Search

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.

The proportion of people 60 years old and above is expected to double globally to reach 22 % by 2050. This creates societal challenges such as the increase of age-related illnesses and the need for caregivers. Falls are a major threat for the elderly, often causing serious injuries especially when the fallen person stays on the ground for a long time without assistance. This paper presents the development of a Fall Detection System (FDS) using an accelerometer combined with a gyroscope worn at the waist. Data come from SisFall, a publicly available dataset containing records of Activities of Daily Living and falls. We compared five Machine Learning algorithms. We first applied 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%.

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.

This paper proposes a new approach for modelling, testing and prototyping pervasive, possibly mobile, and distributed applications. It describes a set of tools aimed at supporting designers in the conceptualisation of their application and in the software development stage, and proposes a method for checking the validity of their design. The article also presents a pervasive application implemented and evaluated using our approach. It concludes with propositions for improvements in order to build a complete modelling, prototyping and testing framework for pervasive applications.

The greenhouse gas effect has become a major preoccupation worldwide. Heating of buildings and houses is one of the major sources of this effect. We propose to optimize heating control systems by directly integrating the recognition of people activities and context in the process of temperature regulation. We introduce the concept of kinetic-awareness as a way of making heating control system aware of userspsila motion in the physical space in order to adjust temperature according to their current activities.

In this paper we address the problem of collaborative workflow in mobile environments. Specifically, we present a solution for opportunistic task assignment to mobile users based on location, context and motion awareness. As an example of this approach, we present an application based on the new Kinetic User Interface framework where users participate to dynamic workflow through their displacement in designated active zones.