基于最小二乘法的动态光谱补偿拟合提取

高信噪比的动态光谱(dynamic spectrum, DS)提取是实现高精度动态光谱血液成分无创检测的一个关键。为了进一步提高提取的精度和速度，从原理上分析了各单波长光电容积脉搏波(photoelectric plethysmography，PPG)的线性相似性，并基于此性质提出了补偿拟合法：首先按照PPG单周期采样点数进行滑动平均得到漂移基线进行补偿，除去基线漂移;其次用各波长对数PPG与全波长叠加平均模板PPG进行最小二乘拟合，提取一次项系数构成DS。利用拟合提取法对近红外和可见光波段各25组PPG数据样本进行DS提取实验验证，并将结果与单沿提取法进行平滑性指标的对比，结果表明：近红外和可见光波段补偿拟合法获取DS的平均方差分别为单沿提取法的77.9%和59.5%，稳定提高了DS的平滑性;近红外和可见光波段补偿拟合法处理时间分别可以达到单沿提取法的10%和20%，处理速度得到显著改善。补偿拟合法在单沿提取法的基础上稳定提高了DS的信噪比，改善了DS提取质量，缩减了提取时间，并简化了处理步骤，有望推动DS无创血液成分检测的发展。

Compensation-Fitting Extraction of Dynamic Spectrum Based on Least Squares Method

Extraction method for dynamic spectrum (DS) with a high signal to noise ratio is a key to achieving high-precision noninvasive detection of blood components. In order to further improve the accuracy and speed of DS extraction, linear similarity between photoelectric plethysmographys (PPG) at each two different wavelengths was analyzed in principle, and an experimental verification was conducted. Based on this property, the method of compensation-fitting extraction was proposed. Firstly, the baseline of PPG at each wavelength is estimated and compensated using single-period sampling average, which would remove the effect of baseline drift caused by motion artifact. Secondly, the slope of least squares fitting between each single-wavelength PPG and full-wavelength averaged PPG is acquired to construct DS, which would significantly suppress random noise. Contrast experiments were conducted on 25 samples in NIR wave band and Vis wave band respectively. Flatness and processing time of DS using compensation-fitting extraction were compared with that using single-trial estimation. In NIR band, the average variance using compensation-fitting estimation was 69.0% of that using single-trial estimation, and in Vis band it was 57.4%, which shows that the flatness of DS is steadily improved. In NIR band, the data processing time using compensation-fitting extraction could be reduced to 10% of that using single-trial estimation, and in Vis band it was 20%, which shows that the time for data processing is significantly reduced. Experimental results show that, compared with single-trial estimation method, dynamic spectrum compensation-fitting extraction could steadily improve the signal to noise ratio of DS, significantly improve estimation quality, reduce data processing time, and simplify procedure. Therefore, this new method is expected to promote the development of noninvasive blood components measurement.