School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.
School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.
Food Chem. 2019 May 15;280:139-145. doi: 10.1016/j.foodchem.2018.12.031. Epub 2018 Dec 13.
Aimed to rapidly identify the edible oils according to their botanical origin, a novel method was proposed using supervised support vector machine based on low-field nuclear magnetic resonance and relaxation features. The low-field (LF) nuclear magnetic resonance (NMR) signals of 11 types of edible oils were acquired, and 5 features were extracted from the transverse relaxation decay curves and modeled using support vector machines (SVM) for the identification of edible oils. Two SVM classification strategies have been applied and discussed. Good performance can be achieved when the relative position of each edible oil has been determined by PCA before the designing of binary tree structure of SVM model, and the classification accuracy is 99.04%. The good robustness of this method has been verify at different data sets. It is almost a real time method, and the entire process takes only 144 s.
为了快速根据植物来源鉴别食用油，提出了一种新的基于低场核磁共振和弛豫特征的有监督支持向量机方法。采集了 11 种食用油的低场（LF）核磁共振（NMR）信号，从横向弛豫衰减曲线中提取 5 个特征，并使用支持向量机（SVM）对特征进行建模，以鉴别食用油。应用并讨论了两种 SVM 分类策略。通过 PCA 确定每种食用油的相对位置，然后设计 SVM 模型的二叉树结构，可获得良好的性能，分类准确率为 99.04%。该方法在不同数据集上具有良好的稳健性。这几乎是一种实时方法，整个过程仅需 144s。
