摘要
针对跌倒检测特征值提取的问题,提出了通过分数阶Fourier变换(FractionalFourier Transform,FRFT)进行时频分析并提取特征值的方法,通过穿戴在人体上的15个IMU采集运动过程中的惯性数据,经过多阶次分数阶Fourier变换后,分析并比较其特征。比较了8种跌倒姿态的特征分布及这8种跌倒姿态与4种日常运动的特征分布,验证了将分数阶Fourier变换应用于跌倒检测的可行性。
Aiming at the problem of features extract method for fall detection, the method using time-frequency analyze and features extraction by Fractional Fourier Transform(FRFT) has been proposed. The inertial data is measured by 15 IMU wearing on body, the features extracted after FRFT with multiple order are analyzed and compared. The difference of feature distribution of eight fall actions has been compared, and the difference of feature distribution between fall action and 4 normal actions has been compared. The feasibility of using FRFT in fall detection is proved.
作者
王天润
苏中
刘宁
李超
付国栋
Wang Tianrun;Su Zhong;LiuNing;Li Chao;Fu Guodong(Beijing Information Science and Technology University,Beijing Key Laboratory of High Dynamic Navigation Technology,Beijing 100101,China;Ministry of Education Key Laboratory of Modem Measurement and Control,Beijing 100101,China;School of Automation,Beijing Institute of Technology,Beijing 100084,China;Beijing DWIN Co.,Ltd,Beijing 100089,China)
出处
《系统仿真学报》
CAS
CSCD
北大核心
2019年第12期2600-2605,共6页
Journal of System Simulation
基金
国家自然科学基金(61801032)
北京市自然科学基金(3184046)
北京市教育委员会科技计划一般项目(77F1910963,71E1810971)
现代测控教育部重点实验室资助(77F1910905)
北京信息科技大学“勤信人才”培育计划(5111911163)
