Robust mean super-resolution for less cooperative NIR iris recognition at a distance and on the move

Less cooperative iris identification systems at a distance and on the move often suffers from poor resolution. The lack of pixel resolution significantly degrades the iris recognition performance. Super-resolution has been considered to enhance resolution of iris images. This paper proposes a pixelwise super-resolution technique to reconstruct a high resolution iris image from a video sequence of an eye. A novel fusion approach is proposed to incorporate information details from multiple frames using robust mean. Experiments on the MBGC NIR portal database show the validity of the proposed approach in comparison with other resolution enhancement techniques.

Frequency decomposition techniques for increased discriminative 3D facial information capture

Eigen-based techniques and other monolithic approaches to face recognition have long been a cornerstone in the face recognition community due to the high dimensionality of face images. Eigen-face techniques provide minimal reconstruction error and limit high-frequency content while linear discriminant-based techniques (fisher-faces) allow the construction of subspaces which preserve discriminatory information. This paper presents a frequency decomposition approach for improved face recognition performance utilising three well-known techniques: Wavelets; Gabor / Log-Gabor; and the Discrete Cosine Transform. Experimentation illustrates that frequency domain partitioning prior to dimensionality reduction increases the information available for classification and greatly increases face recognition performance for both eigen-face and fisher-face approaches.

Innovation networks in the construction arena : the strategic management of mixed enterprises

The building and construction sector is one of the five largest contributors to the Australian economy and is a key performance component in the economy of many other jurisdictions. However, the ongoing viability of this sector is increasingly reliant on its ability to foster and transfer innovated products and practices. Interorganisational networks, which bring together key industry stakeholders and facilitate the flows of information, resources and trust necessary to secure innovation, have emerged as a key growth strategy within this and other arenas. The blending of organisations, resources and purposes creates new, hybrid institutional forms that draw on a mix of contract, structure and interpersonal relationship as integration processes. This paper argues that hybrid networked arrangements, because they incorporate relational elements, require management strategies and techniques that not always synonymous with conventional management approaches, including those used within the building and construction sector. It traces the emergence of the Construction Innovation Project in Australia as a hybrid institutional arrangement moulding public, private and academic stakeholders of the building and construction industry into a coherent collective force aimed at fostering innovation and its application within all levels of the industry. Specifically, the paper examines the Construction Innovation Project to ascertain the impact of relational governance and its management to harness and leverage the skills, resources and capacities of members to secure innovative outcomes. Finally, the paper offers some prospects to guide the ongoing work of this body and any other charged with a similar integrative responsibility.

Addressing sustainable living using a collaborative approach and multi-disciplinary techniques

In order to achieve meaningful reductions in individual ecological footprints, individuals must dramatically alter their day to day behaviours. Effective interventions will need to be evidence based and there is a necessity for the rapid transfer or communication of information from the point of research, into policy and practice. A number of health disciplines, including psychology and public health, share a common mission to promote health and well-being and it is becoming clear that the most practical pathway to achieving this mission is through interdisciplinary collaboration. This paper argues that an interdisciplinary collaborative approach will facilitate research that results in the rapid transfer of findings into policy and practice. The application of this approach is described in relation to the Green Living project which explored the psycho-social predictors of environmentally friendly behaviour. Following a qualitative pilot study, and in consultation with an expert panel comprising academics, industry professionals and government representatives, a self-administered mail survey was distributed to a random sample of 3000 residents of Brisbane and Moreton Bay (Queensland, Australia). The Green Living survey explored specific beliefs which included attitudes, norms, perceived control, intention and behaviour, as well as a number of other constructs such as environmental concern and altruism. This research has two beneficial outcomes. First, it will inform a practical model for predicting sustainable living behaviours and a number of local councils have already expressed an interest in making use of the results as part of their ongoing community engagement programs. Second, it provides an example of how a collaborative interdisciplinary project can provide a more comprehensive approach to research than can be accomplished by a single disciplinary project.

Improved salinity management for the Nebine / Mungallala / Wallam catchment

The low stream salinity naturally in the Nebine-Mungallala Catchment, extent of vegetation retention, relatively low rainfall and high evaporation indicates that there is a relatively low risk of rising shallow groundwater tables in the catchment. Scalding caused by wind and water erosion exposing highly saline sub-soils is a more important regional issue, such as in the Homeboin area. Local salinisation associated with evaporation of bore water from free flowing bore drains and bores is also an important land degradation issue particularly in the lower Nebine, Wallam and Mungallala Creeks. The replacement of free flowing artesian bores and bore drains with capped bores and piped water systems under the Great Artesian Basin bore rehabilitation program is addressing local salinisation and scalding in the vicinity of bore drains and preventing the discharge of saline bore water to streams. Three principles for the prevention and control of salinity in the Nebine Mungallala catchment have been identified in this review: • Avoid salinity through avoiding scalds – i.e. not exposing the near-surface salt in landscape through land degradation; • Riparian zone management: Scalding often occurs within 200m or so of watering lines. Natural drainage lines are most likely to be overstocked, and thus have potential for scalding. Scalding begins when vegetation is removed, and without that binding cover, wind and water erosion exposes the subsoil; and • Monitoring of exposed or grazed soil areas. Based on the findings of the study, we make the following recommendations: 1. Undertake a geotechnical study of existing maps and other data to help identify and target areas most at risk of rising water tables causing salinity. Selected monitoring should then be established using piezometers as an early warning system. 2. SW NRM should financially support scald reclamation activity through its various funding programs. However, for this to have any validity in the overall management of salinity risk, it is critical that such funding require the landholder to undertake a salinity hazard/risk assessment of his/her holding. 3. A staged approach to funding may be appropriate. In the first instance, it would be reasonable to commence funding some pilot scald reclamation work with a view to further developing and piloting the farm hazard/risk assessment tools, and exploring how subsequent grazing management strategies could be incorporated within other extension and management activities. Once the details of the necessary farm level activities have been more clearly defined, and following the outcomes of the geotechnical review recommended above, a more comprehensive funding package could be rolled out to priority areas. 4. We recommend that best-practice grazing management training currently on offer should be enhanced with information about salinity risk in scald-prone areas, and ways of minimising the likelihood of scald formation. 5. We recommend that course material be developed for local students in Years 6 and 7, and that arrangements be made with local schools to present this information. Given the constraints of existing syllabi, we envisage that negotiations may have to be undertaken with the Department of Education in order for this material to be permitted to be used. We have contact with key people who could help in this if required. 6. We recommend that SW NRM continue to support existing extension activities such as Grazing Land Management and the Monitoring Made Easy tools. These aids should be able to be easily expanding to incorporate techniques for monitoring, addressing and preventing salinity and scalding. At the time of writing staff of SW NRM were actively involved in this process. It is important that these activities are adequately resourced to facilitate the uptake by landholders of the perception that salinity is an issue that needs to be addressed as part of everyday management. 7. We recommend that SW NRM consider investing in the development and deployment of a scenario-modelling learning support tool as part of the awareness raising and education activities. Secondary salinity is a dynamic process that results from ongoing human activity which mobilises and/or exposes salt occurring naturally in the landscape. Time scales can be short to very long, and the benefits of management actions can similarly have immediate or very long time frames. One way to help explain the dynamics of these processes is through scenario modelling.

A methodology for object identification and tracking in construction based on spatial modeling and image matching techniques

Understanding the motion characteristics of on-site objects is desirable for the analysis of construction work zones, especially in problems related to safety and productivity studies. This article presents a methodology for rapid object identification and tracking. The proposed methodology contains algorithms for spatial modeling and image matching. A high-frame-rate range sensor was utilized for spatial data acquisition. The experimental results indicated that an occupancy grid spatial modeling algorithm could quickly build a suitable work zone model from the acquired data. The results also showed that an image matching algorithm is able to find the most similar object from a model database and from spatial models obtained from previous scans. It is then possible to use the matched information to successfully identify and track objects.

Machine learning techniques to improve software quality

A significant proportion of the cost of software development is due to software testing and maintenance. This is in part the result of the inevitable imperfections due to human error, lack of quality during the design and coding of software, and the increasing need to reduce faults to improve customer satisfaction in a competitive marketplace. Given the cost and importance of removing errors improvements in fault detection and removal can be of significant benefit. The earlier in the development process faults can be found, the less it costs to correct them and the less likely other faults are to develop. This research aims to make the testing process more efficient and effective by identifying those software modules most likely to contain faults, allowing testing efforts to be carefully targeted. This is done with the use of machine learning algorithms which use examples of fault prone and not fault prone modules to develop predictive models of quality. In order to learn the numerical mapping between module and classification, a module is represented in terms of software metrics. A difficulty in this sort of problem is sourcing software engineering data of adequate quality. In this work, data is obtained from two sources, the NASA Metrics Data Program, and the open source Eclipse project. Feature selection before learning is applied, and in this area a number of different feature selection methods are applied to find which work best. Two machine learning algorithms are applied to the data - Naive Bayes and the Support Vector Machine - and predictive results are compared to those of previous efforts and found to be superior on selected data sets and comparable on others. In addition, a new classification method is proposed, Rank Sum, in which a ranking abstraction is laid over bin densities for each class, and a classification is determined based on the sum of ranks over features. A novel extension of this method is also described based on an observed polarising of points by class when rank sum is applied to training data to convert it into 2D rank sum space. SVM is applied to this transformed data to produce models the parameters of which can be set according to trade-off curves to obtain a particular performance trade-off.

Probabilistic subgroup identification using Bayesian finite mixture modelling : a case study in Parkinson’s disease phenotype identification

This article explores the use of probabilistic classification, namely finite mixture modelling, for identification of complex disease phenotypes, given cross-sectional data. In particular, if focuses on posterior probabilities of subgroup membership, a standard output of finite mixture modelling, and how the quantification of uncertainty in these probabilities can lead to more detailed analyses. Using a Bayesian approach, we describe two practical uses of this uncertainty: (i) as a means of describing a person’s membership to a single or multiple latent subgroups and (ii) as a means of describing identified subgroups by patient-centred covariates not included in model estimation. These proposed uses are demonstrated on a case study in Parkinson’s disease (PD), where latent subgroups are identified using multiple symptoms from the Unified Parkinson’s Disease Rating Scale (UPDRS).