Sökning: "state space models"

Visar resultat 6 - 10 av 273 avhandlingar innehållade orden state space models.

1. 6. Probabilistic Sequence Models with Speech and Language Applications

   Författare :Gustav Eje Henter; W. Bastiaan Kleijn; Arne Leijon; Gernot Kubin; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Time series; acoustic modelling; speech synthesis; stochastic processes; causal-state splitting reconstruction; robust causal states; pattern discovery; Markov models; HMMs; nonparametric models; Gaussian processes; Gaussian process dynamical models; nonlinear Kalman filters; information theory; minimum entropy rate simplification; kernel density estimation; time-series bootstrap;

   Sammanfattning : Series data, sequences of measured values, are ubiquitous. Whenever observations are made along a path in space or time, a data sequence results. To comprehend nature and shape it to our will, or to make informed decisions based on what we know, we need methods to make sense of such data. LÄS MER

3. 7. VAR Models, Cointegration and Mixed-Frequency Data

   Författare :Sebastian Ankargren; Johan Lyhagen; Yukai Yang; Gregor Kastner; Uppsala universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; vector error correction; small open economy; mixed-frequency data; Bayesian; steady state; nowcasting; state-space model; large VARs; simulation smoothing; factor stochastic volatility; R; Statistics; Statistik;

   Sammanfattning : This thesis consists of five papers that study two aspects of vector autoregressive (VAR) modeling: cointegration and mixed-frequency data.Paper I develops a method for estimating a cointegrated VAR model under restrictions implied by the economy under study being a small open economy. LÄS MER

4. 8. Feed-forward Control and Dynamic Modelling in Temperature Control of Buildings

   Författare :Mohsen Soleimani-Mohseni; Chalmers tekniska högskola; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; building models; state space models; feedback; thermostats; transfer function models; intelligent buildings; ON-OFF controllers; Feed-forward; PIL controllers;

   Sammanfattning : This thesis is mainly about the investigations of different control strategies (and in particular feed-forward) in order to improve indoor climate and/or save energy in buildings. One part of the thesis deals with different ways to obtain dynamic models for climate systems in buildings. LÄS MER

5. 9. Numerical modeling of auroral processes

   Författare :Jörgen Vedin; Kjell Rönnmark; Robert Lysak; Umeå universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; space plasma physics; auroral acceleration region; auroral current circuit; Alfvén waves; parallel electric fields; equation of state; fluid simulation; PIC simulation; Space physics; Rymdfysik;

   Sammanfattning : One of the most conspicuous problems in space physics for the last decades has been to theoretically describe how the large parallel electric fields on auroral field lines can be generated. There is strong observational evidence of such electric fields, and stationary theory supports the need for electric fields accelerating electrons to the ionosphere where they generate auroras. LÄS MER

7. 10. On Bounds and Asymptotics of Sequential Monte Carlo Methods for Filtering, Smoothing, and Maximum Likelihood Estimation in State Space Models

   Författare :Jimmy Olsson; Matematisk statistik; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; actuarial mathematics; programming; operations research; Statistics; Matematik; Mathematics; state space models; smoothing; sequential Monte Carlo; particle filter; EM algorithm; maximum likelihood; consistency; Asymptotic normality; Statistik; operationsanalys; programmering; aktuariematematik;

   Sammanfattning : This thesis is based on four papers (A-D) treating filtering, smoothing, and maximum likelihood (ML) estimation in general state space models using stochastic particle filters (also referred to as sequential Monte Carlo (SMC) methods). The aim of Paper A is to study the bias of Monte Carlo integration estimates produced by the so-called bootstrap particle filter. LÄS MER