基于自适应免疫-最小一乘算法的生物电阻抗特征参数提取  

Extraction of bioimpedance characteristic parameters based on adaptive immune-least absolute deviation algorithm

作　　者：黄经纬 曹乐 阚秀[1] 李敏 HUANG Jingwei;CAO Le;KAN Xiu;LI Min(School of Electronic and Electrical Engineering,Shanghai University of Engineering Science,Shanghai 201620,China)

机构地区：[1]上海工程技术大学电子电气工程学院,上海201620

出　　处：《中国医学物理学杂志》2021年第8期1005-1012,共8页Chinese Journal of Medical Physics

基　　金：国家自然科学基金(61703270)。

摘　　要：针对Cole-Cole参数的提取,本文提出自适应免疫-最小一乘算法。首先,通过制定自适应策略,并增设记忆单元,设计本算法对Cole-Cole参数的提取流程;其次,在标准生物阻抗数据集基础上分别添加3种不同噪声,并设置评价指标,对比分析自适应免疫-最小一乘算法与另外3种算法对Cole-Cole圆弧的拟合精度及Cole-Cole参数的提取结果;最后,基于自适应免疫-最小一乘算法,对其在噪声数据集下提取Cole-Cole参数的耗时长短及初值依赖性做出考量。实验结果表明,该算法相较于另外3种算法能够精准、快速地提取Cole-Cole参数,且对初值的依赖性不高。An adaptive immune-least absolute deviation algorithm is proposed for extracting Cole-Cole parameters.The extraction of Cole-Cole parameters by the proposed algorithm is realized by formulating adaptive policies and adding memory units.Then,3 different kinds of noises are added to the standard data sets of the bioimpedance,and related evaluation indicators were set.Based on the fitting accuracy of Cole-Cole arcs and the extraction results of Cole-Cole parameters,the proposed adaptive immune-least absolute deviation algorithm is compared with other 3 algorithms.Finally,the time-consuming and dependence on the initial values of the proposed algorithm for extracting Cole-Cole parameters from the noise data sets are analyzed.Experimental results show that the Cole-Cole parameters can be extracted accurately and quickly by the proposed algorithm compared with other 3 algorithms,and that the dependence on the initial values is relatively low.

关 键 词：生物阻抗 自适应免疫算法 最小一乘法 Cole-Cole参数 

分 类 号：R318[医药卫生—生物医学工程]