1,721,104 research outputs found
Adaptive hidden Markov model estimation and applications
No full textInitially introduced in the late 1960's and early 1970's, hidden Markov models (HMMs) have become increasingly popular in the last decade. The major reason for the increasing popularity of HMMs has been the richness of the model class and the power of the signal processing tools. \ud
\ud
In this thesis we propose several algorithms for estimation of HMM parameters. Initially, we propose recursive prediction error algorithms for separately estimating the state values and the state transition probability matrix. Local convergence results and corresponding convergence rates are obtained via an ordinary differential equation (ODE) approach. Suboptimal extended least squares algorithms are also presented and convergence results are established in idealized situations. These algorithms exploit the discrete-valued nature of HMMs. \ud
\ud
Following this, globally convergent parameter estimators for HMMs are presented. These estimators have parallels to the well known Baum-Welch EM algorithm for off-line estimation of HMM parameters. Almost sure convergence results and convergence rates results are established using martingale convergence results, the Kronecker lemma and an ODE approach. This inspires the proposal of globally convergent parameter estimators for partially observed linear systems and hybrid linear systems. Almost sure convergence results are established using martingale convergence results, the Kronecker lemma and an ODE approach. Finally, as a contribution towards applications, optimal HMM filters are developed for demodulation of differentially encoded transmission systems and a decision feedback equalizer is proposed
Precision guidance with impact angle requirements
No full textThe weapon system guidance problem involves designing control algorithms to achieve weapon trajectories with predetermined interception conditions. The need to investigate precision guidance of weapon systems results from recent developments in weapon systems and sub-systems as well as changes in the deployment and operational philosophies.\ud
\ud
New precision guidance problems have been posed that include requirements involving impact angle criteria in addition to the requirement for zero miss-distance. These new interception requirements facilitate optimization of the warhead/fuzing and seeker components and hence maximise weapon effectiveness. This paper proposes and analyses two solutions to this precision guidance problem.\ud
\ud
The key contribution of this paper is a model of the engagement that highlights the structural properties of weapon trajectories that achieve the precision guidance requirements.\ud
\ud
These structural properties are used to develop an ad hoc controller and are further developed to proposed an optimal control solution.\ud
\ud
The two proposed control algorithms are examined both through theory and simulation studies for a variety of engagement configurations.\ud
\ud
An improved understanding of the precision guidance problem is developed in this paper and this understanding will enable a more thorough and efficient response to the Department of Defence's requirements for assessment, evaluation, advice and modification of weapon systems
Estimation of Manoeuvring Targets using Hybrid Filters
No full textModern guided weapons are frequently required to operate in a complex environment that often involve highly complicated behaviours. In these types of engagements, assumptions of linearity no longer hold and model uncertainties in the form of unmeasured aerodynamic coefficients and complex non-linear aerodynamics are common. The target filter is an important sub-system of any guidance loop that extimates the required target and engagement information. To improve the performance of this target filter in challenging environments involving manoeuvring target, a fill understanding of any non-linearities present is required.\ud
\ud
The aim of this report is to investigate the manoeuvring target filtering problem, to examine the importance of mode measurements and to examine a particular filtering approach. A review of existing filtering results is provided before introducing a non-linear filtering approach known as hybrid filtering. Three possible filtering approaches are examined in simulation studies: the extended Kalman filter, the interacting multiple model filter and a new hybrid filtering approach. The simulation studies suggest that mode measurements may improve target filtering performance but the studies do not support the use of the examined hybrid filtering approach. Some refinement of this hybrid filtering approach is required.\ud
\ud
An improved understanding of filtering techniques is required to aid support of present upgrade programs involving the guidance loops of new air-to-air and standoff missile systems. This understanding is necessary for the support of future weapon procurement upgrade programs
Risk-sensitive filtering and parameter estimation
No full textThis paper investigates the use of risk-senstive filtering for state and parameter estimation in systems with model uncertainties. Modelling uncertainties arise from imperfectly known input process and noise characteristics as well as system model errors such as uncertain or time varying parameters of the system description. No new convergence results are given in this paper but simulation examples demonstrate that, in some situations, risk-sensitive filtering and estimation techniques allow for system uncertainties better than optimal techniques such as Kalman filterin
Partially Observed Non-linear Risk-sensitive Optimal Stopping Control for Non-linear Discrete-time Systems
No full textIn this paper we introduce and solve the partially observed optimal stopping\ud
non-linear risk-sensitive stochastic control problem for discrete-time non-linear\ud
systems. The presented results are closely related to \ud
previous results for finite\ud
horizon partially observed risk-sensitive stochastic control problem. An\ud
information state approach is used and a new (three-way) separation principle established\ud
that leads to a forward dynamic programming equation and a backward \ud
dynamic programming inequality equation (both infinite dimensional). \ud
A verification theorem is \ud
given that establishes the optimal control and optimal stopping time. \ud
The risk-neutral optimal\ud
stopping stochastic control problem is also discussed
Optimal stopping time guidance: deterministic and stochastic targets
No full textThis paper describes a missile guidance problem in which the objective is to guide an interceptor missile towards both deterministic and stochastic targets. We show how this guidance problem can be naturally posed within an optimal stopping time control framework (where both the control and time horizon are designed to optimize a performance index). We believe this to be the first time the missile guidance problem has been posed as an optimal stopping problem. Solutions to the optimal stopping guidance problem are obtained via dynamic programming principles; however, no closed form solutions are apparent. Numeric-solutions are obtained via the Markov chain numerical approximation procedure
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Automated centralised separation management with onboard decision support
No full textThis paper proposes a novel automated separation\ud
management concept in which onboard decision\ud
support is integrated within a centralised\ud
air traffic separation management system. The\ud
onboard decision support system involves a decentralised\ud
separation manager that can overrule\ud
air traffic management instructions under certain\ud
circumstances. This approach allows the\ud
advantages of both centralised and decentralised\ud
concepts to be combined (and disadvantages of\ud
each separation management approach to be mitigated).\ud
Simulation studies are used to illustrate\ud
the potential benefits of the combined separation\ud
management concept
- …
