Enhancing social work students’ learning experience and readiness to undertake practice learning.

This project set out to evaluate the effectiveness of social work education by analysing student perceptions of the strengths and limitations of their education and training on the Bachelor of Social Work, Queen’s University, Belfast (QUB) at different stages of their ‘learning journey’ through the programme.
The author’s primary aim in undertaking this study was to contribute evidence-based understanding of the challenges and opportunities students identified themselves within contemporary practice environments. A secondary aim was to test the effectiveness of key approaches, theories and learning tools in common usage in social work education. The authors believe the outcomes generated by the project demonstrate the value of systematically researching student perceptions of their learning experience and feel the study provides important lessons which should help to inform the future development of social work education not only locally but in other parts of the UK.

‘Preparing Social Workers for Practice: Re-evaluating Student Learning Needs’

Among the key developmental priorities that have been identified in the current process of reform taking place in social work in the UK is the need to improve social work students' preparedness to meet the challenges they will encounter in practice. This paper contributes to the current debate about this issue by reporting a research study that focused on final year undergraduates' experience of academic and practice learning and considered the impact of demographic factors, including age, gender, disability, previous experience and qualifications, on their perceptions of preparedness. The results indicate that students were satisfied with most aspects of preparatory teaching and learning. However, the findings also highlight areas in which students' preparation could be further enhanced, including their skills in dealing with conflict and managing risk. The results suggest that social work programmes should not overly depend on practice learning to prepare students to address the challenges presented by increasingly complex working environments and that educators need to work closely in collaboration with employing partners to ensure that the curriculum keeps up to date with the changing learning needs of practitioners.

An Adaptive Machine Learning Decision System for Flexible Predictive Maintenance

Process monitoring and Predictive Maintenance (PdM) are gaining increasing attention in most manufacturing environments as a means of reducing maintenance related costs and downtime. This is especially true in industries that are data intensive such as semiconductor manufacturing. In this paper an adaptive PdM based flexible maintenance scheduling decision support system, which pays particular attention to associated opportunity and risk costs, is presented. The proposed system, which employs Machine Learning and regularized regression methods, exploits new information as it becomes available from newly processed components to refine remaining useful life estimates and associated costs and risks. The system has been validated on a real industrial dataset related to an Ion Beam Etching process for semiconductor manufacturing.

Clustering-Based Ensemble Learning for Activity Recognition in Smart Homes

Application of sensor-based technology within activity monitoring systems is becoming a popular technique within the smart environment paradigm. Nevertheless, the use of such an approach generates complex constructs of data, which subsequently requires the use of intricate activity recognition techniques to automatically infer the underlying activity. This paper explores a cluster-based ensemble method as a new solution for the purposes of activity recognition within smart environments. With this approach activities are modelled as collections of clusters built on different subsets of features. A classification process is performed by assigning a new instance to its closest cluster from each collection. Two different sensor data representations have been investigated, namely numeric and binary. Following the evaluation of the proposed methodology it has been demonstrated that the cluster-based ensemble method can be successfully applied as a viable option for activity recognition. Results following exposure to data collected from a range of activities indicated that the ensemble method had the ability to perform with accuracies of 94.2% and 97.5% for numeric and binary data, respectively. These results outperformed a range of single classifiers considered as benchmarks.