An ontology-based learning resources management framework for exploratory e-learning

This paper presents an ontology-based conceptual framework for effectively managing exploratory e-learning resources. The proposed framework has five significant novel features including authentication of retrieved resources, automatic ontology-based query refinement, reuse-oriented management of retrieved resources, adaptive retrieval of learning resources based on the style and preference of individual learners, and synthesisation of retrieval and management activities for creating reusable learning repositories. The applicability of the framework is demonstrated using a sample fragment of an ontology developed in the database domain.

SMEDIA: Designing to create a social and dynamic learning framework

This article discusses the design of social networking sites created through a PhD action research study. Social and participatory media was used as an active, flexible and motivating learning management system. The study investigated ways in which a social learning framework could be designed for students aged 13 to 16 and aimed to encourage student knowledge growth through peer-to-peer interaction while supporting both formal and informal learning. New literacies and multimodality were infused into the design. It was found that the practitioner-researcher’s cycles of planning, acting, observing and reflecting, action research, provided a mechanism for scaffolding the redesign of curriculum content and instruction. Social media in education can be dynamic, interactive and appreciated (SMEDIA) by the students.

Infusing instructional design principles into an active student-centred social learning framework

Social and participatory media offer a plethora of ways for students to communicate, collaborate, and learn in schools. Using a social learning approach, Casey (2013a) investigated ways that social media could be integrated into Australian public high school classrooms to enhance student learning. In the process, she developed a social learning framework as discussed in Casey (2013b). Similarly, Davidson-Shivers and Hulon (2013; Hulon & Daidson-Shivers, 2013) suggest ways to employ ID principles to prepare college instructors and pre-service teachers to integrate technology into classrooms. Prior to that, Davidson-Shivers with Rasmussen (2006) developed an instructional design (ID) model for creating effective Web-based learning environments. Through collaboration, Casey and Davidson-Shivers consider a wide range of social learning and instructional design principles and approaches to help develop frameworks for new media integration that can work within varying levels of education.

Towards a framework for aligning learning outcomes, academic literacies and assessment criteria

Although Australian students spend three or more years studying they can seem quite unaware of any of the expected learning outcomes of their course. They are often single unit focused, paying most attention to individual assessment items thus not developing a holistic view of their course. This paper presents a theoretical framework to support staff and students to recognise, scaffold and achieve learning outcomes and academic skills at unit level and to recognise how these contribute to course and graduate learning outcomes, within the boundaries of Australian university and professional accreditation requirements. A case study is described that demonstrates the manual implementation of the framework. The complex nature of the implementation suggests that a software solution is required to ease the process and ensure the resulting mapping will have some longevity by being maintainable.

PELS: a noble architecture and framework for a personal E-learning system (PELS)

This article presents a personal e-learning system architecture in the context of a social network environment. The main objective of a personal e-learning system is to develop individual skills on a specific subject and share resources with peers. The authors' system architecture defines the organisation and management of a personal learning environment that aids in creating, verifying and sharing learning artefacts, and making money at the same time. In their research, they also focus on one of the most interesting arenas in digital content or document management - digital rights management - and its application to e-learning.

A comprehensive diagnostic framework for evaluating business intelligence and analytics effectiveness

Business intelligence and analytics (BIA) initiatives are costly, complex and experience high failure rates. Organizations require effective approaches to evaluate their BIA capabilities in order to develop strategies for their evolution. In this paper, we employ a design scienceparadigm to develop a comprehensive BIA effectiveness diagnostic (BIAED) framework that can be easily operationalized. We propose that a useful BIAED framework must assess the correct factors, should be deployed in the proper process context and acquire the appropriateinput from different constituencies within an organization. Drawing on the BIAED framework, we further develop an online diagnostic toolkit that includes a comprehensive survey instrument. We subsequently deploy the diagnostic mechanism within three large organizations in North America (involving over 1500 participants) and use the results toinform BIA strategy formulation. Feedback from participating organizations indicates that the BIA diagnostic toolkit provides insights that are essential inputs to strategy development. This work addresses a significant research gap in the area of BIA effectiveness assessment.

Creating a standardised teaching and learning framework for social work field placements

© 2014, © 2014 Australian Association of Social Workers. Abstract: Mapping and evaluating a student's progress on placement is a core element of social work education but there has been scant attention to indicate how to effectively create and assess student learning and performance. This paper outlines a project undertaken by the Combined Schools of Social Work to develop a common learning and assessment tool that is being used by all social work schools in Victoria. The paper describes how the Common Assessment Tool (CAT) was developed, drawing on the Australian Association of Social Work Practice Standards, leading to seven key learning areas that form the basis of the assessment of a student's readiness for practice. An evaluation of the usefulness of the CAT was completed by field educators, liaison staff, and students, which confirmed that the CAT was a useful framework for evaluating students' learning goals. The feedback also identified a number of problematic features that were addressed in a revised CAT and rating scale.

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.

A new transfer learning framework with application to model-agnostic multi-task learning

Learning from small number of examples is a challenging problem in machine learning. An effective way to improve the performance is through exploiting knowledge from other related tasks. Multi-task learning (MTL) is one such useful paradigm that aims to improve the performance through jointly modeling multiple related tasks. Although there exist numerous classification or regression models in machine learning literature, most of the MTL models are built around ridge or logistic regression. There exist some limited works, which propose multi-task extension of techniques such as support vector machine, Gaussian processes. However, all these MTL models are tied to specific classification or regression algorithms and there is no single MTL algorithm that can be used at a meta level for any given learning algorithm. Addressing this problem, we propose a generic, model-agnostic joint modeling framework that can take any classification or regression algorithm of a practitioner’s choice (standard or custom-built) and build its MTL variant. The key observation that drives our framework is that due to small number of examples, the estimates of task parameters are usually poor, and we show that this leads to an under-estimation of task relatedness between any two tasks with high probability. We derive an algorithm that brings the tasks closer to their true relatedness by improving the estimates of task parameters. This is achieved by appropriate sharing of data across tasks. We provide the detail theoretical underpinning of the algorithm. Through our experiments with both synthetic and real datasets, we demonstrate that the multi-task variants of several classifiers/regressors (logistic regression, support vector machine, K-nearest neighbor, Random Forest, ridge regression, support vector regression) convincingly outperform their single-task counterparts. We also show that the proposed model performs comparable or better than many state-of-the-art MTL and transfer learning baselines.

Flexible transfer learning framework for bayesian optimisation

Bayesian optimisation is an efficient technique to optimise functions that are expensive to compute. In this paper, we propose a novel framework to transfer knowledge from a completed source optimisation task to a new target task in order to overcome the cold start problem. We model source data as noisy observations of the target function. The level of noise is computed from the data in a Bayesian setting. This enables flexible knowledge transfer across tasks with differing relatedness, addressing a limitation of the existing methods. We evaluate on the task of tuning hyperparameters of two machine learning algorithms. Treating a fraction of the whole training data as source and the whole as the target task, we show that our method finds the best hyperparameters in the least amount of time compared to both the state-of-art and no transfer method.

Toxicity prediction in cancer using multiple instance learning in a multi-task framework

Treatments of cancer cause severe side effects called toxicities. Reduction of such effects is crucial in cancer care. To impact care, we need to predict toxicities at fortnightly intervals. This toxicity data differs from traditional time series data as toxicities can be caused by one treatment on a given day alone, and thus it is necessary to consider the effect of the singular data vector causing toxicity. We model the data before prediction points using the multiple instance learning, where each bag is composed of multiple instances associated with daily treatments and patient-specific attributes, such as chemotherapy, radiotherapy, age and cancer types. We then formulate a Bayesian multi-task framework to enhance toxicity prediction at each prediction point. The use of the prior allows factors to be shared across task predictors. Our proposed method simultaneously captures the heterogeneity of daily treatments and performs toxicity prediction at different prediction points. Our method was evaluated on a real-word dataset of more than 2000 cancer patients and had achieved a better prediction accuracy in terms of AUC than the state-of-art baselines.