电子学报2024，Vol.52Issue(12)：4153-4165,13.DOI:10.12263/DZXB.20230475
基于改进的非负矩阵分解技术的抗运动干扰心电信号感知方法
Motion-Robust Electrocardiogram Signal Sensing Based on Modified Non-Negative Matrix Factorization
摘要
Abstract
Continuous electrocardiogram(ECG)monitoring is crucial for effectively preventing and diagnosing car-diovascular diseases.However,existing ECG monitoring methods are limited by their reliance on expensive equipment un-available to common users,the stringent requirements of the monitoring process,and confined application scenarios,mak-ing them insufficient to meet the urgent need for long-term continuous ECG monitoring of the general population in their daily lives.Given these limitations,this study proposes a motion-robust ECG signal sensing method based on modified non-negative matrix factorization(NMF).The basic idea is to leverage a gyroscope embedded into a low-cost wrist-worn wear-able to characterize cardiac activities encoded into body vibrations and interpret them to generate fine-grained ECG signals accurately.As eliminating body motion interference is inherently hard,this work innovatively employs modified NMF to tackle the problem;this can effectively handle body motion interference,even if untrained,and extract the cardiogenic body vibrations from noisy gyroscope data.Due to the lack of clear pattern of cardiogenic body vibrations in each cardiac cycles,current cardiac cycle segmentation solutions cannot be applied.Thus,this work deeply analyses the morphological features of cardiogenic body vibrations and utilizes machine learning techniques for the identification of spike points for segmenta-tion.Finally,cycle generative adversarial network(CycleGAN)framework is employed to construct a correlation mapping model between the cardiogenic body vibrations and the ECG signals.With innovative construction,this model can accurate generation of the ECG signals without the need for a huge amount of training data.Extensive experiments with 18 volun-teers confirm the effectiveness of the proposed method,with the average amplitude errors of 7.92%and 9.02%for station-ary and moving scenarios,respectively.These values fall well within the acceptable range of medical standards for error tol-erance of less than 10%.关键词
心电/腕戴式智能设备/心冲击振动/非负矩阵分解/循环生成对抗网络Key words
electrocardiogram/wrist-worn devices/cardiogenic body vibrations/non-negative matrix factorization/cycle generative adversarial network分类
信息技术与安全科学引用本文复制引用
曹烨彤,李凡,刘晓晨,谢睆冉,陈慧杰..基于改进的非负矩阵分解技术的抗运动干扰心电信号感知方法[J].电子学报,2024,52(12):4153-4165,13.基金项目
国家自然科学基金(No.62372045,No.62072040,No.62202019) （No.62372045,No.62072040,No.62202019）
中国博士后科学基金(No.2021M700302) National Natural Science Foundation of China(No.62372045,No.62072040,No.62202019) （No.2021M700302）
China Postdoctoral Science Foundation under Grant(No.2021M700302) （No.2021M700302）
