近红外光谱结合特征变量筛选方法测定茶汤中的氨基酸含量.docxVIP

Acta Agriculturae Universitatis JiangxiensisE － mail: ndxb7775@ sina． com近红外光谱结合特征变量筛选方法测定茶汤中的氨基酸含量吴彦红1 ，艾施荣2 ，严霖元1* ，杨红飞1 ，胡琪1( 1． 江西农业大学 工学院，江西 南昌 330045; 2． 江西农业大学 软件学院，江西 南昌 330045 )摘要:采用透射方式获取茶汤的近红外光谱，利用特征变量筛选方法从茶汤的近红外光谱中提取氨基酸光谱信息，建立茶汤中氨基酸含量的快速检测模型。分别利用间隔偏最小二乘法( iPLS) 和联合区间偏最小二乘法 ( siPLS) 从茶汤的近红外光谱中提取微弱的氨基酸信息，建立其近红外光谱定量分析模型。结果表明，利用两 种方法筛选的特征变量都避开了水的强吸收峰影响，但利用 siPLS 方法建立的模型性能明显好于 iPLS 的。最 优的 siPLS 模型对校正集样本的相关系数为 0． 912，交互验证均方根误差为 0． 185; 用预测集中独立样本检验模 型性能，其相关系数为 0． 887，预测均方根误差为 0． 202。研究结果可为液体茶饮料中的成分实时快速检测提 供参考。关键词:茶汤; 氨基酸; 近红外光谱; 特征变量筛选中图分类号:O657． 33文献标志码:A 文章编号:1000 － 2286( 2012) 05 － 1026 － 06Determination of Amino Acid Content in Tea Infusion using NIRSpectroscopy Combined with Characteristic Variables Selection MethodsWU Yan-hong1 ，AI Shi-rong2 ，YAN Lin-yuan1* ，YANG Hong-fei1 ，HU Qi1( 1． College of Engineering，Jiangxi Agricultural University，Nanchang 330045，China; 2． College of Soft- ware，Jiangxi Agricultural University，Nanchang 330045，China)Abstract: The objective of this study was to evaluate the capacity of NIR spectroscopy to rapidly predictthe content of amino acid in tea infusion． Transmission mode was used to attain NIR spectroscopy of tea infu- sion． Interval partial least square ( iPLS) and synergy interval partial least square ( siPLS) were applied to se- lect the feeble amino acid information from NIR spectroscopy of tea infusion in this study． The optimized char- acteristic variables were used to develop PLS models． The results show that the selected feature variables based on iPLS and siPLS were not within the range of the strong absorbance for water，but the built model using si- PLS had better performance than that of iPLS． The optimal siPLS model was achieved with Rc = 0． 912 and RMSECV = 0． 185 in the calibration set，Rp = 0． 912 and RMSEP = 0． 202 in the prediction set． The attained results can provide a reference for the rapid and real － time determination of the components of in liquid tea drinks．Key words: tea infusion; amino