Bagging and the Bayesian Bootstrap

Bagging is a method of obtaining more ro- bust predictions when the model class under consideration is unstable with respect to the data, i.e., small changes in the data can cause the predicted values to change significantly. In this paper, we introduce a Bayesian ver- sion of bagging based on the Bayesian boot- strap. The Bayesian bootstrap resolves a the- oretical problem with ordinary bagging and often results in more efficient estimators. We show how model averaging can be combined within the Bayesian bootstrap and illustrate the procedure with several examples.

Bayesian Model Averaging in the M-Open Framework

This chapter presents a model averaging approach in the M-open setting using sample re-use methods to approximate the predictive distribution of future observations. It first reviews the standard M-closed Bayesian Model Averaging approach and decision-theoretic methods for producing inferences and decisions. It then reviews model selection from the M-complete and M-open perspectives, before formulating a Bayesian solution to model averaging in the M-open perspective. It constructs optimal weights for MOMA:M-open Model Averaging using a decision-theoretic framework, where models are treated as part of the ‘action space’ rather than unknown states of nature. Using ‘incompatible’ retrospective and prospective models for data from a case-control study, the chapter demonstrates that MOMA gives better predictive accuracy than the proxy models. It concludes with open questions and future directions.

SMERED: A Bayesian Approach to Graphical Record Linkage and De-duplication

We propose a novel unsupervised approach for linking records across arbitrarily many files, while simultaneously detecting duplicate records within files. Our key innovation is to represent the pattern of links between records as a {\em bipartite} graph, in which records are directly linked to latent true individuals, and only indirectly linked to other records. This flexible new representation of the linkage structure naturally allows us to estimate the attributes of the unique observable people in the population, calculate $k$-way posterior probabilities of matches across records, and propagate the uncertainty of record linkage into later analyses. Our linkage structure lends itself to an efficient, linear-time, hybrid Markov chain Monte Carlo algorithm, which overcomes many obstacles encountered by previously proposed methods of record linkage, despite the high dimensional parameter space. We assess our results on real and simulated data.

Continuous-wave operation of a modulational instability laser

post-deadline paper

Optimizing the operation of straight-grate iron-ore pellet induration systems using process models

Mathematical models of straight-grate pellet induration processes have been developed and carefully validated by a number of workers over the past two decades. However, the subsequent exploitation of these models in process optimization is less clear, but obviously requires a sound understanding of how the key factors control the operation. In this article, we show how a thermokinetic model of pellet induration, validated against operating data from one of the Iron Ore Company of Canada (IOCC) lines in Canada, can be exploited in process optimization from the perspective of fuel efficiency, production rate, and product quality. Most existing processes are restricted in the options available for process optimization. Here, we review the role of each of the drying (D), preheating (PH), firing (F), after-firing (AF), and cooling (C) phases of the induration process. We then use the induration process model to evaluate whether the first drying zone is best to use on the up- or down-draft gas-flow stream, and we optimize the on-gas temperature profile in the hood of the PH, F, and AF zones, to reduce the burner fuel by at least 10 pct over the long term. Finally, we consider how efficient and flexible the process could be if some of the structural constraints were removed (i.e., addressed at the design stage). The analysis suggests it should be possible to reduce the burner fuel lead by 35 pct, easily increase production by 5+ pct, and improve pellet quality.

Scheduling three-operation jobs in a two-machine flow shop to minimize makespan

This paper considers a variant of the classical problem of minimizing makespan in a two-machine flow shop. In this variant, each job has three operations, where the first operation must be performed on the first machine, the second operation can be performed on either machine but cannot be preempted, and the third operation must be performed on the second machine. The NP-hard nature of the problem motivates the design and analysis of approximation algorithms. It is shown that a schedule in which the operations are sequenced arbitrarily, but without inserted machine idle time, has a worst-case performance ratio of 2. Also, an algorithm that constructs four schedules and selects the best is shown to have a worst-case performance ratio of 3/2. A polynomial time approximation scheme (PTAS) is also presented.

The impact of powder flowing properties on dosator filling system operation

Purpose: To study the impact of powder flow properties on dosator filling systems, with particular focus on improvements in dose weight accuracy and repeatability. Method: This study evaluates a range of critical powder flow properties such as: flow function, cohesion, wall friction, adhesion to wall surfaces, density/compressibility data, stress ratio “K” and gas permeability. The characterisations of the powders considered in this study were undertaken using an annular shear cell using a sample size of 0.5 litres. This tester also incorporated the facility to measure bed expansion during shear in addition to contraction under consolidation forces. A modified Jenike type linear wall friction tester was used to develop the failure loci for the powder sample in conjunction with multiple wall samples (representing a variety of material types and surface finishes). Measurements of the ratio of applied normal stress versus lateral stress were determined using a piece of test equipment specifically designed for the purpose. Results: The correct characterisation of powders and the incorporation of this data into the design of process equipment are recognised as critical for reliable and accurate operation. An example of one aspect of this work is the stress ratio “K”. This characteristic is not well understood or correctly interpreted in many cases – despite its importance. Fig 1 [Omitted] (illustrates a sample of test data. The slope of the line gives the stress ratio in a uniaxial compaction system – indicating the behaviour of the material under compaction during dosing processes. Conclusions: A correct assessment of the bulk powder properties for a given formulation can allow prediction of: cavity filling behaviour (and hence dosage), efficiency of release from dosator, and strength and stability of extruded dose en route to capsule filling Influences over the effectiveness of dosator systems have been shown to be impacted upon by: bed pre-compaction history, gas permeability in the bed (with respect to local density effects), and friction effects for materials of construction for dosators

Modelling of dosator operation for improved manufacturing performance

Purpose: To develop an improved mathematical model for the prediction of dose accuracy of Dosators - based upon the geometry of the machine in conjunction with measured flow properties of the powder. Methods: A mathematical model has been created, based on a analytical method of differential slices - incorporating measured flow properties. The key flow properties of interest in this investigation were: flow function, effective angle of wall friction, wall adhesion, bulk density, stress ratio K and permeability. To simulate the real process and (very importantly) validate the model, a Dosator test-rig has been used to measure the forces acting on the Dosator during the filling stage, the force required to eject the dose and the dose weight. Results: Preliminary results were obtained from the Dosator test-rig. Figure 1 [Omitted] shows the dose weight for different depths to the bottom of the powder bed at the end of the stroke and different levels of pre-compaction of the powder bed. A strong influence over dose weight arising from the proximity between the Dosator and the bottom of the powder bed at the end of the stroke and the conditions of the powder bed has been established. Conclusions: The model will provide a useful tool to predict dosing accuracy and, thus, optimise the future design of Dosator based equipment technology – based on measured bulk properties of the powder to be handled. Another important factor (with a significant influence) on Dosator processes, is the condition of the powder bed and the clearance between the Dosator and the bottom of the powder bed.

Spatio-temporal Bayesian network models with latent variables for revealing trophic dynamics and functional networks in fisheries ecology

Ecosystems consist of complex dynamic interactions among species and the environment, the understanding of which has implications for predicting the environmental response to changes in climate and biodiversity. However, with the recent adoption of more explorative tools, like Bayesian networks, in predictive ecology, few assumptions can be made about the data and complex, spatially varying interactions can be recovered from collected field data. In this study, we compare Bayesian network modelling approaches accounting for latent effects to reveal species dynamics for 7 geographically and temporally varied areas within the North Sea. We also apply structure learning techniques to identify functional relationships such as prey–predator between trophic groups of species that vary across space and time. We examine if the use of a general hidden variable can reflect overall changes in the trophic dynamics of each spatial system and whether the inclusion of a specific hidden variable can model unmeasured group of species. The general hidden variable appears to capture changes in the variance of different groups of species biomass. Models that include both general and specific hidden variables resulted in identifying similarity with the underlying food web dynamics and modelling spatial unmeasured effect. We predict the biomass of the trophic groups and find that predictive accuracy varies with the models' features and across the different spatial areas thus proposing a model that allows for spatial autocorrelation and two hidden variables. Our proposed model was able to produce novel insights on this ecosystem's dynamics and ecological interactions mainly because we account for the heterogeneous nature of the driving factors within each area and their changes over time. Our findings demonstrate that accounting for additional sources of variation, by combining structure learning from data and experts' knowledge in the model architecture, has the potential for gaining deeper insights into the structure and stability of ecosystems. Finally, we were able to discover meaningful functional networks that were spatially and temporally differentiated with the particular mechanisms varying from trophic associations through interactions with climate and commercial fisheries.