Designing and implementing usable and useful Accountable-eHealth systems

This tutorial primarily focuses on the technical challenges surrounding the design and implementation of Accountable-eHealth (AeH) systems. The potential benefits of shared eHealth records systems are promising for the future of improved healthcare; however, their uptake is hindered by concerns over the privacy and security of patient information. In the current eHealth environment, there are competing requirements between healthcare consumers' (i.e. patients) requirements and healthcare professionals' requirements. While consumers want control over their information, healthcare professionals want access to as much information as required in order to make well informed decisions. This conflict is evident in the review of Australia's PCEHR system. Accountable-eHealth systems aim to balance these concerns by implementing Information Accountability (IA) mechanisms. AeH systems create an eHealth environment where health information is available to the right person at the right time without rigid barriers whilst empowering the consumers with information control and transparency, thus, enabling the creation of shared eHealth records that can be useful to both patients and HCPs. In this half-day tutorial, we will discuss and describe the technical challenges surrounding the implementation of AeH systems and the solutions we have devised. A prototype AeH system will be used to demonstrate the functionality of AeH systems, and illustrate some of the proposed solutions. The topics that will be covered include: designing for usability in AeH systems, the privacy and security of audit mechanisms, providing for diversity of users, the scalability of AeH systems, and finally the challenges of enabling research and Big Data Analytics on shared eHealth Records while ensuring accountability and privacy are maintained.

Short utterance PLDA speaker verification using SN-WLDA and variance modelling techniques

This paper proposes a combination of source-normalized weighted linear discriminant analysis (SN-WLDA) and short utterance variance (SUV) PLDA modelling to improve the short utterance PLDA speaker verification. As short-length utterance i-vectors vary with the speaker, session variations and phonetic content of the utterance (utterance variation), a combined approach of SN-WLDA projection and SUV PLDA modelling is used to compensate the session and utterance variations. Experimental studies have found that a combination of SN-WLDA and SUV PLDA modelling approach shows an improvement over baseline system (WCCN[LDA]-projected Gaussian PLDA (GPLDA)) as this approach effectively compensates the session and utterance variations.

Simultaneous localization and planning on multiple map hypotheses

This paper presents a novel method to rank map hypotheses by the quality of localization they afford. The highest ranked hypothesis at any moment becomes the active representation that is used to guide the robot to its goal location. A single static representation is insufficient for navigation in dynamic environments where paths can be blocked periodically, a common scenario which poses significant challenges for typical planners. In our approach we simultaneously rank multiple map hypotheses by the influence that localization in each of them has on locally accurate odometry. This is done online for the current locally accurate window by formulating a factor graph of odometry relaxed by localization constraints. Comparison of the resulting perturbed odometry of each hypothesis with the original odometry yields a score that can be used to rank map hypotheses by their utility. We deploy the proposed approach on a real robot navigating a structurally noisy office environment. The configuration of the environment is physically altered outside the robots sensory horizon during navigation tasks to demonstrate the proposed approach of hypothesis selection.

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.

An efficient tagging data interpretation and representation scheme for item recommendation

A tag-based item recommendation method generates an ordered list of items, likely interesting to a particular user, using the users past tagging behaviour. However, the users tagging behaviour varies in different tagging systems. A potential problem in generating quality recommendation is how to build user profiles, that interprets user behaviour to be effectively used, in recommendation models. Generally, the recommendation methods are made to work with specific types of user profiles, and may not work well with different datasets. In this paper, we investigate several tagging data interpretation and representation schemes that can lead to building an effective user profile. We discuss the various benefits a scheme brings to a recommendation method by highlighting the representative features of user tagging behaviours on a specific dataset. Empirical analysis shows that each interpretation scheme forms a distinct data representation which eventually affects the recommendation result. Results on various datasets show that an interpretation scheme should be selected based on the dominant usage in the tagging data (i.e. either higher amount of tags or higher amount of items present). The usage represents the characteristic of user tagging behaviour in the system. The results also demonstrate how the scheme is able to address the cold-start user problem.

Factors influencing robustness and effectiveness of conditional random fields in active learning frameworks

Active learning approaches reduce the annotation cost required by traditional supervised approaches to reach the same effectiveness by actively selecting informative instances during the learning phase. However, effectiveness and robustness of the learnt models are influenced by a number of factors. In this paper we investigate the factors that affect the effectiveness, more specifically in terms of stability and robustness, of active learning models built using conditional random fields (CRFs) for information extraction applications. Stability, defined as a small variation of performance when small variation of the training data or a small variation of the parameters occur, is a major issue for machine learning models, but even more so in the active learning framework which aims to minimise the amount of training data required. The factors we investigate are a) the choice of incremental vs. standard active learning, b) the feature set used as a representation of the text (i.e., morphological features, syntactic features, or semantic features) and c) Gaussian prior variance as one of the important CRFs parameters. Our empirical findings show that incremental learning and the Gaussian prior variance lead to more stable and robust models across iterations. Our study also demonstrates that orthographical, morphological and contextual features as a group of basic features play an important role in learning effective models across all iterations.

Comparative genomics of koala, cattle and sheep strains of Chlamydia pecorum

Background Chlamydia pecorum is an important pathogen of domesticated livestock including sheep, cattle and pigs. This pathogen is also a key factor in the decline of the koala in Australia. We sequenced the genomes of three koala C. pecorum strains, isolated from the urogenital tracts and conjunctiva of diseased koalas. The genome of the C. pecorum VR629 (IPA) strain, isolated from a sheep with polyarthritis, was also sequenced. Results Comparisons of the draft C. pecorum genomes against the complete genomes of livestock C. pecorum isolates revealed that these strains have a conserved gene content and order, sharing a nucleotide sequence similarity > 98%. Single nucleotide polymorphisms (SNPs) appear to be key factors in understanding the adaptive process. Two regions of the chromosome were found to be accumulating a large number of SNPs within the koala strains. These regions include the Chlamydia plasticity zone, which contains two cytotoxin genes (toxA and toxB), and a 77 kbp region that codes for putative type III effector proteins. In one koala strain (MC/MarsBar), the toxB gene was truncated by a premature stop codon but is full-length in IPTaLE and DBDeUG. Another five pseudogenes were also identified, two unique to the urogenital strains C. pecorum MC/MarsBar and C. pecorum DBDeUG, respectively, while three were unique to the koala C. pecorum conjunctival isolate IPTaLE. An examination of the distribution of these pseudogenes in C. pecorum strains from a variety of koala populations, alongside a number of sheep and cattle C. pecorum positive samples from Australian livestock, confirmed the presence of four predicted pseudogenes in koala C. pecorum clinical samples. Consistent with our genomics analyses, none of these pseudogenes were observed in the livestock C. pecorum samples examined. Interestingly, three SNPs resulting in pseudogenes identified in the IPTaLE isolate were not found in any other C. pecorum strain analysed, raising questions over the origin of these point mutations. Conclusions The genomic data revealed that variation between C. pecorum strains were mainly due to the accumulation of SNPs, some of which cause gene inactivation. The identification of these genetic differences will provide the basis for further studies to understand the biology and evolution of this important animal pathogen. Keywords: Chlamydia pecorum; Single nucleotide polymorphism; Pseudogene; Cytotoxin

Designing with people with disabilities : adapting best practices of DIY and organizational approaches

Individualization of design is often necessary particularly when designing with people with disabilities. Maker communities, with their flexible Do-It-Yourself (DIY) practices, offer potential to support individualized and cost-effective product design. However, efforts to adapt DIY practices in designing with people with disabilities tend to face difficulties with regard to continuous commitment, infrastructure provision and proper guidance. We carried out interviews with diverse stakeholders in the disability services sector and carried out observations of local makerspaces to understand their current practices and potential for future collaborations. We found that makerspace participants face difficulties in terms of infrastructure provision and proper guidance whereas Disability Service Organizations face difficulties in continuous expertise. We suggest that artful infrastructuring to blend the best of both approaches offers potential to create a sustainable community that can design individualized technologies to support people with disabilities.

Review and evaluation of mindfulness-based iPhone apps

Background There is growing evidence for the positive impact of mindfulness on wellbeing. Mindfulness-based mobile apps may have potential as an alternative delivery medium for training. While there are hundreds of such apps, there is little information on their quality. Objective This study aimed to conduct a systematic review of mindfulness-based iPhone mobile apps and to evaluate their quality using a recently-developed expert rating scale, the Mobile Application Rating Scale (MARS). It also aimed to describe features of selected high-quality mindfulness apps. Methods A search for “mindfulness” was conducted in iTunes and Google Apps Marketplace. Apps that provided mindfulness training and education were included. Those containing only reminders, timers or guided meditation tracks were excluded. An expert rater reviewed and rated app quality using the MARS engagement, functionality, visual aesthetics, information quality and subjective quality subscales. A second rater provided MARS ratings on 30% of the apps for inter-rater reliability purposes. Results The “mindfulness” search identified 700 apps. However, 94 were duplicates, 6 were not accessible and 40 were not in English. Of the remaining 560, 23 apps met inclusion criteria and were reviewed. The median MARS score was 3.2 (out of 5.0), which exceeded the minimum acceptable score (3.0). The Headspace app had the highest average score (4.0), followed by Smiling Mind (3.7), iMindfulness (3.5) and Mindfulness Daily (3.5). There was a high level of inter-rater reliability between the two MARS raters. Conclusions Though many apps claim to be mindfulness-related, most were guided meditation apps, timers, or reminders. Very few had high ratings on the MARS subscales of visual aesthetics, engagement, functionality or information quality. Little evidence is available on the efficacy of the apps in developing mindfulness.

Motivation and behavioural patterns of students accessing a peer-facilitated support for learning program

This paper describes the development and use of personas, a Human Computer Interaction (HCI) research methodology, within the STIMulate peer learning program, in order to better understand student behaviour patterns and motivations. STIMulate is a support for learning program at the Queensland University of Technology (QUT) in Brisbane, Australia. The program provides assistance in mathematics, science and information technology (IT) for course work students. A STIMulate space is provided for students to study and obtain one-on-one assistance from Peer Learning Facilitators (PLFs), who are experienced students that have excelled in relevant subject areas. This paper describes personas – archetypal users - that represent the motivations and behavioural patterns of students that utilise STIMulate (particularly the IT stream). The personas were developed based on interviews with PLFs, and subsequently validated by a PLF focus group. Seven different personas were developed. The personas enable us to better understand the characteristics of the students utilising the STIMulate program. The research provides a clearer picture of visiting student motivations and behavioural patterns. This has helped us identify gaps in the services provided, and be more aware of our assumptions about students. The personas have been deployed in PLF training programs, to help PLFs provide a better service to the students. The research findings suggest further study on the resonances between some students and PLFs, which we would like to better elicit.

Delegation of access in an Information Accountability Framework for eHealth

Shared eHealth records systems offer promising benefits for improving healthcare through high availability of information and improved decision making; however, their uptake has been hindered by concerns over the privacy of patient information. To address these privacy concerns while balancing the requirements of healthcare professionals to have access to the information they need to provide appropriate care, the use of an Information Accountability Framework (IAF) has been proposed. For the IAF and so called Accountable-eHealth systems to become a reality, the framework must provide for a diverse range of users and use cases. The initial IAF model did not provide for more diverse use cases including the need for certain users to delegate access to another user in the system to act on their behalf while maintaining accountability. In this paper, we define the requirements for delegation of access in the IAF, how such access policies would be represented in the Framework, and implement and validate an expanded IAF model.

Dashboards in performance management: The foundations and research opportunities for their effective use

When designed effectively dashboards are expected to reduce information overload and improve performance management. Hence, interest in dashboards has increased recently,which is also evident from the proliferation of dashboard solution providers in the market. Despite dashboards popularity, little is known about the extent of their effectiveness in organizations. Dashboards draw from multiple disciplines but ultimately use visualization to communicate important information to stakeholders. Thus,a better understanding of visualization can improve the design and use of dashboards. This paper reviews the foundations and roles of dashboards in performance management and proposes a framework for future research, which can enhance dashboard design and perceived usefulness depending on the fit between the features of the dashboard and the characteristics of the users.

Fostering interpersonal trust on social media: Physicians' perspectives and experiences

Background The problem of developing and sustaining mutual trust is one of the main barriers to knowledge sharing on social media platforms such as blogs, wikis, micro-blogs and social networking websites. While many studies argue that mutual trust is necessary for online communication and knowledge sharing, few have actually explored and demonstrated how physicians can establish and sustain trusted relationships on social media. Objectives To identify approaches through which physicians establish interpersonal trust on social media. Methods Twenty-four physicians, who were active users of social media, were interviewed using a semi-structured approach between 2013 and 2014. Snowball sampling was employed for participant recruitment. The data were analysed using a thematic analysis approach. Results Physicians trust their peers on social media in a slightly different way than in face-to-face communication. The study found that the majority of participants established trust on social media mainly through previous personal interaction, authenticity and relevancy of voice, professional standing, consistency of communication, peer recommendation, and non-anonymous and moderated sites. Conclusions Healthcare professionals need to approach social media carefully when using it for knowledge sharing, networking and developing trusted relations with like-minded peers.

A network forensics tool for precise data packet capture and replay in cyber-physical systems

Network data packet capture and replay capabilities are basic requirements for forensic analysis of faults and security-related anomalies, as well as for testing and development. Cyber-physical networks, in which data packets are used to monitor and control physical devices, must operate within strict timing constraints, in order to match the hardware devices' characteristics. Standard network monitoring tools are unsuitable for such systems because they cannot guarantee to capture all data packets, may introduce their own traffic into the network, and cannot reliably reproduce the original timing of data packets. Here we present a high-speed network forensics tool specifically designed for capturing and replaying data traffic in Supervisory Control and Data Acquisition systems. Unlike general-purpose "packet capture" tools it does not affect the observed network's data traffic and guarantees that the original packet ordering is preserved. Most importantly, it allows replay of network traffic precisely matching its original timing. The tool was implemented by developing novel user interface and back-end software for a special-purpose network interface card. Experimental results show a clear improvement in data capture and replay capabilities over standard network monitoring methods and general-purpose forensics solutions.

Using a glow graph to represent data flow and dependency in event logs

The idea of extracting knowledge in process mining is a descendant of data mining. Both mining disciplines emphasise data flow and relations among elements in the data. Unfortunately, challenges have been encountered when working with the data flow and relations. One of the challenges is that the representation of the data flow between a pair of elements or tasks is insufficiently simplified and formulated, as it considers only a one-to-one data flow relation. In this paper, we discuss how the effectiveness of knowledge representation can be extended in both disciplines. To this end, we introduce a new representation of the data flow and dependency formulation using a flow graph. The flow graph solves the issue of the insufficiency of presenting other relation types, such as many-to-one and one-to-many relations. As an experiment, a new evaluation framework is applied to the Teleclaim process in order to show how this method can provide us with more precise results when compared with other representations.