A Python package for Bayesian estimation using Markov Chain Monte Carlo

Markov chain Monte Carlo (MCMC) estimation provides a solution to the complex integration problems that are faced in the Bayesian analysis of statistical problems. The implementation of MCMC algorithms is, however, code intensive and time consuming. We have developed a Python package, which is called PyMCMC, that aids in the construction of MCMC samplers and helps to substantially reduce the likelihood of coding error, as well as aid in the minimisation of repetitive code. PyMCMC contains classes for Gibbs, Metropolis Hastings, independent Metropolis Hastings, random walk Metropolis Hastings, orientational bias Monte Carlo and slice samplers as well as specific modules for common models such as a module for Bayesian regression analysis. PyMCMC is straightforward to optimise, taking advantage of the Python libraries Numpy and Scipy, as well as being readily extensible with C or Fortran.

An efficient public key management system : an application in vehicular ad hoc networks

The major purpose of Vehicular Ad Hoc Networks (VANETs) is to provide safety-related message access for motorists to react or make a life-critical decision for road safety enhancement. Accessing safety-related information through the use of VANET communications, therefore, must be protected, as motorists may make critical decisions in response to emergency situations in VANETs. If introducing security services into VANETs causes considerable transmission latency or processing delays, this would defeat the purpose of using VANETs to improve road safety. Current research in secure messaging for VANETs appears to focus on employing certificate-based Public Key Cryptosystem (PKC) to support security. The security overhead of such a scheme, however, creates a transmission delay and introduces a time-consuming verification process to VANET communications. This paper proposes an efficient public key management system for VANETs: the Public Key Registry (PKR) system. Not only does this paper demonstrate that the proposed PKR system can maintain security, but it also asserts that it can improve overall performance and scalability at a lower cost, compared to the certificate-based PKC scheme. It is believed that the proposed PKR system will create a new dimension to the key management and verification services for VANETs.

Indigenous mathematics : creating an equitable learning environment

This chapter examines how a change in school leadership can successfully address competencies in complex situations and thus create a positive learning environment in which Indigenous students can excel in their learning rather than accept a culture that inhibits school improvement. Mathematics has long been an area that has failed to assist Indigenous students in improving their learning outcomes, as it is a Eurocentric subject (Rothbaum, Weisz, Pott, Miyake & Morelli, 2000, De Plevitz, 2007) and does not contextualize pedagogy with Indigenous culture and perspectives (Matthews, Cooper & Baturo, 2007). The chapter explores the work of a team of Indigenous and non-Indigenous academics from the YuMi Deadly Centre who are turning the tide on improving Indigenous mathematical outcomes in schools and in communities with high numbers of Aboriginal and Torres Strait Islander students.

Primary students' performance on map tasks : the role of context

This study investigated the longitudinal performance of 583 students on six map items that were represented in various graphic forms. Specifically, this study compared the performance of 7-9-year-olds (across Grades 2 and 3) from metropolitan and non-metropolitan locations. The results of the study revealed significant performance differences in favour of metropolitan students on two of six map tasks. Implications include the need for teachers in non-metropolitan locations to ensure that their students do not overly fixate on landmarks represented on maps but rather consider the arrangement of all elements encompassed within the graphic.

The application of the statutory derivative action in Pt 2F.1A of the Corporations Act to companies in liquidation under Ch 5 : Well oiled machine or is Pt 2F.1A in need of a tune up?

The statutory derivative action was introduced in Australia in 2000. This right of action has been debated in the literature and introduced in a number of other jurisdictions as well. However, it is by no means clear that all issues have been resolved despite its operation in Australia for over 10 years. This article considers the application of Pt 2F.1A of the Corporations Act to companies in liquidation under Ch 5. It demonstrates that the application involves consideration of not only proper statutory interpretation but also policy matters around the role and the supervision by the court of a liquidator once a company has entered liquidation.

Asymptotic and numerical results for a model of solvent-dependent drug diffusion through polymeric spheres

A model for drug diffusion from a spherical polymeric drug delivery device is considered. The model contains two key features. The first is that solvent diffuses into the polymer, which then transitions from a glassy to a rubbery state. The interface between the two states of polymer is modelled as a moving boundary, whose speed is governed by a kinetic law; the same moving boundary problem arises in the one-phase limit of a Stefan problem with kinetic undercooling. The second feature is that drug diffuses only through the rubbery region, with a nonlinear diffusion coefficient that depends on the concentration of solvent. We analyse the model using both formal asymptotics and numerical computation, the latter by applying a front-fixing scheme with a finite volume method. Previous results are extended and comparisons are made with linear models that work well under certain parameter regimes. Finally, a model for a multi-layered drug delivery device is suggested, which allows for more flexible control of drug release.

The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network

Sample complexity results from computational learning theory, when applied to neural network learning for pattern classification problems, suggest that for good generalization performance the number of training examples should grow at least linearly with the number of adjustable parameters in the network. Results in this paper show that if a large neural network is used for a pattern classification problem and the learning algorithm finds a network with small weights that has small squared error on the training patterns, then the generalization performance depends on the size of the weights rather than the number of weights. For example, consider a two-layer feedforward network of sigmoid units, in which the sum of the magnitudes of the weights associated with each unit is bounded by A and the input dimension is n. We show that the misclassification probability is no more than a certain error estimate (that is related to squared error on the training set) plus A3 √((log n)/m) (ignoring log A and log m factors), where m is the number of training patterns. This may explain the generalization performance of neural networks, particularly when the number of training examples is considerably smaller than the number of weights. It also supports heuristics (such as weight decay and early stopping) that attempt to keep the weights small during training. The proof techniques appear to be useful for the analysis of other pattern classifiers: when the input domain is a totally bounded metric space, we use the same approach to give upper bounds on misclassification probability for classifiers with decision boundaries that are far from the training examples.

Boosting the margin: A new explanation for the effectiveness of voting methods

One of the surprising recurring phenomena observed in experiments with boosting is that the test error of the generated classifier usually does not increase as its size becomes very large, and often is observed to decrease even after the training error reaches zero. In this paper, we show that this phenomenon is related to the distribution of margins of the training examples with respect to the generated voting classification rule, where the margin of an example is simply the difference between the number of correct votes and the maximum number of votes received by any incorrect label. We show that techniques used in the analysis of Vapnik's support vector classifiers and of neural networks with small weights can be applied to voting methods to relate the margin distribution to the test error. We also show theoretically and experimentally that boosting is especially effective at increasing the margins of the training examples. Finally, we compare our explanation to those based on the bias-variance decomposition.

Rademacher and Gaussian complexities: Risk bounds and structural results

We investigate the use of certain data-dependent estimates of the complexity of a function class, called Rademacher and Gaussian complexities. In a decision theoretic setting, we prove general risk bounds in terms of these complexities. We consider function classes that can be expressed as combinations of functions from basis classes and show how the Rademacher and Gaussian complexities of such a function class can be bounded in terms of the complexity of the basis classes. We give examples of the application of these techniques in finding data-dependent risk bounds for decision trees, neural networks and support vector machines.

A hardware-based multi-disciplinary design optimization method for aeronautical applications

There are many applications in aeronautics where there exist strong couplings between disciplines. One practical example is within the context of Unmanned Aerial Vehicle(UAV) automation where there exists strong coupling between operation constraints, aerodynamics, vehicle dynamics, mission and path planning. UAV path planning can be done either online or offline. The current state of path planning optimisation online UAVs with high performance computation is not at the same level as its ground-based offline optimizer's counterpart, this is mainly due to the volume, power and weight limitations on the UAV; some small UAVs do not have the computational power needed for some optimisation and path planning task. In this paper, we describe an optimisation method which can be applied to Multi-disciplinary Design Optimisation problems and UAV path planning problems. Hardware-based design optimisation techniques are used. The power and physical limitations of UAV, which may not be a problem in PC-based solutions, can be approached by utilizing a Field Programmable Gate Array (FPGA) as an algorithm accelerator. The inevitable latency produced by the iterative process of an Evolutionary Algorithm (EA) is concealed by exploiting the parallelism component within the dataflow paradigm of the EA on an FPGA architecture. Results compare software PC-based solutions and the hardware-based solutions for benchmark mathematical problems as well as a simple real world engineering problem. Results also indicate the practicality of the method which can be used for more complex single and multi objective coupled problems in aeronautical applications.

Multiview point cloud kernels for semisupervised learning [Lecture Notes]

In semisupervised learning (SSL), a predictive model is learn from a collection of labeled data and a typically much larger collection of unlabeled data. These paper presented a framework called multi-view point cloud regularization (MVPCR), which unifies and generalizes several semisupervised kernel methods that are based on data-dependent regularization in reproducing kernel Hilbert spaces (RKHSs). Special cases of MVPCR include coregularized least squares (CoRLS), manifold regularization (MR), and graph-based SSL. An accompanying theorem shows how to reduce any MVPCR problem to standard supervised learning with a new multi-view kernel.

Correction to “The Importance of Convexity in Learning With Squared Loss” [Sep 98 1974-1980]

The paper "the importance of convexity in learning with squared loss" gave a lower bound on the sample complexity of learning with quadratic loss using a nonconvex function class. The proof contains an error. We show that the lower bound is true under a stronger condition that holds for many cases of interest.

A systematic approach to evaluate the process improvement in lean manufacturing organizations

Numerous tools and techniques have been developed to eliminate or reduce waste and carry out Lean concepts in the manufacturing environment. However, in practice, manufacturers encounter difficulties to clearly identify the weaknesses of the existing processes in order to address them by implementing Lean tools. Moreover, selection and implementation of appropriate Lean strategies to address the problems identified is a challenging task. According best of authors‟ knowledge, there is no method available to quantitatively evaluate the cost and benefits of implementing a Lean strategy to address the weaknesses in the manufacturing process. Therefore, benefits of Lean approaches cannot be clearly established. The authors developed a methodology to quantitatively measure the performances of a manufacturing system in detecting the causes of inefficiencies and to select appropriate Lean strategies to address the problems identified. The proposed methodology demonstrates that the Lean strategies should be implemented based on the contexts of the organization and identified problem in order to achieve maximum cost benefits. Finally, a case study has been presented to demonstrate how the procedure developed works in practical situation.

Overcoming the complexity of diagnostic problems due to sensor network architecture

In fault detection and diagnostics, limitations coming from the sensor network architecture are one of the main challenges in evaluating a system’s health status. Usually the design of the sensor network architecture is not solely based on diagnostic purposes, other factors like controls, financial constraints, and practical limitations are also involved. As a result, it quite common to have one sensor (or one set of sensors) monitoring the behaviour of two or more components. This can significantly extend the complexity of diagnostic problems. In this paper a systematic approach is presented to deal with such complexities. It is shown how the problem can be formulated as a Bayesian network based diagnostic mechanism with latent variables. The developed approach is also applied to the problem of fault diagnosis in HVAC systems, an application area with considerable modeling and measurement constraints.

Exponentiated gradient algorithms for large-margin structured classification

We consider the problem of structured classification, where the task is to predict a label y from an input x, and y has meaningful internal structure. Our framework includes supervised training of Markov random fields and weighted context-free grammars as special cases. We describe an algorithm that solves the large-margin optimization problem defined in [12], using an exponential-family (Gibbs distribution) representation of structured objects. The algorithm is efficient—even in cases where the number of labels y is exponential in size—provided that certain expectations under Gibbs distributions can be calculated efficiently. The method for structured labels relies on a more general result, specifically the application of exponentiated gradient updates [7, 8] to quadratic programs.