30 research outputs found
An overview of human-computer interaction patterns in pervasive systems
No full textDespite a growing interest in design patterns by the Human-Computer Interaction (HCI) community, an interaction pattern collection that is universally accepted is yet to be found. Such a collection would aid the design of pervasive computing systems, in which interactions occur in both the material and logical worlds. This paper first seeks to define interaction patterns by adopting a model that captures such duality and then considers the challenges and opportunities that non-traditional interaction brings. Some patterns are then reviewed, with examples relating to motion-aware systems. We conclude that the creation of a widely accepted interaction pattern collection is unlikely in the near future
A comparison of machine learning algorithms for fall detection using wearable sensors
No full textThe 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 andGradient Boosting have the best performance, with a Sensitivity and Specificity both close to 99%
A Machine learning multi-class approach for fall detection systems based on wearable sensors with a study on sampling rates selection
Get PDFFalls 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
On the Development of a Resident Monitoring System:Usability, Privacy and Security Aspects
Get PDFWorldwide, 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
161 - a machine learning multi-class approach for fall detection systems based on wearable sensors with a study on sampling rates selection
No full textROBIN: activity based robot management system
Get PDFThis paper examines the design and implementation of a system to support firefighting exercises based on tools and ideas of pervasive computing. Through this development a range of technologies and conceptual tools were used, such as sensors, wireless communication, and the programming framework uMove; as well as context-awareness, situation management, and activity detection. In this development, the notion of implicit human-computer interaction was of particular relevance. The use of a programming framework for interaction through motion was central, and this implementation is one of its proofs of concept, as it presented opportunities to improve it and recommendations to adapt it for future applications
Kinetic User Interfaces
No full textThis chapter presents a conceptual framework for an emerging type of user interfaces for mobile ubiquitous computing systems, and focuses in particular on the interaction through motion of people and objects in physical space. We introduce the notion of Kinetic User Interface as a unifying framework and a middleware for the design of pervasive interfaces, in which motion is considered as the primary input modality.</jats:p
uMove: a wholistic framework to design and implement ubiquitous computing systems supporting user's activity and situation
No full textCette thèse présente un ensemble d'outils (un framework) qui permettent la définition, la création et la réalisation de systèmes informatiques ubiquitaires pouvant intégrer la prise en charge des activités des utilisateurs ainsi que de la détection de leur situation. Avec le rapide développement de l'informatique intégrant les contextes des utilisateurs ainsi que l'informatique mobile, de nouveaux défis sont apparus et parmi ceux-ci, trois d'entre eux sont adresses dans cette thèse. Le premier est le besoin d'un ensemble d'outils permettant le développement de systèmes ubiquitaires partant de leur définition théorique jusqu'à leur réalisation. Le deuxième défi consiste à développer des applications intelligentes qui intégrantes les nouvelles technologies telles que les senseurs et l'accès à des systèmes informatiques repartis. Le troisième défi est l'intégration d'interactions homme-machine enrichies par la prise en compte des mouvements, des activités et situations des utilisateurs ceci par le biais de senseurs de plus en plus présents dans nos environnements et sur les dispositifs informatiques mobiles. Dans cette thèse, nous décrivons uMove, un ensemble d'outils permettant la définition et le développement de système ubiquitaire représentant différentes sortes d'environnements physiques ou logiques. uMove comporte trois facettes qui décrivent les concepts fondamentaux ainsi que les outils logiciels nécessaires à leur développement. La première facette est consacrée à la définition du modèle conceptuel décrivant des systèmes ubiquitaires composés d'entités et d'observateurs et ceci en utilisant une approche systémique. La deuxième facette présente une architecture qui permet aux concepteurs et développeurs de formaliser leurs systèmes. La troisième facette décrit les outils logiciels qui permettront d'implémenter les projets définis de manière systémique et en respectant l'architecture uMove. Finalement, uMove est évalué et son modèle validé à travers quatre projets qui ont été implémentés avec l'ensemble de ces outils.This thesis presents a framework that offers tools for the design and the implementation of Ubiquitous computing systems supporting user motions, activities and situations. With the rapid development of context-aware mobile computing and sensor-based interaction, many new challenges come up, three of which are particularly addressed in this thesis. The first is the need for wholistic tools to develop Ubiquitous computing infrastructures. The second concerns smart applications allowing users to benefit from the distributed computing power in their environment, and the third is the integration of enriched human-computer interaction using motions, activity and situation provided by the increasing sensing capabilities of the user environment or mobile devices. We propose the uMove framework, a comprehensive solution which allows to design and develop Ubicomp systems representing different kinds of physical or virtual environments based on a systemic approach. uMove proposes both theoretical foundations and implementation tools and is divided into three specific facets. The first facet is the conceptual model describing a Ubiquitous computing system made of entities and observers within their physical or logical environment. The second facet is a system architecture which offers designers and developers the tools to theoretically define a logical system, including the types of contexts taken into consideration. The third facet is development tools that allow programmers to implement their systems, sensors, applications and services. The uMove framework is evaluated and validated in an interactive manner through four projects
Kinetic user interface: Interaction through motion for pervasive computing systems
Get PDFAbstract. We present in this paper a semantic model for the conception of pervasive computing systems based on object or user's motions. We describe a system made of moving entities, observers and views. More specifically, we focus on the tracking of implicit interaction between entities and their environment. We integrate the user’s motion as primary input modality as well as the contexts in which the interaction takes place. We have combined the user activities with contexts to create situations. We illustrate this new concept of motion-awareness with examples of applications built on this model
Humanitarian Organization ICT field specialists training: Bridging theoretical and practical humanitarian knowledge
No full text
