摘要
基于随机性、相似性和稳定性,通过定标集、预测集、检验集的建模过程,采用可见-近红外(NIR)光谱结合偏最小二乘(PLS)方法建立人类溶血液样品的血红蛋白(Hb)的分析模型。将全谱扫描区(400—249 8 nm)分成可见区(400—780nm)、短波近红外区(780—110 0 nm)、长波近红外区(1100—249 8 nm)、可见-短波近红外区(400-1100 nm)、全近红外区(780—249 8 nm)。经过比较、检验,结果表明,可见-短波近红外区达到了最好的模型效果和稳定性,最优PLS因子数为7,检验的预测均方根误差(V-SEP)和预测相关系数(V-RP)分别为4.42 g.L-1、0.967,达到了高的预测精度和稳定性。
Through rigorous modeling process including the calibration set, the prediction set and validation set based on randomness, similarity and stability, the analytical model of hemoglobin （Hb） in human hemolysis samples was established by visible and near-infrared （VIS-NIR） spectroscopy combined with partial least squares （PLS） method. The overall scanning region （400-2 498 nm） was separated into the visible region （400-780 nm） , the short-wave NIR region （780-1 100 nm）, and the long-wave NIR region （ 1 100-2 498 nm）, the VIS- short NIR region （400-1 100 nm）, the overall NIR region （780-2 498 nm）. By comparison and validation, the results indicated that the VIS-short NIR region had the best prediction accuracy and stability, and the optimal PLS factor was 7, the validation root mean square error of prediction （ V SEP） and the validation correlation coefficient of prediction （V-RP） were 4. 42 （ g ·L^-1 ） and 0. 967 （ g ·L^-1）, respectively, and high prediction accuracy with sta- bility is achieved.
出处
《科学技术与工程》
北大核心
2013年第8期2174-2177,共4页
Science Technology and Engineering
基金
国家自然科学基金(61078040)
广东省科技计划(2009A030301002
2009B030801239)资助
