利用低场核磁共振技术,探究了驼奶粉中掺假不同量的牛奶粉、蛋白粉和淀粉的影响。获得的T2横向弛豫时间反演谱显示了纯驼奶粉和掺假驼奶粉之间存在差异,可用于进一步分析。为了区分不同类型的掺假驼奶粉,研究采用了多种机器学习算法进行分类。结果显示,随机森林模型的表现最为优异,其准确率和F1评分分别达到了96.35%和97.53%。此外,还利用主成分分析对掺有不同浓度牛奶粉、蛋白粉和淀粉的驼奶粉样品进行了分类。结果显示,相同掺假量的驼奶粉出现聚类趋势,不同掺假量的驼奶粉之间出现明显分离。在定量分析中,构建了偏最小二乘回归模型预测掺假量,结果显示3种掺假物的预测性能良好。模型的预测能力通过独立样本集验证,表明其具有较高的泛化性。此外,方法的精密度通过重复性实验评估,日内精密度为3.0%~6.8%,日间精密度为6.1%~10.3%,证实了方法的稳定性和可靠性。
To investigate the effects of adulterating camel milk powder with different concentrations of cow milk powder, protein powder, and starch, low-field nuclear magnetic resonance technology was employed.The T2 transverse relaxation time spectra revealed distinct differences between pure camel milk powder and adulterated samples, providing valuable data for further analysis.Various machine learning algorithms, including support vector machine, k-nearest neighbors, random forest, multilayer perceptron, and extreme gradient boosting, were applied to classify camel milk powder with different types of adulteration.The RF classification model performed most effectively, achieving accuracy and F1 score of 96.35% and 97.53%, respectively.Principal component analysis (PCA) was also utilized to differentiate camel milk samples adulterated with varying concentrations of cow milk powder, protein powder, and starch.PCA results showed clustering trends among samples with the same concentration and clear separation between samples with different concentrations.In quantitative analysis, a partial least squares regression model was constructed to predict adulteration concentrations, with results indicating good predictive performance for three types of adulterants.The model’s predictive capability was validated using an independent sample set, demonstrating its high generalizability.Furthermore, the precision of the method was evaluated through repeatability experiments, with intra-day precision ranging from 3.0% to 6.8% and inter-day precision ranging from 6.1% to 10.3%, thus confirming the method’s stability and reliability.
[1] WU X Y, NA Q, HAO S Q, et al.Detection of ovine or bovine milk components in commercial camel milk powder using a PCR-based method[J].Molecules, 2022, 27(9):3017.
[2] QYResearch.2024年全球骆驼乳制品行业总体规模、主要企业国内外市场占有率及排名[EB/OL].(2023-12-22) [2024-11-07].https://cn.qyresearch.com/reports/3087211/camel-dairy.
QYResearch.Camel dairy report 2024, global revenue, key companies market shatr & rank [EB/OL].(2023-12-22) [2024-11-07].https://cn.qyresearch.com/reports/3087211/camel-dairy.
[3] LI L Y, WANG J, LI M J, et al.Detection of the adulteration of camel milk powder with cow milk by ultra-high performance liquid chromatography (UPLC)[J].International Dairy Journal, 2021, 121:105117.
[4] MORSI R, GHOUDI K, AYYASH M M, et al.Detection of 11 carbamate pesticide residues in raw and pasteurized camel milk samples using liquid chromatography tandem mass spectrometry:Method development, method validation, and health risk assessment[J].Journal of Dairy Science, 2024, 107(4):1916-1927.
[5] CHI S X, LIU B H, ZHANG B, et al.Development of an ELISA method to determine adulterated cow milk in camel milk[J].International Dairy Journal, 2024, 155:105953.
[6] 李玲玉, 王俊, 李敏婧, 等.基于乳清蛋白的骆驼乳中掺假牛乳的检测及热处理对方法的影响[J].食品科学, 2022, 43(10):329-335.
LI L Y, WANG J, LI M J, et al.A method for detection of cow milk in adulterated camel milk based on whey protein and effect of heat treatment on it[J].Food Science, 2022, 43(10):329-335.
[7] SANTOS P M, PEREIRA-FILHO E R, COLNAGO L A.Detection and quantification of milk adulteration using time domain nuclear magnetic resonance (TD-NMR)[J].Microchemical Journal, 2016, 124:15-19.
[8] HU B K, ZHANG D Y, GENG Y Y, et al.Chemometrics analysis of Camellia oil authenticity using LF NMR and fatty acid GC fingerprints[J].Journal of Food Composition and Analysis, 2024, 133:106447.
[9] XING M J, LIU F J, LIN J Z, et al.Origin tracing and adulteration identification of bird’s nest by high- and low-field NMR combined with pattern recognition[J].Food Research International, 2024, 175:113780.
[10] WU M F, LI M M, FAN B, et al.A rapid and low-cost method for detection of nine kinds of vegetable oil adulteration based on 3-D fluorescence spectroscopy[J].LWT, 2023, 188:115419.
[11] YOKOYAMA D, SUZUKI S, ASAKURA T, et al.Chemometric analysis of NMR spectra and machine learning to investigate membrane fouling[J].ACS Omega, 2022, 7(15):12654-12660.
[12] MENÉNDEZ-GARCÍA L A, GARCÍA-NIETO P J, GARCÍA-GONZALO E, et al.Time series analysis for COMEX platinum spot price forecasting using SVM, MARS, MLP, VARMA and ARIMA models:A case study[J].Resources Policy, 2024, 95:105148.
[13] NAKHAEI-KOHANI R, AMIRI-RAMSHEH B, POURMAHDI M, et al.Extensive data analysis and modelling of carbon dioxide solubility in ionic liquids using chemical structure-based ensemble learning approaches[J].Fluid Phase Equilibria, 2024, 585:114166.
[14] FU X X, MA W T, ZUO Q, et al.Application of machine learning for high-throughput tumor marker screening[J].Life Sciences, 2024, 348:122634.
[15] CUI C J, XIA M Y, CHEN J L, et al.1H NMR-based metabolomics combined with chemometrics to detect edible oil adulteration in Huajiao (Zanthoxylum bungeanum Maxim.)[J].Food Chemistry, 2023, 423:136305.
[16] LI Z M, SONG J H, MA Y X, et al.Identification of aged-rice adulteration based on near-infrared spectroscopy combined with partial least squares regression and characteristic wavelength variables[J].Food Chemistry:X, 2023, 17:100539.
[17] PANDISELVAM R, MAHANTI N K, MANIKANTAN M R, et al.Rapid detection of adulteration in desiccated coconut powder:Vis-NIR spectroscopy and chemometric approach[J].Food Control, 2022, 133:108588.
[18] PENG D, ZHOU Q, SU M, et al.Quantitative determination of the carbonyl value in frying oils based on LF-NMR combined with chemometrics[J].LWT, 2024, 198:116067.
[19] MUNIZ R O, GONZALEZ J L, TOCI A T, et al.Using 1H low-field NMR relaxometry to detect the amounts of Robusta and Arabica varieties in coffee blends[J].Food Research International, 2023, 174:113610.
[20] LI Y T, OBADI M, SHI J C, et al.Determination of moisture, total lipid, and bound lipid contents in oats using low-field nuclear magnetic resonance[J].Journal of Food Composition and Analysis, 2020, 87:103401.
[21] QIU Z J, BIAN Y L, WANG F Y, et al.A novel method for detection of internal quality of walnut kernels using low-field magnetic resonance imaging[J].Computers and Electronics in Agriculture, 2024, 217:108546.
