Designing an e-portfolio for assurance of learning focusing on adoptability and learning analytics

The Assurance of Learning for Graduate Employability framework is a quality assurance model for curriculum enhancement for graduate employability, enabling graduates to achieve "the skills, understandings and personal attributes that make [them] more likely to secure employment and be successful in their chosen occupations to the benefit of themselves, the workforce, the community and the economy" (Yorke, 2006). Of particular note is the framework's dependence on three foundations, including easy access to integrated and accessible tools for staff and student self-management. In other words, this approach to curriculum quality depends on staff and student access to tools that enable them to self-manage their learning. This paper examines two aspects which informed the design of a student e-portfolio system, iPortfolio, intended for students' self-management of their learning, particularly recording evidence of their achievement of capabilities. The paper focuses on two particular considerations in the design of the iPortfolio: adoptability and learning analytics. Adoptability means the phase preceding adoption, whether students have the devices, platforms and technology skills to be able to use such an innovation. The iPortfolio also facilitates learning analytics: it has the capability to gather data related to learning indicators for course quality assurance purposes. Both adoptability and analytics are very dynamic fields: new devices, platforms and applications constantly spark changes in user habits, and policy changes mean institutions need to be able to provide new data, often at short notice. In the conclusion, the paper suggests how tools such as the iPortfolio can be designed for 'future proofing' and sustainability.

Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM)

Electronic medical record (EMR) offers promises for novel analytics. However, manual feature engineering from EMR is labor intensive because EMR is complex - it contains temporal, mixed-type and multimodal data packed in irregular episodes. We present a computational framework to harness EMR with minimal human supervision via restricted Boltzmann machine (RBM). The framework derives a new representation of medical objects by embedding them in a low-dimensional vector space. This new representation facilitates algebraic and statistical manipulations such as projection onto 2D plane (thereby offering intuitive visualization), object grouping (hence enabling automated phenotyping), and risk stratification. To enhance model interpretability, we introduced two constraints into model parameters: (a) nonnegative coefficients, and (b) structural smoothness. These result in a novel model called eNRBM (EMR-driven nonnegative RBM). We demonstrate the capability of the eNRBM on a cohort of 7578 mental health patients under suicide risk assessment. The derived representation not only shows clinically meaningful feature grouping but also facilitates short-term risk stratification. The F-scores, 0.21 for moderate-risk and 0.36 for high-risk, are significantly higher than those obtained by clinicians and competitive with the results obtained by support vector machines.

Integrating internet-of-things with the power of cloud computing and the intelligence of big Data analytics- a three layered approach

This paper is written through the vision on integrating Internet-of-Things (IoT) with the power of Cloud Computing and the intelligence of Big Data analytics. But integration of all these three cutting edge technologies is complex to understand. In this research we first provide a security centric view of three layered approach for understanding the technology, gaps and security issues. Then with a series of lab experiments on different hardware, we have collected performance data from all these three layers, combined these data together and finally applied modern machine learning algorithms to distinguish 18 different activities and cyber-attacks. From our experiments we find classification algorithm RandomForest can identify 93.9% attacks and activities in this complex environment. From the existing literature, no one has ever attempted similar experiment for cyber-attack detection for IoT neither with performance data nor with a three layered approach.

A text analytics evaluation of a first-year engineering project-based unit

In the undergraduate engineering program at Griffith University in Australia, the unit 1006ENG Design and Professional Skills aims to provide an introduction to engineering design and professional practice through a project-based learning (PBL) approach to problem solving. It provides students with an experience of PBL in the first-year of their programme. The unit comprises an underpinning lecture series, design work including group project activities, an individual computer-aided drawing exercise/s and an oral presentation. Griffith University employs a ‘Student Experience of Course’ (SEC) online survey as part of its student evaluation of teaching, quality improvement and staff performance management processes. As well as numerical response scale items, it includes the following two questions inviting open-ended text responses from students: i) What did you find particularly good about this course? and ii) How could this course be improved? The collection of textual data in in student surveys is commonplace, due to the rich descriptions of respondent experiences they can provide at relatively low cost. However, historically these data have been underutilised because they are time consuming to analyse manually, and there has been a lack of automated tools to exploit such data efficiently. Text analytics approaches offer analysis methods that result in visual representations of comment data that highlight key individual themes in these data and the relationships between those themes. We present a text analytics-based evaluation of the SEC open-ended comments received in the first two years of offer of the PBL unit 1006ENG. We discuss the results obtained in detail. The method developed and documented here is a practical and useful approach to analysing/visualising open-ended comment data that could be applied by others with similar comment data sets.

Continuous validation for data analytics systems

From a future history of 2025: Continuous development is common for build/test (continuous integration) and operations (devOps). This trend continues through the lifecycle, into what we call `devUsage': continuous usage validation. In addition to ensuring systems meet user needs, organisations continuously validate their legal and ethical use. The rise of end-user programming and multi-sided platforms exacerbate validation challenges. A separate trend isthe specialisation of software engineering for technical domains, including data analytics. This domain has specific validation challenges. We must validate the accuracy of sta-tistical models, but also whether they have illegal or unethical biases. Usage needs addressed by machine learning are sometimes not speci able in the traditional sense, and statistical models are often `black boxes'. We describe future research to investigate solutions to these devUsage challenges for data analytics systems. We will adapt risk management and governance frameworks previously used for soft-ware product qualities, use social network communities for input from aligned stakeholder groups, and perform cross-validation using autonomic experimentation, cyber-physical data streams, and online discursive feedback.

Applied machine learning for personalised early intervention in autism

This thesis is the first to address the problems of early intervention in Autism Spectrum Disorder through the lens of machine learning and data analytics. The key contribution is the establishment of large datasets in this domain for the first time together with a systematic data-based approach to extract knowledge relevant to Autism.

Social media as sensor for healthcare: A machine learning approach.

This thesis advances the area of applied machine learning, sentiment and psycholinguistic analysis in social media for health analytics. In particular, the thesis views social media as a gigantic form of 'sensor' to inform about mental health community and related topics.