基于传递熵的复杂网络人体平衡特征分析  

Analysis of Human Body Balance Characteristics in Complex Network Based on Transfer Entropy

作　　者：王哲远 罗志增[2] 裘晟晨 Wang Zheyuan;Luo Zhizeng;Qiu Shenchen(HDU-ITMO Joint Instiute,Hangzhou Danzi Unineniy,Hangzhou 310018,China;Instiute of Ilelligent Control and Robotics,School of Auonation,Hangzhou Diani Unicersily,Hangzhou 310018,China;The Fourth Ailiated Hospital Zhejiang Unitersity School of Medicine,Jinhua 32000 Zhejiang,China)

机构地区：[1]杭州电子科技大学圣光机联合学院,杭州310018 [2]杭州电子科技大学自动化学院智能控制与机器人研究所,杭州310018 [3]浙江大学医学院附属第四医院,浙江金华32000

出　　处：《中国生物医学工程学报》2022年第2期159-166,共8页Chinese Journal of Biomedical Engineering

基　　金：国家自然科学基金(61671197);浙江省教育厅科研项目(Y202044328)。

摘　　要：为克服人体平衡能力医学评估方法中的主观性缺陷,提出一种基于相位同步数据筛选和传递熵脑网络特征的人体平衡能力评估算法;采集20名被试在本体觉与视觉分别被阻断的4种范式下共1 200 min的EEG平衡数据;基于人体平衡生理机制,利用相位同步特性计算每段数据间的锁相值,并按照调节指标筛选出有效数据段,经过数据筛选后得到859段有效数据,每段长度在50~2 000 ms。利用该数据构建基于传递熵的脑功能网络连接模型,并定义了一种能够同步反映人体平衡信息接收与运动感觉协同处理的特征系数。在同一批次的实验数据中进行10折交叉验证。结果发现,新特征的加入将4类范式的整体分类准确率提高到73.63%,高于其他脑功能网络特征(56.23%)和足底压力中心(COP)特征(67.90%)。根据同步性分析结果推断视觉系统在人体平衡调节中占据主要作用;人体平衡协调新特征的应用可使平衡分类结果准确性有效提高。In order to overcome the subjective defects of medical evaluation methods for human balance ability, an algorithm based on phase synchronization screening data and transfer entropy brain network was proposed. A total of 1 200 minutes of EEG balance data were collected from 20 subjects under 4 paradigms of occlusion of proprioception and vision. According to the physiological mechanism of human balance, the effective data segment of the balance adjustment process was screened through the phase synchronization. After data screening, 859 valid data segments were obtained, each with a length of 50~2 000 ms, and the brain function network model based on the transfer entropy was constructed from the screening results. A kind of characteristics was defined that can reflect the reception of human balance information and cooperative processing of motion perception. The 10-fold cross-validation in the same batch of experimental data showed that the new feature improved the classification accuracy of the 4 paradigms to 73.63%, which was higher than that of other brain functional network features(56.23%) and center of pressure(COP) features(67.90%). According to the analysis of synchronization, it is concluded that the visual system plays a major role in the adjustment of human body balance. The application of the new balance features has significantly improved the accuracy of the classification.

关 键 词：平衡能力评估 脑电信号相位同步 传递熵 平衡调节协同系数 

分 类 号：R318[医药卫生—生物医学工程]