Belmonte-Fernández Óscar, Puertas-Cabedo Adrian, Torres-Sospedra Joaquín, Montoliu-Colás Raúl, Trilles-Oliver Sergi
Institute of New Imaging Technologies (INIT), Jaume I University, Av. Vicente Sos Baynat s/n, 12071 Castelló de la Plana, Spain.
Soluciones Cuatroochenta S.L., Av. Vicente Sos Baynat s/n, Espaitec2 Building, 12071 Castelló de la Plana, Spain.
Sensors (Basel). 2016 Dec 25;17(1):36. doi: 10.3390/s17010036.
The urban population is growing at such a rate that by 2050 it is estimated that 84% of the world's population will live in cities, with flats being the most common living place. Moreover, WiFi technology is present in most developed country urban areas, with a quick growth in developing countries. New Ambient-Assisted Living applications will be developed in the near future having user positioning as ground technology: elderly tele-care, energy consumption, security and the like are strongly based on indoor positioning information. We present an Indoor Positioning System for wearable devices based on WiFi fingerprinting. Smart-watch wearable devices are used to acquire the WiFi strength signals of the surrounding Wireless Access Points used to build an ensemble of Machine Learning classification algorithms. Once built, the ensemble algorithm is used to locate a user based on the WiFi strength signals provided by the wearable device. Experimental results for five different urban flats are reported, showing that the system is robust and reliable enough for locating a user at room level into his/her home. Another interesting characteristic of the presented system is that it does not require deployment of any infrastructure, and it is unobtrusive, the only device required for it to work is a smart-watch.
城市人口正以这样一种速度增长，以至于据估计到2050年世界84%的人口将居住在城市，公寓是最常见的居住场所。此外，WiFi技术在大多数发达国家的城市地区都有应用，在发展中国家也迅速发展。在不久的将来，将开发以用户定位为基础技术的新型环境辅助生活应用：老年远程护理、能源消耗、安全等都强烈依赖于室内定位信息。我们提出了一种基于WiFi指纹识别的可穿戴设备室内定位系统。智能手表可穿戴设备用于获取周围无线接入点的WiFi强度信号，这些信号用于构建机器学习分类算法集合。一旦构建完成，该集合算法就用于根据可穿戴设备提供的WiFi强度信号来定位用户。报告了五个不同城市公寓的实验结果，表明该系统在将用户定位到其家中的房间级别时足够稳健和可靠。所提出系统的另一个有趣特性是它不需要部署任何基础设施，而且不引人注意，其工作所需的唯一设备是智能手表。
