A Bayesian framework for learning shared and individual subspaces from multiple data sources

This paper presents a novel Bayesian formulation to exploit shared structures across multiple data sources, constructing foundations for effective mining and retrieval across disparate domains. We jointly analyze diverse data sources using a unifying piece of metadata (textual tags). We propose a method based on Bayesian Probabilistic Matrix Factorization (BPMF) which is able to explicitly model the partial knowledge common to the datasets using shared subspaces and the knowledge specific to each dataset using individual subspaces. For the proposed model, we derive an efficient algorithm for learning the joint factorization based on Gibbs sampling. The effectiveness of the model is demonstrated by social media retrieval tasks across single and multiple media. The proposed solution is applicable to a wider context, providing a formal framework suitable for exploiting individual as well as mutual knowledge present across heterogeneous data sources of many kinds.

The classification of lands managed for conservation : existing and proposed frameworks, with particular reference to Australia

Comprehensive classification systems to accurately account for lands managed for biodiversity conservation, are an essential component of conservation planning and policy. The current international classification systems for lands managed for nature conservation are reviewed, with a particular emphasis on Australia. The need for a broader, all-encompassing, categorisation of lands managed for conservation is presented and a proposed broader categorisation system is developed—the Conservation Lands Classification. This classification system has the advantage of incorporating data on both tenure and protection mechanisms and has been applied in this paper using conservation lands in three Australian jurisdictions as examples. It is envisaged that this method of classification has the potential to significantly improve the ability to measure current and future trends in nature conservation across all land types at a variety of scales and hence is put forward in order to stimulate discussion on this important topic.

A purposive approach to content analysis : designing analytical frameworks

Content analysis of computer conferences provides a rich source of data for researching and understanding online learning. However, the complexities of using content analysis in a relatively new research field have resulted in researchers often avoiding this method and using more familiar methods such as survey and interview instead. This article discusses content analysis as a methodology, with emphasis on the development of analytical frameworks. The literature indicates that researchers either use or modify existing frameworks or, more commonly, develop new ones, either through grounded theory approaches or the adaptation of existing theories, concepts or models. The development and implementation of two frameworks are then discussed in detail. Both were developed purposively to investigate and evaluate firstly collaborative learning and secondly deep and surface approaches to learning as evidenced in computer conferences. The article concludes with recommendations for framework development.

Mature workers, training and using TLM frameworks

Mature workers have been at the centre of policies aimed at encouraging higher workforce participation, longer working life and enhanced savings for retirement. Low mature age workforce participation rates reflect labour market withdrawal in the face of multiple barriers to participation for many. Their apparent voluntary joblessness conceals the fact that mature workers endure longer periods of unemployment, discrimination, redundancy and other barriers to employment (hence the drift to 'early retirement'). The policy dilemma is not just about addressing discrimination barriers, access to appropriate retraining or skills enhancement for mature workers, but what this tells us about lifelong learning as a means of managing and mitigating risk. The mismatch between work opportunities/skills shortages and the low education and skills base of many mature workers, means it is simplistic to think that working longer might be a short term way to address skills shortages; without an enormous investment in the current ageing cohort. Drawing on Transitional Labour Market (TLM) theory and European reform agendas, this article argues that the link between investment in lifelong education/ skills training and stronger labour market participation needs attention; not just for current cohorts of excluded or underemployed mature workers but to position strategically for future generations.

Evolutionary structure learning algorithm for Bayesian network and penalized mutual information metric

This paper formulates the problem of learning Bayesian network structures from data as determining the structure that best approximates the probability distribution indicated by the data. A new metric, Penalized Mutual Information metric, is proposed, and a evolutionary algorithm is designed to search for the best structure among alternatives. The experimental results show that this approach is reliable and promising.

An objective function based on Bayesian likelihoods of necessity and sufficiency for concept learning in the absence of labeled counter-examples

Supervised machine learning techniques generally require that the training set on which learning is based contain sufficient examples representative of the target concept, as well as known counter-examples of the concept; however, in many application domains it is not possible to supply a set of labeled counter-examples. This paper proposes an objective function based on Bayesian likelihoods of necessity and sufficiency. This function can be used to guide search towards the discovery of a concept description given only a set of labeled positive examples of the target concept, and as a corpus of unlabeled examples. Results of experiments performed on several datasets from the VCI repository show that the technique achieves comparable accuracy to conventional supervised learning techniques, despite the fact that the latter require a set of labeled counter-examples to be supplied. The technique can be applied in many domains in which the provision of labeled counter-examples is problematic.

Comparison of MLP and Bayesian approaches on mineral prospectivity mapping tasks

Mineral Prospectivity Mapping is the process of combining maps containing different geoscientific data sets to produce a single map depicting areas ranked according to their potential to host mineral deposits of a particular type. This paper outlines two approaches for deriving a function which can be used to assign to each cell in the study area a value representing the posterior probability that the cell contains a deposit of the sought-after mineral. One approach is based on estimating probability density functions (pdfs); the second uses multilayer perceptrons (MLPs). Results are provided from applying these approaches to geoscientific datasets covering a region in North Western Victoria, Australia. The results demonstrate that while both the Bayesian approach and the MLP approach yield similar results when the number of input dimensions is small, the Bayesian approach rapidly becomes unstable as the number of input dimensions increases, with the resulting maps displaying high sensitivity to the number of mixtures used to model the distributions. However, despite the fact that Bayesian assigned values cannot be interpreted as posterior probabilities in high dimensional input spaces, the pixel favorability rankings produced by the two methods is similar.

Transforming frameworks: new approaches to CCTs and the pursuit of educational equity

Teacher educators throughout the world are increasingly under pressure to develop educational programs and school-based relationships which respond simultaneously to the multiple consequences of changed and changing technologies, new understandings of identity (what it means to be a teacher and a student) and persistently uneven pattems of educational (and social) success. Responses to these challenges regularly draw upon computer and communication technologies (CCTs) in the sometimes optimistic belief that this will improve the chance of any educational reform having a positive impact on students at risk of educational alienation and failure. Unfortunately, the gap between the hopeful embrace of technology and the actual outcomes delivered by technologically mediated educational innovations is often quite considerable. This paper investigates the kinds of educational conversations that are necessary to allow us to move beyond these optimistic adoptions of technology to address long standing patterns of educational success and failure and outlines a framework for transformative work in this area.

Are metropolitan planning frameworks healthy? The case of Melbourne 2030

This paper presents preliminary findings of a project investigating the integration and application of ecological public health principles in Melboume 2030, the Victorian Government's urban planning blueprint for Melboume for the next 30 years. The study examines the political, organisational, social, and inter-personal factors that impact on the integration and application of broad health considerations into urban planning policy in Victoria. We are testing the premise that achieving integrated planning requires a systematic integration of government activity across sectors. Using discourse analysis and key informant interviews, we examined relevant government policy and legislation and its implementation against world's best practice. Preliminary findings show that the degree of leadership in relation to deploying the mission, and implementation processes sustain or impede integrated planning at a whole-of-government and intersectoral level.

These findings may inform a much-needed national agenda on promoting health through integrated planning. Findings will identify future research directions and action to bridge the gap between urban planning and health planning systems

Problem of precision missile guidance: LQR and H‡ control frameworks

Addressed here is the precision missile guidance problem where the successful intercept criterion has been defined in terms of both minimizing the miss distance and controlling the missile body attitude with respect to the target at the terminal point. We show that the H∞ control theory, when suitably modified, provides an effective framework for the precision missile guidance problem. The existence of feedback controllers (guidance laws) is investigated for the case of finite horizon and non-zero initial conditions. Both state feedback and output feedback implementations are explored.

Anion recognition and anion-mediated self-assembly with thiourea-functionalised fused [3]polynorbornyl frameworks

Three conformationally preorganised host molecules based on the [3]polynorbornyl framework and incorporating di-urea receptors were synthesised and their interaction with a series of anions investigated by 1H NMR spectroscopy. A high affinity of each host molecule for dihydrogenphosphate (H2PO4–) and dihydrogenpyrophosphate (H2P2O72–) was identified. In addition to binding to the urea receptors of the host molecules, evidence for an interaction involving the non-polar C–H groups within the binding cavity of the framework and guest anions was also discovered. Furthermore, an unusual 2 : 1 host-to-anion stoichiometry was indicated when binding H2P2O72–, and a model for the anion-mediated self-assembly of this complex species is proposed.