Tianjin Key Laboratory of Risk Assessment and Control Technology for Environment and Food Safety, Tianjin Institute of Environment and Operational Medicine, Tianjin, 300050, PR China.
State Key Laboratory of Agricultural Microbiology, Huazhong Agricultural University, Wuhan, 430070, PR China.
Talanta. 2022 Jan 15;237:122901. doi: 10.1016/j.talanta.2021.122901. Epub 2021 Oct 1.
Raman spectroscopy combined with artificial intelligence algorithms have been widely explored and focused on in recent years for food safety testing. It is still a challenge to overcome the cumbersome culture process of bacteria and the need for a large number of samples, which hinder qualitative analysis, to obtain a high classification accuracy. In this paper, we propose a method based on Raman spectroscopy combined with generative adversarial network and multiclass support vector machine to classify foodborne pathogenic bacteria. 30,000 iterations of generative adversarial network are trained for three strains of bacteria, generative model G generates data similar to the actual samples, discriminant model D verifies the accuracy of the generated data, and 19 feature variables are obtained by selecting the feature bands according to the Raman spectroscopy pattern. Better classification results are obtained by optimising the parameters of the multi-class support vector machine, etc. Our detection and classification method not only solves the problem of needing a large number of samples as training set, but also improves the accuracy of the classification model. Therefore, this GAN-SVM classification model provides a new idea for the detection of bacteria based on Raman spectroscopy technology combined with artificial intelligence algorithms.
近年来，拉曼光谱结合人工智能算法在食品安全检测方面得到了广泛的探索和关注。然而，仍面临着克服细菌繁琐的培养过程以及需要大量样本的挑战，这阻碍了定性分析，难以获得高分类准确性。在本文中，我们提出了一种基于拉曼光谱结合生成对抗网络和多类支持向量机的方法，用于对食源性致病菌进行分类。针对三种细菌进行了 30000 次的生成对抗网络训练，生成模型 G 生成与实际样本相似的数据，判别模型 D 验证生成数据的准确性，并根据拉曼光谱图谱选择特征波段，获得 19 个特征变量。通过优化多类支持向量机的参数等方法，获得了更好的分类结果。我们的检测和分类方法不仅解决了需要大量样本作为训练集的问题，而且提高了分类模型的准确性。因此，该 GAN-SVM 分类模型为基于拉曼光谱技术结合人工智能算法的细菌检测提供了新的思路。
