China
Africa
Explore chapters and articles related to this topic
Indoor Localization and Tracking Systems
Published in Yufeng Wang, Athanasios V. Vasilakos, Qun Jin, Hongbo Zhu, Device-to-Device based Proximity Service, 2017
Yufeng Wang, Athanasios V. Vasilakos, Qun Jin, Hongbo Zhu
Wi-Fi is one of the most popular wireless network technologies and widely deployed in almost every building. Therefore, it could be naturally used to estimate the location of mobile devices within this network. Indoor positioning system based on Wi-Fi fingerprint consists of three main physical entities: wireless network terminal, wireless local area networks (WLANs) hotspots (i.e., AP) in fixed-location, and position platform. As Figure 7.2 shows, Wi-Fi fingerprint-based indoor localization can be divided into two phases: training phase (to construct offline Wi-Fi fingerprint database) and real-time positioning phase.
Stop motion: using high resolution spatiotemporal data to estimate and locate stationary and movement behaviour in an office workplace
Published in Ergonomics, 2022
Brett Pollard, Gordon McDonald, Fabian Held, Lina Engelen
Recently, Indoor Positioning Systems (IPS) based on technologies, such as Bluetooth, Radio-Frequency Identification (RFID), and Ultra-Wideband, have become available, allowing the collection of high-resolution, spatiotemporal data within buildings (Loveday et al. 2016; Mautz 2012). To date, measuring building occupancy levels has been a focus of research efforts (Baek and Cha 2019; Cha et al. 2018). While other studies have used IPS to examine movement within buildings, they have focussed on specific movement types and contexts, such as the atypical movement of developmentally delayed children in an early childcare centre (Irvin et al. 2018) or the wandering behaviour of residents with dementia in assisted living facilities (Kumar et al. 2016). Other studies have used the systems to assess patient waiting times in a hospital imaging department (Amir et al. 2019) or the interaction of teachers and students in classrooms (Martinez-Maldonado et al. 2020). The small number of physical activity studies undertaken in office workplaces have used systems with a low spatial resolution to provide broad locational context to accelerometer data collected over very short time periods (Clark et al. 2018; Magistro et al. 2018; Spinney et al. 2015). We are not aware of any studies that have used high-resolution spatiotemporal data to estimate and locate stationary and non-stationary movement behaviour in office workplaces.