Journal of Computer Applications ›› 2017, Vol. 37 ›› Issue (5): 1326-1330.DOI: 10.11772/j.issn.1001-9081.2017.05.1326

Previous Articles     Next Articles

Indoor activity-recognition based on received signal strength in WLAN

WEI Chunling, WANG Bufei   

  1. School of Electronic Information, Huanggang Normal University, Huanggang Hubei 438000, China
  • Received:2016-10-17 Revised:2016-12-19 Online:2017-05-10 Published:2017-05-16
  • Supported by:
    This work is partially supported by the Scientific Research Project of Huanggang Normal University in 2016(zj201628), Information and Communication Engineering Research Project of Huanggang Normal University in 2015(zdxk1501), Information and Communication Engineering Research Project of Huanggang Normal University in 2016 (zdxk1601); High-Level training program Project of Huanggang Normal University (201719541).


韦春玲, 王步飞   

  1. 黄冈师范学院 电子信息学院, 湖北 黄冈 438000
  • 通讯作者: 韦春玲
  • 作者简介:韦春玲(1980-),女,陕西西安人,讲师,硕士,主要研究方向:通信与信息系统;王步飞(1964-),男,湖北麻城人,副教授,硕士,主要研究方向:通信工程。
  • 基金资助:

Abstract: The mainstream activity recognition technology depends on professional measurement equipment, which leads to the problem of difficult deployment and use. An activity identification technology based on the characteristics of existing WiFi hotspot received signal strength was proposed. The result shows that the proposed algorithm is capable of identifying the existence of a person in the room with 80% accuracy. And person's standing, walking and lying activity can be inferred with 95% accuracy. The walking direction can also be identified with 80% accuracy. The required signal of the proposed algorithm exists everywhere in daily life, and can be effectively used to identify indoor activities with low power consumption, and high precision.

Key words: receiver signal strength, indoor activity-recognition, machine learning, Wireless Local Area Network (WLAN), smart home

摘要: 针对主流的活动感知技术依赖于专业测量设备,难以广泛部署与使用的问题,提出一种基于现有WiFi热点接收信号强度特征的活动识别技术。利用机器学习算法对实时接收到的WiFi信号强度特征进行分类,通过特征匹配识别用户当前活动。实验结果显示,所提算法能够以80%以上概率判断室内是否有人,以95%以上概率判断室内的人处于什么状态,并以80%的概率识别人的运动方向。所提算法所需信号广泛存在,可有效识别室内活动,具有低功耗、高精度的优点。

关键词: 接收信号强度, 室内活动识别, 机器学习, 无线局域网, 智能家居

CLC Number: