基于多源光谱分析技术的鱼油品牌判别方法研究

发布时间：2018-06-28 13:13

本文选题：鱼油 + 品牌判别　；参考：《现代食品科技》2014年10期

【摘要】：多源光谱分析技术被用于鱼油品牌快速无损鉴别。采用可见光谱分析技术、短波近红外光谱分析技术、长波近红外光谱分析技术、中红外光谱分析技术和核磁共振光谱分析技术采集了7种不同品牌的鱼油的光谱特征,并应用偏最小二乘判别分析法(partial least squares discrimination analysis,PLS-DA)和最小二乘支持向量机(least-squares support vector machine,LS-SVM)建立判别模型并比较判别结果。基于长波近红外光谱的PLS-DA模型和LS-SVM模型取得了最高识别正确率,建模集和预测集识别正确率均达到100%。采用中红外光谱和核磁共振谱分别建立的LS-SVM模型,也可以获得100%的判别正确率。而可见光谱和短波近红外光谱则判别准确率较差。且LS-SVM算法较PLS-DA更加适合用于建立光谱数据和鱼油品牌之间的判别模型。研究结果表面长波近红外光谱技术能够有效判别不同鱼油的品牌,为将来鱼油品质鉴定便携式仪器的开发提供了技术支持和理论依据。
[Abstract]:Multi-source spectral analysis is used for fast non-destructive identification of fish oil brands. The spectral characteristics of seven different brands of fish oil were collected by visible spectrum analysis, short wave near infrared spectroscopy, long wave near infrared spectroscopy, mid infrared spectroscopy and nuclear magnetic resonance spectroscopy. Partial least squares discriminant analysis method (partial least squares discrimination analysism PLS-DA) and least squares support vector machine (least-squares support vector machine) are used to establish the discriminant model and compare the discriminant results. The PLS-DA model and LS-SVM model based on long wave near infrared spectrum (LS-SVM) have achieved the highest recognition accuracy. The recognition accuracy of both the modeling set and the prediction set is 100. The LS-SVM model established by mid-infrared spectrum and nuclear magnetic resonance spectrum can also obtain 100% accuracy. But the accuracy of visible spectrum and short wave near infrared spectrum is poor. The LS-SVM algorithm is more suitable than PLS-DA to establish the discriminant model between the spectral data and the fish oil brand. The results show that the surface long wave near infrared spectroscopy (LWNIR) technology can effectively identify the brands of different fish oils and provide technical support and theoretical basis for the development of portable instrument for fish oil quality evaluation in the future.
【作者单位】：浙江经济职业技术学院;浙江大学生物系统工程与食品科学学院;
【基金】：国家自然科学基金(31072247)
【分类号】：O657.3;TS225.24

【参考文献】