基于改进变分模态分解的生命体征检测

Vital signs detection based on improved variational mode decomposition

变分模态分解方法常被用于生命体征信号检测,针对该方法模态个数确定存在主观性的问题,提出一种改进变分模态分解方法进行非接触式测量生命体征信号.利用毫米波雷达获得生命体征回波信号,经过降噪、目标距离单元定位等处理获得生命体征信号.生命体征信号成分主要包括心跳与呼吸信号.其中心跳信号能量小,受呼吸信号影响大,本方法利用余量与模态分量重构信号的自相关系数确定最优分解模态数量,避免了模态数量的过分解和欠分解,达到自适应分离生命体征信号的目的 .实验结果表明,与变分模态分解方法相比,该方法可自适应确定模态分解个数.

Variational modal decomposition method is often used for vital sign signal detection. Aiming at the problem of subjectivity in determining the number of modes in this method, this paper proposes an improved variational modal decomposition method for non-contact measurement of vital sign signals. Here,the millimeter wave radar is used to obtain the vital sign echo signal,and the vital sign signal is obtained through noise reduction,target distance unit positioning and other processing. The vital sign signal components mainly include heartbeat and respiration signals. Among them,the energy of the heartbeat signal is small and is greatly affected by the breathing signal. The method proposed uses the autocorrelation coefficient of the residual and modal components to reconstruct the signal to determine the optimal number of decomposed modes, which avoids over-decomposition and under-decomposition of the number of modes. The purpose of adaptively separating vital sign signals is achieved. The experimental results show that, compared with the variational modal decomposition method,the proposed method can adaptively determine the number of modal decompositions.