Simulation-based fully Bayesian experimental design for mixed effects models

In this paper, we present fully Bayesian experimental designs for nonlinear mixed effects models, in which we develop simulation-based optimal design methods to search over both continuous and discrete design spaces. Although Bayesian inference has commonly been performed on nonlinear mixed effects models, there is a lack of research into performing Bayesian optimal design for nonlinear mixed effects models that require searches to be performed over several design variables. This is likely due to the fact that it is much more computationally intensive to perform optimal experimental design for nonlinear mixed effects models than it is to perform inference in the Bayesian framework. In this paper, the design problem is to determine the optimal number of subjects and samples per subject, as well as the (near) optimal urine sampling times for a population pharmacokinetic study in horses, so that the population pharmacokinetic parameters can be precisely estimated, subject to cost constraints. The optimal sampling strategies, in terms of the number of subjects and the number of samples per subject, were found to be substantially different between the examples considered in this work, which highlights the fact that the designs are rather problem-dependent and require optimisation using the methods presented in this paper.

A Bayesian hurdle model for analysis of an insect resistance monitoring database

Motivated by the analysis of the Australian Grain Insect Resistance Database (AGIRD), we develop a Bayesian hurdle modelling approach to assess trends in strong resistance of stored grain insects to phosphine over time. The binary response variable from AGIRD indicating presence or absence of strong resistance is characterized by a majority of absence observations and the hurdle model is a two step approach that is useful when analyzing such a binary response dataset. The proposed hurdle model utilizes Bayesian classification trees to firstly identify covariates and covariate levels pertaining to possible presence or absence of strong resistance. Secondly, generalized additive models (GAMs) with spike and slab priors for variable selection are fitted to the subset of the dataset identified from the Bayesian classification tree indicating possibility of presence of strong resistance. From the GAM we assess trends, biosecurity issues and site specific variables influencing the presence of strong resistance using a variable selection approach. The proposed Bayesian hurdle model is compared to its frequentist counterpart, and also to a naive Bayesian approach which fits a GAM to the entire dataset. The Bayesian hurdle model has the benefit of providing a set of good trees for use in the first step and appears to provide enough flexibility to represent the influence of variables on strong resistance compared to the frequentist model, but also captures the subtle changes in the trend that are missed by the frequentist and naive Bayesian models.

Optimal Bayesian experimental design for models with intractable likelihoods using indirect inference applied to biological process models

This paper addresses the problem of determining optimal designs for biological process models with intractable likelihoods, with the goal of parameter inference. The Bayesian approach is to choose a design that maximises the mean of a utility, and the utility is a function of the posterior distribution. Therefore, its estimation requires likelihood evaluations. However, many problems in experimental design involve models with intractable likelihoods, that is, likelihoods that are neither analytic nor can be computed in a reasonable amount of time. We propose a novel solution using indirect inference (II), a well established method in the literature, and the Markov chain Monte Carlo (MCMC) algorithm of Müller et al. (2004). Indirect inference employs an auxiliary model with a tractable likelihood in conjunction with the generative model, the assumed true model of interest, which has an intractable likelihood. Our approach is to estimate a map between the parameters of the generative and auxiliary models, using simulations from the generative model. An II posterior distribution is formed to expedite utility estimation. We also present a modification to the utility that allows the Müller algorithm to sample from a substantially sharpened utility surface, with little computational effort. Unlike competing methods, the II approach can handle complex design problems for models with intractable likelihoods on a continuous design space, with possible extension to many observations. The methodology is demonstrated using two stochastic models; a simple tractable death process used to validate the approach, and a motivating stochastic model for the population evolution of macroparasites.

Integrated plasma-aided nanofabrication facility: Operation, parameters, and assembly of quantum structures and functional nanomaterials

The development, operation, and applications of two configurations of an integrated plasma-aided nanofabrication facility (IPANF) comprising low-frequency inductively coupled plasma-assisted, low-pressure, multiple-target RF magnetron sputtering plasma source, are reported. The two configurations of the plasma source have different arrangements of the RF inductive coil: a conventional external flat spiral "pancake" coil and an in-house developed internal antenna comprising two orthogonal RF current sheets. The internal antenna configuration generates a "unidirectional" RF current that deeply penetrates into the plasma bulk and results in an excellent uniformity of the plasma over large areas and volumes. The IPANF has been employed for various applications, including low-temperature plasma-enhanced chemical vapor deposition of vertically aligned single-crystalline carbon nanotips, growth of ultra-high aspect ratio semiconductor nanowires, assembly of optoelectronically important Si, SiC, and Al1-xInxN quantum dots, and plasma-based synthesis of bioactive hydroxyapatite for orthopedic implants.

Degradation modeling and monitoring of machines using operation-specific hidden Markov models

In this paper, a novel data-driven approach to monitoring of systems operating under variable operating conditions is described. The method is based on characterizing the degradation process via a set of operation-specific hidden Markov models (HMMs), whose hidden states represent the unobservable degradation states of the monitored system while its observable symbols represent the sensor readings. Using the HMM framework, modeling, identification and monitoring methods are detailed that allow one to identify a HMM of degradation for each operation from mixed-operation data and perform operation-specific monitoring of the system. Using a large data set provided by a major manufacturer, the new methods are applied to a semiconductor manufacturing process running multiple operations in a production environment.

Using the Alliance Form for Operation and Maintenance of Privatized Infrastructures

A significant number of privatizations utilized to operate and maintain critical networked infrastructures have failed to meet contractual expectations and the expectations of the community. The author carried out empirical research ex-ploring four urban water systems. This research revealed that of the four forms of privatization the alliance form was particularly suited to the stewardship of an ur-ban water system. The question then is whether these findings from urban water can be generalised to O&M of infrastructure generally. The answer is increasingly important as governments seek financial sustainability through reapplying the contestability strategy and outsource and privatise further services and activities. This paper first examines the issues encountered with O & M privatisations. Second the findings as to the stewardship achieved by the four case study water systems are unpacked with particular focus upon the alliance form. Third the key variables which were found to have distinct causal links to the stewardship-like behaviour of the private participants in the Alliance case study are described. Fourth the variables which may be crucial to the successful application of the alliance form to the broader range of infrastructures are separated out. Fifth this paper then sets the path for research into these crucial features of the alliance form.

Low-frequency, high-density, inductively coupled plasma sources : operation and applications

Operation regimes, plasma parameters, and applications of the low-frequency (∼500 kHz) inductively coupled plasma (ICP) sources with a planar external coil are investigated. It is shown that highly uniform, high-density (ne∼9×1012 cm-3) plasmas can be produced in low-pressure argon discharges with moderate rf powers. The low-frequency ICP sources operate in either electrostatic (E) or electromagnetic (H) regimes in a wide pressure range without any Faraday shield or an external multipolar magnetic confinement, and exhibit high power transfer efficiency, and low circuit loss. In the H mode, the ICP features high level of uniformity over large processing areas and volumes, low electron temperatures, and plasma potentials. The low-density, highly uniform over the cross-section, plasmas with high electron temperatures and plasma and sheath potentials are characteristic to the electrostatic regime. Both operation regimes offer great potential for various plasma processing applications. As examples, the efficiency of the low-frequency ICP for steel nitriding and plasma-enhanced chemical vapor deposition of hydrogenated diamond-like carbon (DLC) films, is demonstrated. It appears possible to achieve very high nitriding rates and dramatically increase micro-hardness and wear resistance of the AISI 304 stainless steel. It is also shown that the deposition rates and mechanical properties of the DLC films can be efficiently controlled by selecting the discharge operating regime.

Nanoparticle emissions from a fleet of CNG buses in transient and steady state operation

Particle emission measurements from a fleet of 14 CNG and 5 Diesel buses were measured both for transient and steady state mode s on a chassis dynamometer with a CVS dilution system. Several transient DT80 cycles and 4 steady sate modes (0, 25, 50 100% of maximum load) were measured for each bus tested. Particle number concentration data was collected by three CPC’s (TSI 3022, 3010 3782WCPC) having D50 cut-offs set to 5, 10 and 20nm respectively. The size distributions were measured with a TSI 3080 SMPS with a 3025 CPC during the steady state modes. Particle mass emissions were measured with a TSI Dustrak. Particle mass emissions for Diesel buses were upto 2 orders of magnitude higher than for CNG buses. Particle number emissions during steady state modes for Diesel busses were 2 to 5 times higher than for CNG busses for all of the tested loads. On the other hand for the DT80 transient cycle particle number emissions were up to 3 times higher for the CNG buses. More detailed analysis of the transient cycles revealed that the reason for this was due to high particle number emissions from CNG busses during the acceleration parts of the cycles. Particles emitted by the CNG busses during acceleration were in the nucleation mode with the majority being smaller than 10nm. Volatility measurements have also shown that they were highly volatile.

Defining the spatiotemporal surveillance space for alien species’ invasions using approximate Bayesian computation

The spatiotemporal dynamics of an alien species invasion across a real landscape are typically complex. While surveillance is an essential part of a management response, planning surveillance in space and time present a difficult challenge due to this complexity. We show here a method for determining the highest probability sites for occupancy across a landscape at an arbitrary point in the future, based on occupancy data from a single slice in time. We apply to the method to the invasion of Giant Hogweed, a serious weed in the Czech republic and throughout Europe.

A review of modern computational algorithms for Bayesian optimal design

Bayesian experimental design is a fast growing area of research with many real-world applications. As computational power has increased over the years, so has the development of simulation-based design methods, which involve a number of algorithms, such as Markov chain Monte Carlo, sequential Monte Carlo and approximate Bayes methods, facilitating more complex design problems to be solved. The Bayesian framework provides a unified approach for incorporating prior information and/or uncertainties regarding the statistical model with a utility function which describes the experimental aims. In this paper, we provide a general overview on the concepts involved in Bayesian experimental design, and focus on describing some of the more commonly used Bayesian utility functions and methods for their estimation, as well as a number of algorithms that are used to search over the design space to find the Bayesian optimal design. We also discuss other computational strategies for further research in Bayesian optimal design.

Toward an object-based semantic memory for long-term operation of mobile service robots

Throughout a lifetime of operation, a mobile service robot needs to acquire, store and update its knowledge of a working environment. This includes the ability to identify and track objects in different places, as well as using this information for interaction with humans. This paper introduces a long-term updating mechanism, inspired by the modal model of human memory, to enable a mobile robot to maintain its knowledge of a changing environment. The memory model is integrated with a hybrid map that represents the global topology and local geometry of the environment, as well as the respective 3D location of objects. We aim to enable the robot to use this knowledge to help humans by suggesting the most likely locations of specific objects in its map. An experiment using omni-directional vision demonstrates the ability to track the movements of several objects in a dynamic environment over an extended period of time.

Cost efficiency of Japanese steam power generation companies : a Bayesian comparison of random and fixed frontier models

This study analyses and compares the cost efficiency of Japanese steam power generation companies using the fixed and random Bayesian frontier models. We show that it is essential to account for heterogeneity in modelling the performance of energy companies. Results from the model estimation also indicate that restricting CO2 emissions can lead to a decrease in total cost. The study finally discusses the efficiency variations between the energy companies under analysis, and elaborates on the managerial and policy implications of the results.