School of Electrical and Information Engineering, Jiangsu University, Zhenjiang, 212013, China.
School of Food and Biological Engineering, Jiangsu University, Zhenjiang, 212013, China.
J Sci Food Agric. 2021 Jun;101(8):3448-3456. doi: 10.1002/jsfa.10975. Epub 2020 Dec 21.
The edible oil storage period is one of the important indicators for evaluating the intrinsic quality of edible oil. The present study aimed to develop a portable electronic nose device for the qualitative identification of the edible oil storage period. First, four metal oxide semiconductor gas sensors, comprising TGS2600, TGS2611, TGS2620 and MQ138, were selected to prepare a sensor array to assemble a portable electronic nose device. Second, the homemade portable electronic nose device was used to obtain the odor change information of edible oil samples during different storage periods, and the sensor features were extracted. Finally, three pattern recognition methods, comprising linear discriminant analysis (LDA), K-nearest neighbors (KNN) and support vector machines (SVM), were compared to establish a qualitative identification model of the edible oil storage period. The input features and related parameters of the model were optimized by a five-fold cross-validation during the process of model establishment.
The research results showed that the recognition performance of the non-linear SVM model was significantly better than that of the linear LDA and KNN models, especially in terms of generalization performance, which had a correct recognition rate of 100% when predicting independent samples in the prediction set.
The overall results demonstrate that it is feasible to apply the homemade portable electronic nose device with the help of the appropriate pattern recognition methods to achieve the fast and efficient identification of the edible oil storage period, which provides an effective analysis tool for the quality detection of the edible oil storage. © 2020 Society of Chemical Industry.
食用油的储存期是评价食用油内在质量的重要指标之一。本研究旨在开发一种用于定性识别食用油储存期的便携式电子鼻装置。首先，选择了四种金属氧化物半导体气体传感器，包括 TGS2600、TGS2611、TGS2620 和 MQ138，用于制备传感器阵列，组装便携式电子鼻装置。其次，使用自制的便携式电子鼻装置获取不同储存期食用油样品的气味变化信息，并提取传感器特征。最后，比较了三种模式识别方法，包括线性判别分析（LDA）、K-最近邻（KNN）和支持向量机（SVM），以建立食用油储存期的定性识别模型。在模型建立过程中，通过五折交叉验证对模型的输入特征和相关参数进行了优化。
研究结果表明，非线性 SVM 模型的识别性能明显优于线性 LDA 和 KNN 模型，尤其是在泛化性能方面，在预测集的独立样本预测中具有 100%的正确识别率。
总体结果表明，借助适当的模式识别方法，使用自制的便携式电子鼻装置实现食用油储存期的快速、高效识别是可行的，为食用油储存质量检测提供了有效的分析工具。© 2020 英国化学学会。
