fois en capture-recapture, une situation de non-independance des comportements migratoires est envisagee. Nous considerons une structure de dependance de nature unilaterale qui permet de rendre compte d'un eventuel effet guide en dynamique des populations animales
30
Telionis, Pyrros A. "Lyme Disease and Forest Fragmentation in the Peridomestic Environment." Thesis, Virginia Tech, 2020. http://hdl.handle.net/10919/99281.
Full textAbstract:
Over the last 20 years, Lyme disease has grown to become the most common vector-borne disease affecting Americans. Spread in the eastern U.S. primarily by the bite of Ixodes scapularis, the black-legged tick, the disease affects an estimated 329,000 Americans per year. Originally confined to New England, it has since spread across much of the east coast and has become endemic in Virginia. Since 2010 the state has averaged 1200 cases per year, with 200 annually in the New River Health District (NRHD), the location of our study.
Efforts to geographically model Lyme disease primarily focus on landscape and climatic variables. The disease depends highly on the survival of the tick vector, and white-footed mouse, the primary reservoir. Both depend on the existence of forest-herbaceous edge-habitats, as well as warm summer temperatures, mild winter lows, and summer wetness. While many studies have investigated the effect of forest fragmentation on Lyme, none have made use of high-resolution land cover data to do so at the peridomestic level.
To fill this knowledge gap, we made use of the Virginia Geographic Information Network’s 1-meter land cover dataset and identified forest-herbaceous edge-habitats for the NRHD. We then calculated the density of these edge-habitats at 100, 200 and 300-meter radii, representing the peridomestic environment. We also calculated the density of <2-hectare forest patches at the same distance thresholds. To avoid confounding from climatic variation, we also calculated mean summer temperatures, total summer rainfall, and number of consecutive days below freezing of the prior winters. Adding to these data, elevation, terrain shape index, slope, and aspect, and including lags on each of our climatic variables, we created environmental niche models of Lyme in the NRHD. We did so using both Boosted Regression Trees (BRT) and Maximum Entropy (MaxEnt) modeling, the two most common niche modeling algorithms in the field today.
We found that Lyme is strongly associated with higher density of developed-herbaceous edges within 100-meters from the home. Forest patch density was also significant at both 100-meter and 300-meter levels. This supports the notion that the fine scale peridomestic environment is significant to Lyme outcomes, and must be considered even if one were to account for fragmentation at a wider scale, as well as variations in climate and terrain.<br>M.S.<br>Lyme disease is the most common vector-borne disease in the United States today. Infecting about 330,000 Americans per year, the disease continues to spread geographically. Originally found only in New England, the disease is now common in Virginia. The New River Health District, where we did our study, sees over 200 cases per year.
Lyme disease is mostly spread by the bite of the black-legged tick. As such we can predict where Lyme cases might be found if we understand the environmental needs of these ticks. The ticks themselves depend on warm summer temperatures, mild winter lows, and summer wetness. But they are also affected by forest fragmentation which drives up the population of white-footed mice, the tick’s primary host. The mice are particularly fond of the interface between forests and open fields. These edge habitats provide food and cover for the mice, and in turn support a large population of ticks.
Many existing studies have demonstrated this link, but all have done so across broad scales such as counties or census tracts. To our knowledge, no such studies have investigated forest fragmentation near the home of known Lyme cases. To fill this gap in our knowledge, we made use of high-resolution forest cover data to identify forest-field edge habitats and small isolated forest patches. We then calculated the total density of both within 100, 200 and 300 meters of the homes of known Lyme cases, and compared these to values from non-cases using statistical modeling. We also included winter and summer temperatures, rainfall, elevation, slope, aspect, and terrain shape.
We found that a large amount of forest-field edges within 100 meters of a home increases the risk of Lyme disease to residents of that home. The same can be said for isolated forest patches. Even after accounting for all other variables, this effect was still significant. This information can be used by health departments to predict which neighborhoods may be most at risk for Lyme. They can then increase surveillance in those areas, warn local doctors, or send out educational materials.
31
Duchon, Eric Nicholas. "Quantum Phase Transitions in the Bose Hubbard Model and in a Bose-Fermi Mixture." The Ohio State University, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=osu1386002245.
Full text
32
Le, Corff Sylvain. "Estimations pour les modèles de Markov cachés et approximations particulaires : Application à la cartographie et à la localisation simultanées." Phd thesis, Telecom ParisTech, 2012. http://tel.archives-ouvertes.fr/tel-00773405.
Full textAbstract:
Dans cette thèse, nous nous intéressons à l'estimation de paramètres dans les chaînes de Markov cachées dans un cadre paramétrique et dans un cadre non paramétrique. Dans le cas paramétrique, nous imposons des contraintes sur le calcul de l'estimateur proposé : un premier volet de cette thèse est l'estimation en ligne d'un paramètre au sens du maximum de vraisemblance. Le fait d'estimer en ligne signifie que les estimations doivent être produites sans mémoriser les observations. Nous proposons une nouvelle méthode d'estimation en ligne pour les chaînes de Markov cachées basée sur l'algorithme Expectation Maximization appelée Block Online Expectation Maximization (BOEM). Cet algorithme est défini pour des chaînes de Markov cachées à espace d'état et espace d'observations généraux. La consistance de l'algorithme ainsi que des vitesses de convergence en probabilité ont été prouvées. Dans le cas d'espaces d'états généraux, l'implémentation numérique de l'algorithme BOEM requiert d'introduire des méthodes de Monte Carlo séquentielles - aussi appelées méthodes particulaires - pour approcher des espérances conditionnelles sous des lois de lissage qui ne peuvent être calculées explicitement. Nous avons donc proposé une approximation Monte Carlo de l'algorithme BOEM appelée Monte Carlo BOEM. Parmi les hypothèses nécessaires à la convergence de l'algorithme Monte Carlo BOEM, un contrôle de la norme Lp de l'erreur d'approximation Monte Carlo explicite en fonction du nombre d'observations T et du nombre de particules N est nécessaire. Par conséquent, une seconde partie de cette thèse a été consacrée à l'obtention de tels contrôles pour plusieurs méthodes de Monte Carlo séquentielles : l'algorithme Forward Filtering Backward Smoothing et l'algorithme Forward Filtering Backward Simulation. Ensuite, nous considérons des applications de l'algorithme Monte Carlo BOEM à des problèmes de cartographie et de localisation simultanées. Ces problèmes se posent lorsqu'un mobile se déplace dans un environnement inconnu. Il s'agit alors de localiser le mobile tout en construisant une carte de son environnement. Enfin, la dernière partie de cette thèse est relative à l'estimation non paramétrique dans les chaînes de Markov cachées. Le problème considéré a été très peu étudié et nous avons donc choisi de l'aborder dans un cadre précis. Nous supposons que la chaîne (Xk) est une marche aléatoire sur un sous-espace compact de Rm dont la loi des incréments est connue à un facteur d'échelle a près. Nous supposons également que, pour tout k, Yk est une observation dans un bruit additif gaussien de f(Xk), où f est une fonction à valeurs dans Rl que nous cherchons à estimer. Le premier résultat que nous avons établi est l'identifiabilité du modèle statistique considéré. Nous avons également proposé une estimation de la fonction f et du paramètre a à partir de la log-vraisemblance par paires des observations. Nous avons prouvé la convergence en probabilité de ces estimateurs lorsque le nombre d'observations utilisées tend vers l'infini.
33
Mikolov, Tomáš. "Statistické jazykové modely založené na neuronových sítích." Doctoral thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2012. http://www.nusl.cz/ntk/nusl-261268.
Full textAbstract:
Statistické jazykové modely jsou důležitou součástí mnoha úspěšných aplikací, mezi něž patří například automatické rozpoznávání řeči a strojový překlad (příkladem je známá aplikace Google Translate). Tradiční techniky pro odhad těchto modelů jsou založeny na tzv. N-gramech. Navzdory známým nedostatkům těchto technik a obrovskému úsilí výzkumných skupin napříč mnoha oblastmi (rozpoznávání řeči, automatický překlad, neuroscience, umělá inteligence, zpracování přirozeného jazyka, komprese dat, psychologie atd.), N-gramy v podstatě zůstaly nejúspěšnější technikou. Cílem této práce je prezentace několika architektur jazykových modelůzaložených na neuronových sítích. Ačkoliv jsou tyto modely výpočetně náročnější než N-gramové modely, s technikami vyvinutými v této práci je možné jejich efektivní použití v reálných aplikacích. Dosažené snížení počtu chyb při rozpoznávání řeči oproti nejlepším N-gramovým modelům dosahuje 20%. Model založený na rekurentní neurovové síti dosahuje nejlepších publikovaných výsledků na velmi známé datové sadě (Penn Treebank).
34
McGarry, Gregory John. "Model-based mammographic image analysis." Thesis, Queensland University of Technology, 2002.
Find full text
35
Chabot, John Alva. "VALIDATING STEADY TURBULENT FLOW SIMULATIONS USING STOCHASTIC MODELS." Miami University / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=miami1443188391.
Full text
36
Megyesi, Beata. "Data-driven syntactic analysis." Doctoral thesis, KTH, Speech Transmission and Music Acoustics, 2002. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-3433.
Full text
37
Robles, Bernard. "Etude de la pertinence des paramètres stochastiques sur des modèles de Markov cachés." Phd thesis, Université d'Orléans, 2013. http://tel.archives-ouvertes.fr/tel-01058784.
Full textAbstract:
Le point de départ de ce travail est la thèse réalisée par Pascal Vrignat sur la modélisation de niveaux de dégradation d'un système dynamique à l'aide de Modèles de Markov Cachés (MMC), pour une application en maintenance industrielle. Quatre niveaux ont été définis : S1 pour un arrêt de production et S2 à S4 pour des dégradations graduelles. Recueillant un certain nombre d'observations sur le terrain dans divers entreprises de la région, nous avons réalisé un modèle de synthèse à base de MMC afin de simuler les différents niveaux de dégradation d'un système réel. Dans un premier temps, nous identifions la pertinence des différentes observations ou symboles utilisés dans la modélisation d'un processus industriel. Nous introduisons ainsi le filtre entropique. Ensuite, dans un but d'amélioration du modèle, nous essayons de répondre aux questions : Quel est l'échantillonnage le plus pertinent et combien de symboles sont ils nécessaires pour évaluer au mieux le modèle ? Nous étudions ensuite les caractéristiques de plusieurs modélisations possibles d'un processus industriel afin d'en déduire la meilleure architecture. Nous utilisons des critères de test comme les critères de l'entropie de Shannon, d'Akaike ainsi que des tests statistiques. Enfin, nous confrontons les résultats issus du modèle de synthèse avec ceux issus d'applications industrielles. Nous proposons un réajustement du modèle pour être plus proche de la réalité de terrain.
38
Le, Corff Sylvain. "Estimations pour les modèles de Markov cachés et approximations particulaires : Application à la cartographie et à la localisation simultanées." Electronic Thesis or Diss., Paris, ENST, 2012. http://www.theses.fr/2012ENST0052.
Full textAbstract:
Dans cette thèse, nous nous intéressons à l'estimation de paramètres dans les chaînes de Markov cachées. Nous considérons tout d'abord le problème de l'estimation en ligne (sans sauvegarde des observations) au sens du maximum de vraisemblance. Nous proposons une nouvelle méthode basée sur l'algorithme Expectation Maximization appelée Block Online Expectation Maximization (BOEM). Cet algorithme est défini pour des chaînes de Markov cachées à espace d'état et espace d'observations généraux. Dans le cas d'espaces d'états généraux, l'algorithme BOEM requiert l'introduction de méthodes de Monte Carlo séquentielles pour approcher des espérances sous des lois de lissage. La convergence de l'algorithme nécessite alors un contrôle de la norme Lp de l'erreur d'approximation Monte Carlo explicite en le nombre d'observations et de particules. Une seconde partie de cette thèse se consacre à l'obtention de tels contrôles pour plusieurs méthodes de Monte Carlo séquentielles. Nous étudions enfin des applications de l'algorithme BOEM à des problèmes de cartographie et de localisation simultanées. La dernière partie de cette thèse est relative à l'estimation non paramétrique dans les chaînes de Markov cachées. Le problème considéré est abordé dans un cadre précis. Nous supposons que (Xk) est une marche aléatoire dont la loi des incréments est connue à un facteur d'échelle a près. Nous supposons que, pour tout k, Yk est une observation de f(Xk) dans un bruit additif gaussien, où f est une fonction que nous cherchons à estimer. Nous établissons l'identifiabilité du modèle statistique et nous proposons une estimation de f et de a à partir de la vraisemblance par paires des observations<br>This document is dedicated to inference problems in hidden Markov models. The first part is devoted to an online maximum likelihood estimation procedure which does not store the observations. We propose a new Expectation Maximization based method called the Block Online Expectation Maximization (BOEM) algorithm. This algorithm solves the online estimation problem for general hidden Markov models. In complex situations, it requires the introduction of Sequential Monte Carlo methods to approximate several expectations under the fixed interval smoothing distributions. The convergence of the algorithm is shown under the assumption that the Lp mean error due to the Monte Carlo approximation can be controlled explicitly in the number of observations and in the number of particles. Therefore, a second part of the document establishes such controls for several Sequential Monte Carlo algorithms. This BOEM algorithm is then used to solve the simultaneous localization and mapping problem in different frameworks. Finally, the last part of this thesis is dedicated to nonparametric estimation in hidden Markov models. It is assumed that the Markov chain (Xk) is a random walk lying in a compact set with increment distribution known up to a scaling factor a. At each time step k, Yk is a noisy observations of f(Xk) where f is an unknown function. We establish the identifiability of the statistical model and we propose estimators of f and a based on the pairwise likelihood of the observations
39
Löhr, Wolfgang. "Models of Discrete-Time Stochastic Processes and Associated Complexity Measures." Doctoral thesis, Universitätsbibliothek Leipzig, 2010. http://nbn-resolving.de/urn:nbn:de:bsz:15-qucosa-38267.
Full textAbstract:
Many complexity measures are defined as the size of a minimal representation in
a specific model class. One such complexity measure, which is important because
it is widely applied, is statistical complexity. It is defined for
discrete-time, stationary stochastic processes within a theory called
computational mechanics. Here, a mathematically rigorous, more general version
of this theory is presented, and abstract properties of statistical complexity
as a function on the space of processes are investigated. In particular, weak-*
lower semi-continuity and concavity are shown, and it is argued that these
properties should be shared by all sensible complexity measures. Furthermore, a
formula for the ergodic decomposition is obtained.
The same results are also proven for two other complexity measures that are
defined by different model classes, namely process dimension and generative
complexity. These two quantities, and also the information theoretic complexity
measure called excess entropy, are related to statistical complexity, and this
relation is discussed here.
It is also shown that computational mechanics can be reformulated in terms of
Frank Knight's prediction process, which is of both conceptual and technical
interest. In particular, it allows for a unified treatment of different
processes and facilitates topological considerations. Continuity of the Markov
transition kernel of a discrete version of the prediction process is obtained as
a new result.
40
Löhr, Wolfgang. "Models of Discrete-Time Stochastic Processes and Associated Complexity Measures." Doctoral thesis, Max Planck Institut für Mathematik in den Naturwissenschaften, 2009. https://ul.qucosa.de/id/qucosa%3A11017.
Full textAbstract:
Many complexity measures are defined as the size of a minimal representation in
a specific model class. One such complexity measure, which is important because
it is widely applied, is statistical complexity. It is defined for
discrete-time, stationary stochastic processes within a theory called
computational mechanics. Here, a mathematically rigorous, more general version
of this theory is presented, and abstract properties of statistical complexity
as a function on the space of processes are investigated. In particular, weak-*
lower semi-continuity and concavity are shown, and it is argued that these
properties should be shared by all sensible complexity measures. Furthermore, a
formula for the ergodic decomposition is obtained.
The same results are also proven for two other complexity measures that are
defined by different model classes, namely process dimension and generative
complexity. These two quantities, and also the information theoretic complexity
measure called excess entropy, are related to statistical complexity, and this
relation is discussed here.
It is also shown that computational mechanics can be reformulated in terms of
Frank Knight''s prediction process, which is of both conceptual and technical
interest. In particular, it allows for a unified treatment of different
processes and facilitates topological considerations. Continuity of the Markov
transition kernel of a discrete version of the prediction process is obtained as
a new result.
41
Avila, Manuel. "Optimisation de modèles markoviens pour la reconnaissance de l'écrit." Rouen, 1996. http://www.theses.fr/1996ROUES034.
Full textAbstract:
Cette thèse traite de l'optimisation de modèles markoviens dédiés à la reconnaissance de textes manuscrits, dans le cas particulier d'une application à vocabulaire réduit : la lecture des montants littéraux de chèques. Le premier chapitre décrit brièvement les techniques utilisées pour la reconnaissance de l'écrit. Nous présentons également les descriptions des mots que nous avons utilisées. Le second chapitre présente les modèles de Markov cache. Nous présentons notamment les différents niveaux de représentation du problème de la lecture de l'écrit dans le cas de modélisations markoviennes : les niveaux phrase, mot et lettre. Finalement, nous présentons les algorithmes couramment utilisés pour exploiter des modèles de Markov : les algorithmes de Viterbi et de Baum-welch, avec des variantes que nous avons adaptées à nos besoins. Dans le troisième chapitre, nous traitons du problème d'une optimisation des descriptions des mots. Nous donnons trois méthodes de représentation des mots. Nous présentons ensuite une méthode de recherche de l'ordre optimal d'un processus de Markov basée sur la minimisation de critères d'information de type Akaike soit AIC, BIC etc. Finalement, nous comparons les résultats des trois alphabets pour les ordres de 1 à 3. Ceci nous permet de valider le choix de la description des mots et de l'ordre du modèle de Markov correspondant. Nous réutilisons ces résultats au chapitre 4. Dans ce chapitre, trois approches sont proposées pour la reconnaissance des mots : la première est une approche globale qui par définition ne s'attache pas à l'identification des lettres, la seconde est une approche analytique basée sur une modélisation complètement explicitée, la troisième méthode est une approche pseudo-analytique intermédiaire entre les deux approches précédentes. Elle modélise le mot de manière analytique en utilisant des modèles globaux de lettres. Finalement, les résultats de ces trois méthodes sont ensuite fusionnés : chapitre 5. Ce chapitre traite de l'identification des montants littéraux de chèques. La stratégie développée se décompose en trois parties : validation de la segmentation des mots, identification des mots et reconstitution de la phrase. A chaque partie correspond une modélisation markovienne adaptée.
42
Mattrand, Cécile. "Approche probabiliste de la tolérance aux dommages." Phd thesis, Université Blaise Pascal - Clermont-Ferrand II, 2011. http://tel.archives-ouvertes.fr/tel-00738947.
Full textAbstract:
En raison de la gravité des accidents liés au phénomène de fatigue-propagation de fissure, les préoccupations de l'industrie aéronautique à assurer l'intégrité des structures soumises à ce mode de sollicitation revêtent un caractère tout à fait essentiel. Les travaux de thèse présentés dans ce mémoire visent à appréhender le problème de sûreté des structures aéronautiques dimensionnées en tolérance aux dommages sous l'angle probabiliste. La formulation et l'application d'une approche fiabiliste menant à des processus de conception et de maintenance fiables des structures aéronautiques en contexte industriel nécessitent cependant de lever un nombre important de verrous scientifiques. Les efforts ont été concentrés au niveau de trois domaines dans ce travail. Une méthodologie a tout d'abord été développée afin de capturer et de retranscrire fidèlement l'aléa du chargement de fatigue à partir de séquences de chargement observées sur des structures en service et monitorées, ce qui constitue une réelle avancée scientifique. Un deuxième axe de recherche a porté sur la sélection d'un modèle mécanique apte à prédire l'évolution de fissure sous chargement d'amplitude variable à coût de calcul modéré. Les travaux se sont ainsi appuyés sur le modèle PREFFAS pour lequel des évolutions ont également été proposées afin de lever l'hypothèse restrictive de périodicité de chargement. Enfin, les analyses probabilistes, produits du couplage entre le modèle mécanique et les modélisations stochastiques préalablement établies, ont entre autre permis de conclure que le chargement est un paramètre qui influe notablement sur la dispersion du phénomène de propagation de fissure. Le dernier objectif de ces travaux a ainsi porté sur la formulation et la résolution du problème de fiabilité en tolérance aux dommages à partir des modèles stochastiques retenus pour le chargement, constituant un réel enjeu scientifique. Une méthode de résolution spécifique du problème de fiabilité a été mise en place afin de répondre aux objectifs fixés et appliquée à des structures jugées représentatives de problèmes réels.
43
Nourbakhsh, Ghavameddin. "Reliability analysis and economic equipment replacement appraisal for substation and sub-transmission systems with explicit inclusion of non-repairable failures." Thesis, Queensland University of Technology, 2011. https://eprints.qut.edu.au/40848/1/Ghavameddin_Nourbakhsh_Thesis.pdf.
Full textAbstract:
The modern society has come to expect the electrical energy on demand, while many of the facilities in power systems are aging beyond repair and maintenance. The risk of failure is increasing with the aging equipments and can pose serious consequences for continuity of electricity supply. As the equipments used in high voltage power networks are very expensive, economically it may not be feasible to purchase and store spares in a warehouse for extended periods of time. On the other hand, there is normally a significant time before receiving equipment once it is ordered. This situation has created a considerable interest in the evaluation and application of probability methods for aging plant and provisions of spares in bulk supply networks, and can be of particular importance for substations. Quantitative adequacy assessment of substation and sub-transmission power systems is generally done using a contingency enumeration approach which includes the evaluation of contingencies, classification of the contingencies based on selected failure criteria. The problem is very complex because of the need to include detailed modelling and operation of substation and sub-transmission equipment using network flow evaluation and to consider multiple levels of component failures. In this thesis a new model associated with aging equipment is developed to combine the standard tools of random failures, as well as specific model for aging failures. This technique is applied in this thesis to include and examine the impact of aging equipments on system reliability of bulk supply loads and consumers in distribution network for defined range of planning years. The power system risk indices depend on many factors such as the actual physical network configuration and operation, aging conditions of the equipment, and the relevant constraints. The impact and importance of equipment reliability on power system risk indices in a network with aging facilities contains valuable information for utilities to better understand network performance and the weak links in the system. In this thesis, algorithms are developed to measure the contribution of individual equipment to the power system risk indices, as part of the novel risk analysis tool. A new cost worth approach was developed in this thesis that can make an early decision in planning for replacement activities concerning non-repairable aging components, in order to maintain a system reliability performance which economically is acceptable. The concepts, techniques and procedures developed in this thesis are illustrated numerically using published test systems. It is believed that the methods and approaches presented, substantially improve the accuracy of risk predictions by explicit consideration of the effect of equipment entering a period of increased risk of a non-repairable failure.
44
Anand, A. "Parts of speech tagging using hidden Markov model, maximum entropy model and conditional random field." Thesis, 2014. http://ethesis.nitrkl.ac.in/6171/1/E-42.pdf.
Full textAbstract:
Parts of Speech tagging assigns the suitable part of speech or in other words, the lexical category to every word in the sentence in Natural language. It is one of the essential tasks of Natural Language Processing. Parts of Speech tagging is the very first step following which various other processes as in chunking, parsing, named entity recognition etc. are performed. An adaptation of various machine learning methods are applied namely Hidden Markov Model (HMM), Maximum Entropy Model(MEM) and Conditional Random Field(CRF) . For HMM models, we have used the suffix information for smoothing of the emission probabilities, while for ME model, the suffix information is used as features. Similar case for the CRF as that used by ME model. The significant points brought about by thesis can be highlighted below: • Use of Hidden Markov Model for Parts Of Speech tagging purpose. To create a sophisticated tagger using small set of training corpus , resources like a Dictionary is used that improves the overall accuracy of the tagger. • Machine learning techniques have been introduced for acquiring discriminative approach. The Maximum Entropy Model and Conditional Random Field has been used for this task. Keywords: Hidden Markov Model, Maximum Entropy Model, Conditional Random Field, POS tagger.
45
Shin, Donghun. "Maximum entropy model for Korean word sense disambiguation." Thesis, 2009. http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqdiss&rft_dat=xri:pqdiss:1464536.
Full text
46
Shih, Chu-Fu, and 石儲輔. "Pseudo Maximum Likelihood in Hidden Markov Model." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/88961318150457809796.
Full textAbstract:
碩士<br>國立臺灣大學<br>應用數學科學研究所<br>104<br>Hidden Markov models are a fundamental tool in applied statistics, econometrics, and machine learning for treating data taken from multiple subpopulations. When the sequence of observations is from a discrete-time, finite-state hidden Markov model, the current practice for estimating the parameters of such models relies on local search heuristics such as the EM algorithm. A new method named as pairing method is proposed to serve as an initial estimate of the transition matrix and parameters in hidden Markov models. Under regularity conditions, it can be shown that EM leads to the maximum likelihood estimator by given a suitable initial estimate. However, there is no method of finding suitable initial points in hidden Markov model. Pairing method can provide a good initial parameter estimate which can expedite EM in terms of computing time.When the underlying state transition matrix is not taken into consideration, the marginal distribution will be
a mixture distribution while only limited information on state transition matrix is kept for inference. In order to recover full information contained in the data on transition matrix, we utilize characteristics of stochastic matrix by enlarging the Markov chain to recover information governing dynamic of transition matrix. Consistent and asymptotic normal estimators of hidden transition matrix are provided.
47
Hung, Cheng-Tse, and 洪誠澤. "Hierarchical Catalog Integrate based on the Maximum Entropy Model." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/14842545761557971657.
Full textAbstract:
碩士<br>元智大學<br>資訊工程學系<br>95<br>In many areas, information is organized in catalogs on the Web. Demands of integration two catalogs appear in many applications. These catalogs usually contain a lot of Web documents and have complicated hierarchical structures. Therefore, how to integrate two catalogs accurately becomes an important research topic.
For the catalog integration problem, past studies mainly focus on flattened catalogs, and only few papers further discuss the integration of hierarchical catalogs. To the best
of our survey, no research has discussed the improvement from additional semantic information on hierarchical catalog integration. This thesis presents an enhancement based
on the Maximum Entropy (ME) model using the hierarchical thesaurus information embedded in the catalogs and the additional semantic features expanded from an external
corpus. Experimental results on real-world catalogs indicate that the proposed approach consistently improves the integration performance.
48
Mai, Ya-Chun, and 麥雅鈞. "Applying Maximum Entropy Model in the Spatial Distribution Factors of Invading Mikania." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/98598473774325749849.
Full textAbstract:
碩士<br>國立東華大學<br>自然資源與環境學系<br>102<br>Mikania micrantha H.B.K- an invasive alien plant - is a vine plant of Asteraceae family. It has been introduced by the Forestry Bureau since 1970 for the purpose of enhancing soil and water conservation in Taiwan, and resulted in serious ecological crisis, too. It not only influenced the growth of native plants, but also changed ecological environment. Therefore, in recent years, the government has tried actively to implement the vine-removing policy for Mikania micrantha, although the effect is limited. In this study, using maximum threshold of species distribution pattern, we investigated the spatial distribution of Mikania micrantha, ranging from the north of northeastern end of Three-stack Creek to the southern tip of Gian Creek, and environmental influential factors, slope, slope direction, rainfall, population, land coverage, non-urban usage to establish diagrams of natural and artificial environmental factors.
The result suggested that the spatial distribution of the specie resulted not just from single environmental condition. According to our study, the spatial-distributing ratio of Mikania micrantha can be divided into high-potential areas, mid-potential areas, and low-potential areas. Among all of the environmental factors, land coverage plays a crucial role for Mikania micrantha’s spatial distribution.
49
Chang, I.-Ming, and 張溢明. "Applying Maximum Entropy Species Distribution Model on the Study of Amaranthus viridis L." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/b3x82g.
Full textAbstract:
碩士<br>逢甲大學<br>土地管理所<br>100<br>The national or urban development is one of competitive approaches when the organizations are under the pressure of economic growth. The Main factor of change in ecosystem is led by human activity. The original ecosystem has been interfered by cultivation, deforestation, human development, plant introduction, and even led to the migration of native species or could not survived. The vegetation community also has the same problem.
The original vegetation communities were influenced by different form, composition or distribution. The key biological and non-biological factors which were included human factors, rainfall, soil, topography and geology. The space had cited by human activities to the development of many species in habitats besides the original and had threatened steadily native vegetation communities with unnatural distribution, growth and decline.
The research which is applying species distribution model referred the GBIF and TaiBIF data portal as data source to build the distribution. The relationship between distribution in invasive plant(Amaranthus viridis L.) and environment is discussed with maximum entropy method(Maxent), statistics methods, geographic information system(GIS), and digital elevation model. Lastly, the space database could be a reference for invasive plants in the future.
50
Miller, Steven R. "A regional policy simulation and forecast model for the state of Oklahoma a maximum entropy approach /." 2005. http://digital.library.okstate.edu/etd/umi-okstate-1554.pdf.
Full text