Activity Recognition with Smartphone Sensors
Activity Recognition with Smartphone Sensors
复制标题
DOI：
10.1109/tst.2014.6838194
复制
发表时间：
2014-06-01
影响因子：
6.6
通讯作者：
Ji, Ping
中科院分区：
文献类型：
--
作者：
Su, Xing;Tong, Hanghang;Ji, Ping
无处不在的智能手机及其不断增长的计算、网络和传感能力正在改变人们日常生活的面貌。其中，以原始传感器读数为输入并预测用户运动活动的活动识别是近年来一个活跃的研究领域。它是许多高影响力应用的核心构建模块，包括健康和健身监测、个人生物特征签名、城市计算、辅助技术、老年人护理、室内定位和导航等。本文全面介绍了智能手机传感器在活动识别方面的最新进展。我们从传感器、活动类型等基本概念开始。我们回顾了主流活动识别算法背后的核心数据挖掘技术，分析了它们的主要挑战，并介绍了活动识别支持的各种实际应用。
The ubiquity of smartphones together with their ever-growing computing, networking, and sensing powers have been changing the landscape of people's daily life. Among others, activity recoginition, which takes the raw sensor reading as inputs and predicts a user's motion activity, has become an active research area in recent years. It is the core building block in many high-impact applications, ranging from health and fitness monitoring, personal biometric signature, urban computing, assistive technology, and elder-care, to indoor localization and navigation, etc. This paper presents a comprehensive survey of the recent advances in activity recognition with smartphones' sensors. We start with the basic concepts such as sensors, activity types, etc. We review the core data mining techniques behind the main stream activity recognition algorithms, analyze their major challenges, and introduce a variety of real applications enabled by activity recognition.