生物医学工程研究2025，Vol.44Issue(1)：1-7,7.DOI:10.19529/j.cnki.1672-6278.2025.01.01
基于小波变换与随机森林算法的针刺手法脑电分类研究
EEG classification for acupuncture manipulation based on wavelet transform and random forest algorithm
摘要
Abstract
To investigate the specificity of different acupuncture manipulations on electroencephalogram(EEG)signals,the EEG signals after acupuncture manipulations at Quchi(LI11)were classified based on wavelet transform and random forest algorithm.First-ly,18 healthy volunteers were performed three kinds of acupuncture intervention at LI11(reinforcing,reducing,and even reinforcing-re-ducing methods).The scalp EEG signals of 100 s during acupuncture were recorded and segmented by 2 s.Secondly,the mean energy and wavelet entropy of δ,θ,α,β and γ waves were extracted by wavelet transform to construct the feature set.Finally,the features were sorted by maximal-relevance-minimal-redundancy algorithm,combined with the random forest algorithm,and the model perform-ance assessed via 10-fold cross-validation.The results showed that the classification accuracy of the model based on random forest al-gorithm could reach 0.950 for the EEG signals of three kinds of acupuncture manipulations.The research enables the classification of EEG signals induced by three acupuncture manipulations at LI11,indicating the significant differences of acupuncture manipulations in the regulation of brain function,and can provide a new method and approach for the quantitative evaluation of acupuncture efficacy.关键词
针刺手法/脑电/小波变换/随机森林/曲池穴Key words
Acupuncture manipulations/Eletroencephalogram/Wavelet transform/Random forest/Quchi acupoint分类
基础医学引用本文复制引用
张可,姚勇,徐刚,杨华元..基于小波变换与随机森林算法的针刺手法脑电分类研究[J].生物医学工程研究,2025,44(1):1-7,7.基金项目
上海市科技创新行动计划启明星计划扬帆专项项目(22YF1449100) （22YF1449100）
上海中医药大学预算内项目(2021LK103). （2021LK103）
