Anomaly detection is a key factor in the processing of large amounts of sensor data from Wireless Sensor Networks (WSN). Efficient anomaly detection algorithms can be devised performing online node-local computations and reducing communication overhead, thus improving the use of the limited hardware resources. This work introduces a fixed-point embedded implementation of Online Sequential Extreme Learning Machine (OS-ELM), an online learning algorithm for Single Layer Feed forward Neural Networks (SLFN). To overcome the stability issues introduced by the fixed precision, we apply correction mechanisms previously proposed for Recursive Least Squares (RLS). The proposed implementation is tested extensively with generated and real-world datasets, and compared with RLS, Linear Least Squares Estimation, and a rule-based method as benchmarks. The methods are evaluated on the prediction accuracy and on the detection of anomalies. The experimental results demonstrate that fixed-point OS-ELM can be successfully implemented on resource-limited embedded systems, with guarantees of numerical stability. Furthermore, the detection accuracy of fixed-point OS-ELM shows better generalization properties in comparison with, for instance, fixed-point RLS. © 2013 IEEE.
Purpose – In the domain of healthcare, both process efficiency and the quality of care can be improved through the use of dedicated pervasive technologies. Among these applications are so-called real-time location systems (RTLS). Such systems are designed to determine and monitor the location of assets and people in real time through the use of wireless sensor networks. Numerous commercially available RTLS are used in hospital settings. The nursing home is a relatively unexplored context for the application of RTLS and offers opportunities and challenges for future applications. The paper aims to discuss these issues. Design/methodology/approach – This paper sets out to provide an overview of general applications and technologies of RTLS. Thereafter, it describes the specific healthcare applications of RTLS, including asset tracking, patient tracking and personnel tracking. These overviews are followed by a forecast of the implementation of RTLS in nursing homes in terms of opportunities and challenges. Findings – By comparing the nursing home to the hospital, the RTLS applications for the nursing home context that are most promising are asset tracking of expensive goods owned by the nursing home in orderto facilitate workflow and maximise financial resources, and asset tracking of personal belongings that may get lost due to dementia. Originality/value – This paper is the first to provide an overview of potential application of RTLS technologies for nursing homes. The paper described a number of potential problem areas that can be addressed by RTLS. Published by Emerald Publishing Limited Original article: https://doi.org/10.1108/JET-11-2017-0046 For this paper Joost van Hoof received the Highly Recommended Award from Emerald Publishing Ltd. in October 2019: https://www.emeraldgrouppublishing.com/authors/literati/awards.htm?year=2019
MULTIFILE
At the end of January 2015 I was given a research assignment formulated and sponsored by two professors of professorships (hereafter lectoraten) associated with the Academy for Social Studies (SASS), and the manager of Professionals and Bedrijven (hereafter P&B). At a later stage, the research was expanded by the sponsorship of the educational managers of the bachelor and master studies of SPH and MWD. It is a complex assignment with several research perspectives and aims. The main goal was to find out how to make better use of the products of the lectoraten for educational purposes. This umbrella goal included many subordinate aims. One aim concerned identifying the products and prioritizing them according to the educational demands of clients in the field and of teachers of the SASS educational programmes. Another aim was to demonstrate which skills the teachers who develop educational materials need to have and to identify steps necessary to adapt the products. Yet another aim consisted of finding better ways for knowledge to circulate between the lectoraten and the teaching staff of SASS. Finally advising the staff of P & B on marketing and communications in relation to the products of the lectoraten was aimed at. Overview of the reportAs stated, there are multiple assignment-givers (hereafter sponsors). In the first section the general societal context which triggered the assignment has been sketched but contextual aspects related to each of the sponsors have also been identified (in Appendix 1). The individual contexts of sponsors were important because, although they agreed on the broad aims of the assignment, they naturally have specific expectations of the results based on their particular situations. After the background sketch, seven sub-tasks given by the sponsors have been turned into subordinate - research and consultation questions. The second section describes the methods used and measures taken to obtain findings. This includes an identification of the inventory structure, actors involved both intramurally and extramurally (the stakeholders). Next, a Delphi method for developing a profile of learner needs and a list of topics of products is described.In the third section, findings are set out in relation to the 7 sub-research and consultation questions. Some discussion and concluding remarks are given for most of the seven questions. The findings are written in English but most of the quotations from respondents have not been translated so they appear in Dutch. Section four summarises these findings in a compact manner since there were conclusions throughout the findings. Section five offers recommendations in Dutch. Attention is given to the different emphases of the sponsors in the details of recommendations. Please note that many end notes and appendices are offered for further reading since some of the approaches mentioned in the text may be unfamiliar to some readers. A word about terms Both Dutch and English employ a variety of terms to identify the provision (aanbod) of learning for adults in working environments and to identify the learning activities or programmes. This can be confusing but is, unfortunately, unavoidable. In Dutch, the terms ‘deskundigheidsbevordering, nascholing, bijscholing’ and ‘trainingsaanbod’ or occasionally ‘professionalisering’ are all used to indicate what in English is called ‘professional development’ (often abbreviated to PD) or ‘staff development’ or, recently, ‘professionalisation’ The typical Dutch use of the term ‘training’ for almost all stypes of learning activities has a somewhat more restricted meaning in English. Educational activities are often referred to as ‘learning trajectories’; ‘ learning opportunities’ or ‘interventions’ as well as, less commonly, ‘training sessions’ or ‘workshops’. All of the English terms are employed throughout this report. The most commonly used are ‘professionalisation’ or ‘PD’ for the provision and ‘interventions’ to indicate specific educational programmes or activities.
