为提高近红外血红蛋白预测模型的稳健性, 分别应用Savitzky-Golay平滑、 移动窗口平滑以及经验模态分解(EMD)方法对原始光谱进行去噪处理, 以提高数据信噪比。 采集了81例临床志愿者的手指指端血流容积脉搏波光谱数据, 同时获取相应的血红蛋白浓度值临床化验结果。 剔除异常样品, 确定78例样品为研究对象, 建立反向传播神经网络(BP-ANN)定量分析模型并预测。 结果表明, 经EMD处理后的模型预测效果最优, 预测相关系数由0.74提高至0.87, 误差均方根由12.85 g·L-1减小至8.08 g·L-1。 实验证明应用EMD方法能够获得高信噪比的容积脉搏信号, 提高血红蛋白浓度预测模型的准确性, 有利于推动近红外无创血红蛋白检测技术的进一步发展。

To increase the signal-to-noise ratio (SNR) of human near infrared (NIR) spectra, so as to improve the stability and precision of calibration model, the empirical mode decomposition (EMD) method was applied. Eighty-one fingertip absorption curves were collected, with the corresponding clinical examination results obtained immediately. By means of outliers detection and removal, finally 78 samples were determined as the research objects. A three-layer back-propagation artificial neutron network (BP-ANN) model was established and worked for prediction. The results turned out that, through EMD method, the prediction correlation coefficient increased greatly from 0.74 to 0.87. RMSEP was reduced from 12.85 to 8.08 g·L-1. Other indexes were also obviously improved. The overall results sufficiently demonstrate that it is feasible to use EMD method for high SNR pulse wave signals, thus improving the performance of noninvasive hemoglobin calibration models. The application of EMD method can help promote the development of noninvasive hemoglobin monitoring technology.