School of Food and Biological Engineering, Jiangsu University, Zhenjiang, People's Republic of China.
Food Sci Technol Int. 2013 Aug;19(4):305-14. doi: 10.1177/1082013212452475. Epub 2013 May 31.
Amino acid nitrogen and total acid are two most important quality indices to assess the quality of soy sauce in China. This work employed near infrared spectroscopy combined with synergy interval partial least square and genetic algorithm to detect amino acid nitrogen and total acid content in soy sauce. First, synergy interval partial least square was used to select efficient spectral regions from the full spectrum region; and then, genetic algorithm was used to selected variables from the efficient spectral regions, to build partial least square model. The optimal genetic algorithm synergy interval partial least square models were obtained as follows: Rc = 0.9988 and Rp = 0.9988 for amino acid nitrogen content model using 64 variables; Rc = 0.9917 and Rp = 0.9902 for total acid content model using 81 variables. Genetic algorithm synergy interval partial least square models showed superiority over the partial least square and synergy interval partial least square models. The results indicated that amino acid nitrogen and total acid content in soy sauce could be rapidly determined by near infrared spectroscopy technique. Also, the results indicated that genetic algorithm synergy interval partial least square can improve the performance in measurement of amino acid nitrogen and total acid content by near infrared spectroscopy.
氨基酸态氮和总酸是中国评估酱油质量的两个最重要的质量指标。本工作采用近红外光谱结合协同区间偏最小二乘法和遗传算法检测酱油中的氨基酸态氮和总酸含量。首先，采用协同区间偏最小二乘法从全光谱区域中选择有效的光谱区域；然后，遗传算法从有效光谱区域中选择变量，建立偏最小二乘模型。得到的最优遗传算法协同区间偏最小二乘模型如下：用于测定氨基酸态氮含量的模型，使用 64 个变量，Rc=0.9988，Rp=0.9988；用于测定总酸含量的模型，使用 81 个变量，Rc=0.9917，Rp=0.9902。遗传算法协同区间偏最小二乘模型优于偏最小二乘和协同区间偏最小二乘模型。结果表明，近红外光谱技术可快速测定酱油中的氨基酸态氮和总酸含量。同时，结果表明遗传算法协同区间偏最小二乘法可以提高近红外光谱法测定氨基酸态氮和总酸含量的性能。
