Analyze the near infrared spectrum of the glucose concentration using main component regression and partial least square algorithm, build up the adjusting mathematical model.
采用主成分回归和偏最小二乘法分别对血糖近红外光谱进行分析，建立数学校正模型。
For all samples, the raw spectra were pretreated as second derivative and Norris derivative filter(7,5). partial least square (PLS) was used as the calibration algorithm.
在所有的校正模型中，原始谱图经过二阶导数和偏最小二乘（ PLS）处理，20个外部样品用于所建模型的验证，实际和预测的平均相对偏差<5%。
应用推荐