摘要
人体活动行为识别在医疗、安全、娱乐等方面有着广泛的应用,为了高效、准确地获取人体活动的行为信息,提出一种基于加速度传感器和神经网络的个人活动行为识别方法。该方法通过在个人手上佩戴加速度传感器,实时采集个人活动的行为数据;再通过BP神经网络分析相关行为数据并建立个人活动行为模型,分类识别个人的行走、坐着、躺卧、站立和突然跌倒等活动行为特征。实验结果表明,该方法能够有效检测到个人活动的行为特征参数,并可准确识别出人体活动的五种典型行为。
Human activity behavior recognition has a wide range of applications in medical treatment,safety,entertainment and so on. In order to efficiently and accurately obtain human activity behavior information,a method of personal activity behavior recognition based on acceleration sensor and neural network is proposed in this paper. The method can realize realtime acquisition of personal activity behavior data by acceleration sensor acquisition nodes worn on the hands of individuals. The relevant behavior data is analyzed and the personal activity behavior model is established by means of BP neural network,so as to identify the characteristics of five kinds of individual activity behaviors:walking,sitting,lying down,standing and suddenly falling according to classification criteria. The experimental results show that the proposed method can effectively detect the behavioral characteristic parameters of individual activities and accurately identify five typical behaviors of human activities.
作者
张烈平
匡贞伍
李昆键
韦克莹
王政忠
张声岚
王瑞
ZHANG Lieping;KUANG Zhenwu;LI Kunjian;WEI Keying;WANG Zhengzhong;ZHANG Shenglan;WANG Rui(College of Mechanical and Control Engineering,Guilin University of Technology,Guilin 541004,China)
出处
《现代电子技术》
北大核心
2019年第16期71-74,78,共5页
Modern Electronics Technique
基金
国家自然科学基金项目(61741303)
广西空间信息与测绘重点实验室基金项目(15-140-07-23)
广西空间信息与测绘重点实验室基金项目(16-380-25-23)
国家级大学生创新创业训练计划项目(201810596049)~~
关键词
人体活动
行为识别
特征提取
加速度传感器
BP神经网络
实验仿真
human activity
behavior recognition
feature extraction
acceleration sensor
BP neural network
experimental simulation