一种基于阵列式PVDF触觉传感器和机器学习的针刺手法识别系统  

Recognition system of acupuncture manipulations based on an array PVDF tactile sensor and machine learning

作　　者：苟升异 宿翀[1] 王磊 赵亚楠 陈捷 GOU Sheng-yi;SU Chong;WANG Lei;ZHAO Ya-nan;CHEN Jie(School of Information Science and Technology,Beijing University of Chemical Technology,Beijing 100029,China;Institute of Acupuncture and Moxibustion,China Academy of Chinese Medical Sciences,Beijing 100700;Department of Traditional Chinese Medicine,Beijing Zhongguancun Hospital,Beijing 100190)

机构地区：[1]北京化工大学信息科学与技术学院,北京100029 [2]中国中医科学院针灸研究所,北京100700 [3]北京市中关村医院中医综合科,北京100190

出　　处：《针刺研究》2021年第6期474-479,共6页Acupuncture Research

基　　金：国家自然科学基金项目(No.82074285);北京市中医管理局科技发展资金项目(No.JJ-2020-07)。

摘　　要：目前,对于针灸手法的学习评价,缺少针刺时施力大小、时长和方向等可以进行量化的物理参数。本文针对采集针刺过程中“捻转”和“提插”动作的触觉参数,设计了一种阵列式聚偏二氟乙烯膜(PVDF)触觉传感器;随后,给出了面向触觉信号的窗口分割方法,并提取窗口中的时域特征;最后,构建了一种基于模糊C均值聚类法(FCM)的针刺手法识别方法。通过实验证明该方法能够有效识别捻转补、捻转泻、提插补、提插泻四种基本针刺动作,有利于针刺手法的量化与传播。In learning and evaluation of acupuncture manipulations,there are lack of quantitative physical parameters on exertion strength,duration and direction of acupuncture technique at present.Based on the tactile parameters collected during“twirling”and“lifting-thrusting”of needling,a kind of array polyvinylidene fluoride(PVDF)tactile sensor was designed.Followed by,a window segmentation method for tactile signal was proposed and the time domain features of the window were extracted.Finally,an identification method of acupuncture manipulation based on FCM(Fuzzy C-Means)was constructed.Through the experiment,it was proved that this sensor can effectively identify the four kinds of basic acupuncture manipulations,i.e.reinforcing by twirling and rotating,reducing by twirling and rotating,reinforcing by lifting and thrusting and reducing by lifting and thrusting and it was conductive to the quantification and dissemination of acupuncture manipulations.

关 键 词：聚偏二氟乙烯膜传感器 机器学习 针刺手法分类 

分 类 号：R245-3[医药卫生—针灸推拿学]