Simulation-based optimal sensor scheduling with application to observer trajectory planning

The sensor scheduling problem can be formulated as a controlled hidden Markov model and this paper solves the problem when the state, observation and action spaces are continuous. This general case is important as it is the natural framework for many applications. The aim is to minimise the variance of the estimation error of the hidden state w.r.t. the action sequence. We present a novel simulation-based method that uses a stochastic gradient algorithm to find optimal actions. © 2007 Elsevier Ltd. All rights reserved.

Integrated optically triggered polarisation-switching in InGaAsP twin-stripe injection lasers

A new form of ultrafast bistable polarization switching in twin-stripe injection lasers has been observed. For the first time, triggering between bistable states has been achieved by injecting light from a neighboring laser integrated on the same chip. Ultrafast switching times of 250 ps have been measured (detector limited).

Optically triggered polarisation bistability in GaInAsP twin stripe injection lasers using integrated devices

A bistable polarization switching element and optical triggering source has been produced by etching a facet in a twin stripe semiconductor laser. The switching element is formed by a pair of stripe segments at one end of the device and triggered with short light pulses from the other two segments. Detector limited switching risetimes have been measured at 250 ps.

Two-Dimensional Kinematic Wave Model of Overland-Flow

A two-dimensional kinematic wave model was developed for simulating runoff generation and flow concentration on an experimental infiltrating hillslope receiving artificial rainfall. Experimental observations on runoff generation and flow concentration on irregular hillslopes showed that the topography of the slope surface controlled the direction and flow lines of overland flow. The model-simulated results satisfactorily compared with experimental observations. The erosive ability of the concentrated flow was found to mainly depend on the ratio of the width and depth of confluent grooves.

Uniform stability of a particle approximation of the optimal filter derivative

Sequential Monte Carlo methods, also known as particle methods, are a widely used set of computational tools for inference in non-linear non-Gaussian state-space models. In many applications it may be necessary to compute the sensitivity, or derivative, of the optimal filter with respect to the static parameters of the state-space model; for instance, in order to obtain maximum likelihood model parameters of interest, or to compute the optimal controller in an optimal control problem. In Poyiadjis et al. [2011] an original particle algorithm to compute the filter derivative was proposed and it was shown using numerical examples that the particle estimate was numerically stable in the sense that it did not deteriorate over time. In this paper we substantiate this claim with a detailed theoretical study. Lp bounds and a central limit theorem for this particle approximation of the filter derivative are presented. It is further shown that under mixing conditions these Lp bounds and the asymptotic variance characterized by the central limit theorem are uniformly bounded with respect to the time index. We demon- strate the performance predicted by theory with several numerical examples. We also use the particle approximation of the filter derivative to perform online maximum likelihood parameter estimation for a stochastic volatility model.

Asymptotic behaviour of approximate Bayesian estimators

Although approximate Bayesian computation (ABC) has become a popular technique for performing parameter estimation when the likelihood functions are analytically intractable there has not as yet been a complete investigation of the theoretical properties of the resulting estimators. In this paper we give a theoretical analysis of the asymptotic properties of ABC based parameter estimators for hidden Markov models and show that ABC based estimators satisfy asymptotically biased versions of the standard results in the statistical literature.

Parameter Estimation for Hidden Markov Models with Intractable Likelihoods

Approximate Bayesian computation (ABC) is a popular technique for analysing data for complex models where the likelihood function is intractable. It involves using simulation from the model to approximate the likelihood, with this approximate likelihood then being used to construct an approximate posterior. In this paper, we consider methods that estimate the parameters by maximizing the approximate likelihood used in ABC. We give a theoretical analysis of the asymptotic properties of the resulting estimator. In particular, we derive results analogous to those of consistency and asymptotic normality for standard maximum likelihood estimation. We also discuss how sequential Monte Carlo methods provide a natural method for implementing our likelihood-based ABC procedures.

Case Study: Influence Of Morphological Changes On Flooding In Jingjiang River

The middle reach of the Yangtze River, customarily called the Jingjiang River, together with its diversion channels and Dongting Lake, form a large complicated drainage system. In the last five decades, significant geomorphological changes have occurred in the drainage system, including the shrinkage of diversion channels, contraction of Dongting Lake, changes in the rating curve at the Luoshan station, and cutoffs of the lower Jingjiang River. These changes are believed to be the cause of the occurrence of abnormal floods in the Jingjiang River. Qualitative analyses suggest that the first three factors aggravate the flood situation in the lower Jingjiang River, while the last factor seems beneficial for flood prevention. To quantitatively evaluate these conclusions, a finite-volume numerical model was constructed. A series of numerical simulations were carried out to test the individual and combined effects of the aforementioned four factors, and these simulations showed that high flood stages in the Jingjiang River clearly are related to the geomorphological changes.

Limiting States Of Internal Wave Rays

Existing models of baroclinic tides are based upon the "traditional approximation'', i. e., neglect of the horizontal component of the Earth's rotation, leading to a well- known conclusion that no freely propagating internal waves can exist beyond the critical latitude and the wave rays are symmetric to the vertical. However, recent studies have contended that the situation may change if both the vertical and horizontal components of the Earth's rotation are taken into account. With the full account of the Coriolis force, characteristics of the internal wavefield generated by tidal flow over uneven topography are investigated. It is found that "nontraditional effects'' profoundly change not only the dynamics of internal waves but also the rate at which the barotropic tidal energy is fed into the internal wavefield. Discarding the traditional approximation, internal waves are proved to be able to generate poleward of the critical latitude, rays of which are no longer symmetric and the limiting values of ray angles become greater or less than 90 degrees, depending on the local latitude and the direction of ray. More importantly, in contrast to the predictions of models based upon the traditional approximation, a substantial conversion occurs in the situations when stratification is so weak that the buoyancy frequency is below the tidal one.

Distributed maximum likelihood for self-localization in sensor networks

We show that the sensor localization problem can be cast as a static parameter estimation problem for Hidden Markov Models and we develop fully decentralized versions of the Recursive Maximum Likelihood and the Expectation-Maximization algorithms to localize the network. For linear Gaussian models, our algorithms can be implemented exactly using a distributed version of the Kalman filter and a message passing algorithm to propagate the derivatives of the likelihood. In the non-linear case, a solution based on local linearization in the spirit of the Extended Kalman Filter is proposed. In numerical examples we show that the developed algorithms are able to learn the localization parameters well.

An overview of sequential Monte Carlo methods for parameter estimation in general state-space models

Nonlinear non-Gaussian state-space models arise in numerous applications in control and signal processing. Sequential Monte Carlo (SMC) methods, also known as Particle Filters, are numerical techniques based on Importance Sampling for solving the optimal state estimation problem. The task of calibrating the state-space model is an important problem frequently faced by practitioners and the observed data may be used to estimate the parameters of the model. The aim of this paper is to present a comprehensive overview of SMC methods that have been proposed for this task accompanied with a discussion of their advantages and limitations.

NUMERICAL ANALYSIS OF THE FLOWFIELD IN A SUPERSONIC COIL WITH AN INTERLEAVED JET CONFIGURATION AND ITS EFFECT ON THE GAIN DISTRIBUTION

In a supersonic chemical oxygen-iodine laser (COIL) operating without primary buffer gas, the features of flowfield have significant effects on the Laser efficiency and beam quality. In this paper three-dimensional, multi-species, chemically reactive CFD technology was used to study the flowfield in mixing nozzle implemented with a supersonic interleaving jet configuration. The features of the flowfield as well as its effect on the spatial distribution of small signal gain were analyzed.

Sequential Monte Carlo computation of the score and observed information matrix in state-space models with application to parameter estimation

Sequential Monte Carlo (SMC) methods are popular computational tools for Bayesian inference in non-linear non-Gaussian state-space models. For this class of models, we propose SMC algorithms to compute the score vector and observed information matrix recursively in time. We propose two different SMC implementations, one with computational complexity $\mathcal{O}(N)$ and the other with complexity $\mathcal{O}(N^{2})$ where $N$ is the number of importance sampling draws. Although cheaper, the performance of the $\mathcal{O}(N)$ method degrades quickly in time as it inherently relies on the SMC approximation of a sequence of probability distributions whose dimension is increasing linearly with time. In particular, even under strong \textit{mixing} assumptions, the variance of the estimates computed with the $\mathcal{O}(N)$ method increases at least quadratically in time. The $\mathcal{O}(N^{2})$ is a non-standard SMC implementation that does not suffer from this rapid degrade. We then show how both methods can be used to perform batch and recursive parameter estimation.