Social presence – connecting pre-service teachers as learners using a blended learning model

The national reform agenda for early childhood education and care across Australia has led to an increased demand for qualified early childhood teachers. In response, universities have developed innovative approaches in delivering early childhood teacher educa tion courses designed to support existing diploma qualified educators to gain their teaching qualifications. One such course at a major Australian University incorporated a flexible multi-modal option of study which included community -based, on line e-learning and face -to- face intensive tutorials. This paper reports on a study examining the outcomes for students undertaking their studies using this course delivery mode. The study sought to examine the students’ perceptions of the efficacy of the teaching and learning approach in meeting their learning needs, and the factors that were most influential in informing these perceptions. The findings indicated that it was the inclusion of contact and a social presence in the online learning environment which was most influential.

Prediciton of emergency events: a multi-task multi-label learning approach

Prediction of patient outcomes is critical to plan resources in an hospital emergency department. We present a method to exploit longitudinal data from Electronic Medical Records (EMR), whilst exploiting multiple patient outcomes. We divide the EMR data into segments where each segment is a task, and all tasks are associated with multiple patient outcomes over a 3, 6 and 12 month period. We propose a model that learns a prediction function for each task-label pair, interacting through two subspaces: the first subspace is used to impose sharing across all tasks for a given label. The second subspace captures the task-specific variations and is shared across all the labels for a given task. The proposed model is formulated as an iterative optimization problems and solved using a scalable and efficient Block co-ordinate descent (BCD) method. We apply the proposed model on two hospital cohorts - Cancer and Acute Myocardial Infarction (AMI) patients collected over a two year period from a large hospital emergency department. We show that the predictive performance of our proposed models is significantly better than those of several state-of-the-art multi-task and multi-label learning methods.