Graph theory based representation of building information models for access control applications

Building information models are increasingly being utilised for facility management of large facilities such as critical infrastructures. In such environments, it is valuable to utilise the vast amount of data contained within the building information models to improve access control administration. The use of building information models in access control scenarios can provide 3D visualisation of buildings as well as many other advantages such as automation of essential tasks including path finding, consistency detection, and accessibility verification. However, there is no mathematical model for building information models that can be used to describe and compute these functions. In this paper, we show how graph theory can be utilised as a representation language of building information models and the proposed security related functions. This graph-theoretic representation allows for mathematically representing building information models and performing computations using these functions.

Human identification from video using advanced gait recognition techniques

The solutions proposed in this thesis contribute to improve gait recognition performance in practical scenarios that further enable the adoption of gait recognition into real world security and forensic applications that require identifying humans at a distance. Pioneering work has been conducted on frontal gait recognition using depth images to allow gait to be integrated with biometric walkthrough portals. The effects of gait challenging conditions including clothing, carrying goods, and viewpoint have been explored. Enhanced approaches are proposed on segmentation, feature extraction, feature optimisation and classification elements, and state-of-the-art recognition performance has been achieved. A frontal depth gait database has been developed and made available to the research community for further investigation. Solutions are explored in 2D and 3D domains using multiple images sources, and both domain-specific and independent modality gait features are proposed.

Locality-sensitive hashing for protein classification

Determination of sequence similarity is a central issue in computational biology, a problem addressed primarily through BLAST, an alignment based heuristic which has underpinned much of the analysis and annotation of the genomic era. Despite their success, alignment-based approaches scale poorly with increasing data set size, and are not robust under structural sequence rearrangements. Successive waves of innovation in sequencing technologies – so-called Next Generation Sequencing (NGS) approaches – have led to an explosion in data availability, challenging existing methods and motivating novel approaches to sequence representation and similarity scoring, including adaptation of existing methods from other domains such as information retrieval. In this work, we investigate locality-sensitive hashing of sequences through binary document signatures, applying the method to a bacterial protein classification task. Here, the goal is to predict the gene family to which a given query protein belongs. Experiments carried out on a pair of small but biologically realistic datasets (the full protein repertoires of families of Chlamydia and Staphylococcus aureus genomes respectively) show that a measure of similarity obtained by locality sensitive hashing gives highly accurate results while offering a number of avenues which will lead to substantial performance improvements over BLAST..

Exploring the impact of shared domain knowledge on strategic alignment in the Australian public sector

In this age of ever-increasing information technology (IT) driven environments, governments/or public sector organisations (PSOs) are expected to demonstrate the business value of the investment in IT and take advantage of the opportunities offered by technological advancements. Strategic alignment (SA) emerged as a mechanism to bridge the gap between business and IT missions, objectives, and plans in order to ensure value optimisation from investment in IT and enhance organisational performance. However, achieving and sustaining SA remains a challenge requiring even more agility nowadays to keep up with turbulent organisational environments. The shared domain knowledge (SDK) between the IT department and other diverse organisational groups is considered as one of the factors influencing the successful implementation of SA. However, SDK in PSOs has received relatively little empirical attention. This paper presents findings from a study which investigated the influence of SDK on SA within organisations in the Australian public sector. The developed research model examined the relationship of SDK between business and IT domains with SA using a survey of 56 public sector professionals and executives. A key research contribution is the empirical demonstration that increasing levels of SDK between IT and business groups leads to increased SA.

Speaker verification using I-vector features

This PhD research has provided novel solutions to three major challenges which have prevented the wide spread deployment of speaker recognition technology: (1) combating enrolment/ verification mismatch, (2) reducing the large amount of development and training data that is required and (3) reducing the duration of speech required to verify a speaker. A range of applications of speaker recognition technology from forensics in criminal investigations to secure access in banking will benefit from the research outcomes.

An efficient and robust system for multi-person event detection in real world indoor surveillance scenes

Due to the popularity of security cameras in public places, it is of interest to design an intelligent system that can efficiently detect events automatically. This paper proposes a novel algorithm for multi-person event detection. To ensure greater than real-time performance, features are extracted directly from compressed MPEG video. A novel histogram-based feature descriptor that captures the angles between extracted particle trajectories is proposed, which allows us to capture motion patterns of multi-person events in the video. To alleviate the need for fine-grained annotation, we propose the use of Labelled Latent Dirichlet Allocation, a “weakly supervised” method that allows the use of coarse temporal annotations which are much simpler to obtain. This novel system is able to run at approximately ten times real-time, while preserving state-of-theart detection performance for multi-person events on a 100-hour real-world surveillance dataset (TRECVid SED).

eHealth-as-a-Service (eHaaS) : the industrialisation of health informatics, a practical approach

With the introduction of the Personally Controlled Health Record (PCEHR), the Australian public is being asked to accept greater responsibility for their healthcare. Although well designed, constructed and intentioned, policy and privacy concerns have resulted in an eHealth model that may impact future health information sharing requirements. Thus an opportunity to transform the beleaguered Australian PCEHR into a sustainable on-demand technology consumption model for patient safety must be explored further. Moreover, the current clerical focus of healthcare practitioners must be renegotiated to establish a shared knowledge creation landscape of action for safer patient interventions. To achieve this potential however requires a platform that will facilitate efficient and trusted unification of all health information available in real-time across the continuum of care. As a conceptual paper, the goal of the authors is to deliver insights into the antecedents of usage influencing superior patient outcomes within an eHealth-as-a-Service framework. To achieve this, the paper attempts to distil key concepts and identify common themes drawn from a preliminary literature review of eHealth and cloud computing concepts, specifically cloud service orchestration to establish a conceptual framework and a research agenda. Initial findings support the authors’ view that an eHealth-as-a-Service (eHaaS) construct will serve as a disruptive paradigm shift in the aggregation and transformation of health information for use as real-world knowledge in patient care scenarios. Moreover, the strategic value of extending the community Health Record Bank (HRB) model lies in the ability to automatically draw on a multitude of relevant data repositories and sources to create a single source of practice based evidence and to engage market forces to create financial sustainability.

The effect of endplate preselection when measuring supine versus standing cobb angle change in idiopathic scoliosis

The primary aim of this study was to determine whether endplate pre-selection makes a difference to the Cobb Angle change between supine and standing which is known to occur in idiopathic scoliosis. A secondary aim of this study was to identify which (if any) patient characteristics were correlated with supine versus standing Cobb change. The study found that pre-selecting vertebral endplates causes only has a minor effect on supine to standing Cobb change in scoliosis. There is a statistically significant relationship between supine to standing Cobb Angle change and fulcrum flexibility. Therefore, supine to standing Cobb Angle change can be considered as a measure of spinal flexibility when both standing and supine images are clinically available.

A tag-based personalized item recommendation system using tensor modeling and topic model approaches

This research falls in the area of enhancing the quality of tag-based item recommendation systems. It aims to achieve this by employing a multi-dimensional user profile approach and by analyzing the semantic aspects of tags. Tag-based recommender systems have two characteristics that need to be carefully studied in order to build a reliable system. Firstly, the multi-dimensional correlation, called as tag assignment , should be appropriately modelled in order to create the user profiles [1]. Secondly, the semantics behind the tags should be considered properly as the flexibility with their design can cause semantic problems such as synonymy and polysemy [2]. This research proposes to address these two challenges for building a tag-based item recommendation system by employing tensor modeling as the multi-dimensional user profile approach, and the topic model as the semantic analysis approach. The first objective is to optimize the tensor model reconstruction and to improve the model performance in generating quality rec-ommendation. A novel Tensor-based Recommendation using Probabilistic Ranking (TRPR) method [3] has been developed. Results show this method to be scalable for large datasets and outperforming the benchmarking methods in terms of accuracy. The memory efficient loop implements the n-mode block-striped (matrix) product for tensor reconstruction as an approximation of the initial tensor. The probabilistic ranking calculates the probabil-ity of users to select candidate items using their tag preference list based on the entries generated from the reconstructed tensor. The second objective is to analyse the tag semantics and utilize the outcome in building the tensor model. This research proposes to investigate the problem using topic model approach to keep the tags nature as the “social vocabulary” [4]. For the tag assignment data, topics can be generated from the occurrences of tags given for an item. However there is only limited amount of tags availa-ble to represent items as collection of topics, since an item might have only been tagged by using several tags. Consequently, the generated topics might not able to represent the items appropriately. Furthermore, given that each tag can belong to any topics with various probability scores, the occurrence of tags cannot simply be mapped by the topics to build the tensor model. A standard weighting technique will not appropriately calculate the value of tagging activity since it will define the context of an item using a tag instead of a topic.

Score-level multibiometric fusion based on Dempster-Shafer theory incorporating uncertainty factors

While existing multi-biometic Dempster-Shafer the- ory fusion approaches have demonstrated promising perfor- mance, they do not model the uncertainty appropriately, sug- gesting that further improvement can be achieved. This research seeks to develop a unified framework for multimodal biometric fusion to take advantage of the uncertainty concept of Dempster- Shafer theory, improving the performance of multi-biometric authentication systems. Modeling uncertainty as a function of uncertainty factors affecting the recognition performance of the biometric systems helps to address the uncertainty of the data and the confidence of the fusion outcome. A weighted combination of quality measures and classifiers performance (Equal Error Rate) are proposed to encode the uncertainty concept to improve the fusion. We also found that quality measures contribute unequally to the recognition performance, thus selecting only significant factors and fusing them with a Dempster-Shafer approach to generate an overall quality score play an important role in the success of uncertainty modeling. The proposed approach achieved a competitive performance (approximate 1% EER) in comparison with other Dempster-Shafer based approaches and other conventional fusion approaches.

Spatial and temporal patterns of locally-acquired dengue transmission in northern Queensland, Australia, 1993-2012

BACKGROUND: Dengue has been a major public health concern in Australia since it re-emerged in Queensland in 1992-1993. We explored spatio-temporal characteristics of locally-acquired dengue cases in northern tropical Queensland, Australia during the period 1993-2012. METHODS: Locally-acquired notified cases of dengue were collected for northern tropical Queensland from 1993 to 2012. Descriptive spatial and temporal analyses were conducted using geographic information system tools and geostatistical techniques. RESULTS: 2,398 locally-acquired dengue cases were recorded in northern tropical Queensland during the study period. The areas affected by the dengue cases exhibited spatial and temporal variation over the study period. Notified cases of dengue occurred more frequently in autumn. Mapping of dengue by statistical local areas (census units) reveals the presence of substantial spatio-temporal variation over time and place. Statistically significant differences in dengue incidence rates among males and females (with more cases in females) (χ(2) = 15.17, d.f.  = 1, p<0.01). Differences were observed among age groups, but these were not statistically significant. There was a significant positive spatial autocorrelation of dengue incidence for the four sub-periods, with the Moran's I statistic ranging from 0.011 to 0.463 (p<0.01). Semi-variogram analysis and smoothed maps created from interpolation techniques indicate that the pattern of spatial autocorrelation was not homogeneous across the northern Queensland. CONCLUSIONS: Tropical areas are potential high-risk areas for mosquito-borne diseases such as dengue. This study demonstrated that the locally-acquired dengue cases have exhibited a spatial and temporal variation over the past twenty years in northern tropical Queensland, Australia. Therefore, this study provides an impetus for further investigation of clusters and risk factors in these high-risk areas.

Component modeling for SCADA network mapping

Supervisory Control and Data Acquisition systems (SCADA) are widely used to control critical infrastructure automatically. Capturing and analyzing packet-level traffic flowing through such a network is an essential requirement for problems such as legacy network mapping and fault detection. Within the framework of captured network traffic, we present a simple modeling technique, which supports the mapping of the SCADA network topology via traffic monitoring. By characterizing atomic network components in terms of their input-output topology and the relationship between their data traffic logs, we show that these modeling primitives have good compositional behaviour, which allows complex networks to be modeled. Finally, the predictions generated by our model are found to be in good agreement with experimentally obtained traffic.

Contextualising co-creation of value in electronic personal health records

This conceptual paper is a preliminary part of an ongoing study into take-up of electronic personal health records (ePHRs). The purpose of this work is to contextually ‘operationalise' Grönroos’ (2012) model of value co-creation in service for ePHRs. Using findings in the extant literature we enhance theoretical and practical understanding of the potential for co-creation of value with ePHRs for relevant stakeholders. The research design focused on the selection and evaluation of relevant literature to include in the discussion. The objective was to demonstrate which articles can be used to 'contextualise' the concepts in relation to relevant healthcare providers and patient engagement in the co-creation of value from having shared ePHRs. Starting at the service concept, that is, what the service provider wants to achieve and for whom, there is little doubt that there are recognised benefits that co-create value for both healthcare providers and healthcare consumers (i.e. patients) through shared ePHRs. We further highlight both alignments and misalignments in the resources and activities concepts between stakeholder groups. Examples include the types of functionalities as well as the interactive and peer communication needs perceived as useful for healthcare providers compared to healthcare consumers. The paper has implications for theory and practice and is an original and innovative approach to studying the co-creation of value in eHealth delivery.