Computing and Information Systems - Research Publications

Permanent URI for this collection

Search Results

Now showing 1 - 10 of 96
  • Item
    Thumbnail Image
    Run or Pat: Using Deep Learning to Classify the Species Type and Emotion of Pets
    Sinnott, RO ; Aickelin, U ; Jia, Y ; Sun, PY ; Susanto, R (EEE, 2021-01-01)
    Deep learning has been applied in many contexts. In this paper we present a novel application area: to detect the species type and emotion of pets with focus on a diverse set of dog and cat collections comprising 52 dog and 23 cat species. Building on an extensive collection of labelled images with over 300 images per species type, we explore a range of deep learning models to develop a classifier for species type and their associated emotion. We outline the realization of the technical solution delivered through a mobile application (iPhone/Android) and present results based on feedback based on real world adoption and utilisation by the broader mobile application community.
  • Item
    Thumbnail Image
    Eliciting group judgements about replicability: A technical implementation of the IDEA Protocol
    Pearson, ER ; Fraser, H ; Bush, M ; Mody, F ; Widjaja, I ; Head, A ; Wilkinson, DP ; Wintle, B ; Sinnott, R ; Vesk, P ; Burgman, M ; Fidler, F (Hawaii International Conference on System Sciences, 2021-01-01)
    In recent years there has been increased interest in replicating prior research. One of the biggest challenges to assessing replicability is the cost in resources and time that it takes to repeat studies. Thus there is an impetus to develop rapid elicitation protocols that can, in a practical manner, estimate the likelihood that research findings will successfully replicate. We employ a novel implementation of the IDEA ('Investigate', 'Discuss', 'Estimate' and 'Aggregate) protocol, realised through the repliCATS platform. The repliCATS platform is designed to scalably elicit expert opinion about replicability of social and behavioural science research. The IDEA protocol provides a structured methodology for eliciting judgements and reasoning from groups. This paper describes the repliCATS platform as a multi-user cloud-based software platform featuring (1) a technical implementation of the IDEA protocol for eliciting expert opinion on research replicability, (2) capture of consent and demographic data, (3) on-line training on replication concepts, and (4) exporting of completed judgements. The platform has, to date, evaluated 3432 social and behavioural science research claims from 637 participants.
  • Item
    Thumbnail Image
    The Urban Research Gateway for Australia: Development of a Federated, Multi-disciplinary Research e-Infrastructure
    Sinnott, RO ; Bayliss, C ; Bromage, AJ ; Galang, GC ; Grazioli, G ; Greenwood, PA ; Macauley, A ; Mannix, D ; Morandini, LF ; Nino-Ruiz, M ; Pettit, CJ ; Tomko, M ; Sarwar, M ; Stimson, RJ ; Voorsluys, WV ; Widjaja, I (CEUR Workshop Proceedings, 2013)
  • Item
    Thumbnail Image
    e-Enabling international cancer research: lessons being learnt in the ENS@T-CANCER Project
    STELL, ANTHONY ; SINNOTT, RICHARD (IEEE Computer Society Press, 2013)
  • Item
    Thumbnail Image
    The design of a flexible web-based analytical platform for urban research
    Tomko, M ; Greenwood, P ; Sarwar, M ; Morandini, L ; Stimson, R ; Bayliss, C ; Galang, G ; Nino-Ruiz, M ; Voorsluys, W ; Widjaja, I ; Koetsier, G ; Mannix, D ; Pettit, C ; Sinnott, R (ACM, 2012-12-01)
  • Item
    Thumbnail Image
    Tools and Processes to Support the Development of a National Platform for Urban Research: Lessons (Being) Learnt from the AURIN Project
    Sinnott, RO ; Bayliss, C ; Morandini, LF ; Tomko, M (Australian Computer Society, 2013)
  • Item
    Thumbnail Image
    Index-based symmetric DNA encryption algorithm
    Yunpeng, Z ; Yu, Z ; Zhong, W ; Sinnott, RO (IEEE, 2011-12-01)
  • Item
    Thumbnail Image
    Policy-based vulnerability assessment for virtual organisations
    Muhammad, J ; Doherty, T ; Hussain, S ; Sinnott, R (Springer Berlin Heidelberg, 2012)
  • Item
    Thumbnail Image
    Visualisation support for exploring urban space and place
    Pettit, C. ; Widjaja, I. ; Russo, P. ; Sinnott, R. ; STIMSON, R. ; Tomko, M. (International Society for Photogrammetry and Remote Sensing, 2012)
    Urban research is fundamentally underpinned by heterogeneous, highly varied data. The availability and quantity of digital data sources is increasing rapidly. In order to facilitate decision-making and support processes related to urban policy and management, such data has to be readily analysed, synthesised and the results readily communicated to support evidence based decision-making. In this paper, we consider the current state of play of visualisation as it supports urban research. In doing so we firstly consider visualisation environments such as geographical information systems (GIS) and Cartography tools, digital globes, virtual simulation environments, building information models and gaming platforms. Secondly, we consider a number of visualisation techniques with a focusing on GIS and Cartography tools including space time cubes, heat maps, choropleth maps, flow maps and brushing. This review of visualisation environments and techniques is undertaken in the context of the Australian Urban Research Infrastructure Network project (www.aurin.org.au). AURIN is tasked with developing a portal and associated e-Infrastructure, which provides seamless access to federated data, modelling and visualisation tools to support the urban researcher community in Australia. We conclude by outlining future research and development opportunities in developing the AURIN visualisation toolkit by reflecting on the value of visualisation as a data exploration and communication tool for researchers and decision-makers to assist with the study and management of the urban fabric.
  • Item
    Thumbnail Image
    A collaborative infrastructure supporting international adrenal cancer research
    STELL, ANTHONY ; SINNOTT, RICHARD ; DURAN, CHRIS ( 2012)
    A wealth of information about adrenal cancer exists in many individual specialist centres around the world. The cancers themselves are very rare, often fatal and no common consensus on optimal treatment strategies exists, and certainly no treatments targeted to the individual genetic makeup of the tumours and individuals. In order to conduct effective and progressive research into these tumours and the surrounding conditions and treatments of individuals, it is essential to pool the expertise from specialist centres that exist in each country. The ENSAT-CANCER project is a 5-year European Union FP7-funded project tasked with this, through the development of an online environment that holds core data from a body of patients aligned with identified needs from leading specialists in the field. These data sets are also augmented with a host of tools and features that enable and support the research in this domain. This presentation will describe some of the novel features that have been developed in the project including biobank labelling and “match-making” services between centres. The presentation will also cover the hurdles involved in putting together such an enterprise – such as ethical approval for international data sharing and the establishment of canonical identification systems, and how these have been successfully overcome. The ENSAT-CANCER platform has now been used to support a portfolio of major international genetically targeted clinical trials and outcome studies. The presentation will describe the different processes involved in connecting and effectively sharing data and making best use of the ENSAT-CANCER platform. To date, the registry holds over 2900 patient cases and continues to grow every day.