Falls are dangerous for the elderly, often causing serious injuries especially when the fallen person stays on the ground for a long time without assistance. This paper extends our previous work on the development of a Fall Detection System (FDS) using an inertial measurement unit worn at the waist. Data come from SisFall, a publicly available dataset containing records of Activities of Daily Living and falls. We first applied a preprocessing and a feature extraction stage before using five Machine Learning algorithms, allowing us to compare them. Ensemble learning algorithms such as Random Forest and Gradient Boosting have the best performance, with a Sensitivity and Specificity both close to 99%. Our contribution is: a multi-class classification approach for fall detection combined with a study of the effect of the sensors’ sampling rate on the performance of the FDS. Our multi-class classification approach splits the fall into three phases: pre-fall, impact, post-fall. The extension to a multi-class problem is not trivial and we present a well-performing solution. We experimented sampling rates between 1 and 200 Hz. The results show that, while high sampling rates tend to improve performance, a sampling rate of 50 Hz is generally sufficient for an accurate detection.
Worldwide, the elderly have suffered disproportionately from the effects of the COVID-19 pandemic, both in terms of their prognosis once contracted the disease and in terms of the preventative measures required for this demographic, who are at much higher risk than the rest of the population. In the “new normal”, the well-being of older adults (residing either in their own homes or in care homes) will be ideally monitored remotely. These measures would preserve the independence of individuals without compromising on their safety. In this paper we discuss aspects of the design and implementation of a resident monitoring system (RMS) with particular emphasis on overcoming the barriers for adoption among these populations, by addressing the aspects of usability, privacy and security at the core of the development of such a system. We discuss the current challenges of this research and future work on the RMS.
Information and communication technologies are central tools for Humanitarian Organizations operations. ICT field specialists are real practical experts, but the lack of theoretical knowledge prevents them from being self-sufficient and efficient in unexpected situations. United Nations (UN) members have agreed on defining 17 Sustainable Development Goals (SDG). As a University of Applied Sciences, we are concerned about the development of skills in information and communication technologies (ICT). This concern is shared in the “SDG 4: Quality education”. Training can be a controversial topic in the humanitarian field because of the priority of operations activities. Our aim was to design a training device which could cope with this priority. Through our partnership with a Humanitarian Organization (HO), we built a full and innovating hybrid training methodology for ICT field specialists. This methodology is based on state-of-the-art education and ergonomics techniques. Work analysis and ergonomic theory assume that in order to offer a pertinent and transferable training, the learnings must be built on the real work the trainees do. In this study, we present our global training concept in broad terms. We focus here on the results of the first implemented phase. This phase concerns the assessment of the ICT theoretical knowledge of our HO partner's specialists.