This study tackled mislabeling fraud in vegetable oils, driven by price disparities and profit motives, by developing an approach combining desorption electrospray ionization mass spectrometry (DESI-MS) with a shallow convolutional neural network (SCNN). The method was designed to characterize lipids and distinguish between nine vegetable oils: corn, soybean, peanut, sesame, rice bran, sunflower, camellia, olive, and walnut oils. The optimized DESI-MS method enhanced the ionization of non-polar glycerides and detected ion adducts like [TG + Na]⁺, [TG + NH₄]⁺. This process identified 53 lipid peaks, forming a robust lipid fingerprint for each oil type. An SCNN model was developed using fingerprints, achieving an impressive classification accuracy of 98.5 ± 2.2 %. The integration of DESI-MS with SCNN provides a fast and reliable tool for identifying and classifying vegetable oils, thereby reducing mislabeling fraud and assuring oil quality. By enabling accurate authentication, it contributes to improved transparency and integrity in food labeling and quality control practices.

中文翻译：

---

使用 DESI-MS 结合神经网络对植物油进行化学表征和分类


本研究通过开发一种将解吸电喷雾电离质谱 （DESI-MS） 与浅层卷积神经网络 （SCNN） 相结合的方法，解决了由价格差异和利润动机驱动的植物油错误标签欺诈问题。该方法旨在表征脂质并区分九种植物油：玉米油、大豆油、花生油、芝麻油、米糠油、向日葵油、山茶油、橄榄油和核桃油。优化的 DESI-MS 方法增强了非极性甘油酯的电离，并检测到 [TG + Na]⁺、[TG + NH₄]⁺ 等离子加合物。该过程鉴定了 53 个脂质峰，为每种油类型形成了强大的脂质指纹图谱。使用指纹开发了 SCNN 模型，实现了令人印象深刻的 98.5 ± 2.2% 的分类准确率。DESI-MS 与 SCNN 的集成为植物油的识别和分类提供了一种快速可靠的工具，从而减少了贴错标签的欺诈行为，确保了油品质量。通过实现准确的身份验证，它有助于提高食品标签和质量控制实践的透明度和完整性。