Identification of Water Adulteration in Non-bovine Milks Using Near-Infrared Spectroscopy Combined with a Convolutional Neural Network Model

doi:10.7506/rykxyjs1671-5187-20260205-011

Journal of Dairy Science and Technology ›› 2026, Vol. 49 ›› Issue (3): 41-47.DOI: 10.7506/rykxyjs1671-5187-20260205-011

• Analysis & Detection • Previous Articles

Identification of Water Adulteration in Non-bovine Milks Using Near-Infrared Spectroscopy Combined with a Convolutional Neural Network Model

SHAO Zixiang, Torkun·MAMET*

To address the increasingly severe issue of water adulteration in the non-bovine milks market, this study proposed a rapid, non-destructive method for identifying multiple types of adulterated non-bovine milks based on portable near-infrared spectroscopy combined with convolutional neural networks (CNN). Spectral data were collected for four types of non-bovine milks, camel, horse, donkey, and yak milks, as well as samples of these milks diluted with water at varying concentrations (2%–80%, V/V). We compared the effects of standard normal variate transformation (SNV) and Savitzky-Golay filter smoothing preprocessing on the performance of partial least squares discriminant analysis (PLS-DA) and CNN models. The results showed that non-bovine milks exhibited significant characteristic absorption of moisture at 6 882 and 10 200 cm?1. The CNN model with SNV preprocessing achieved the best performance, with a classification accuracy of 98.71% on the test set, and its precision and recall were superior to those of traditional PLS-DA model. This model not only accurately distinguished between milks from different species but also exhibited high sensitivity in detecting water adulteration as low as 2%. The present study demonstrates that the discrimination system based on a portable near-infrared spectrometer and CNN can effectively reduce matrix interference in minor species milks.

Published:2026-07-06

卷积神经网络模型结合近红外光谱对特种乳掺水的鉴别

邵子祥, 托尔坤・买买提

新疆大学智慧农业学院(研究院),新疆乌鲁木齐 830017

基金资助:
新疆战略人才培养计划一流科技领军人才项目（XJRC-2025-KJ-PY-KJLJ-126）

Abstract

Abstract: near-infrared spectroscopy; non-bovine milks; water adulteration identification; convolutional neural network

摘要： 针对特种乳市场日益严重的掺水欺诈问题，本研究提出一种基于便携式近红外光谱结合卷积神经网络的多种类特种乳掺假快速、无损鉴别方法。采集驼乳、马乳、驴乳及牦牛乳4种典型特种乳及其2%~80%梯度掺水样本的光谱数据，对比标准正态变量变换、Savitzky-Golay滤波平滑两种预处理方式，探究其对偏最小二乘判别分析与卷积神经网络模型鉴别性能的影响。结果表明，特种乳在6882 cm?1及10200 cm?1波段存在显著水分特征吸收峰；经标准正态变量变换预处理的卷积神经网络模型性能最优，测试集分类准确率可达98.71%，精确率与召回率均优于传统偏最小二乘判别分析模型，能够精准区分不同乳种来源，对低至2%的微量掺水比例也具备良好识别能力。该研究构建的便携式近红外光谱与深度学习结合的鉴别体系，可有效消除不同特种乳间的基质干扰，为特种乳掺水无损快速筛查、保障特种乳市场质量安全提供了高效可靠的技术方案。

关键词: 近红外光谱；特种乳；掺水鉴别；卷积神经网络

CLC Number:

TS252.2

College of Smart Agriculture (Research Institute), Xinjiang University, Ürümqi 830017, China. Identification of Water Adulteration in Non-bovine Milks Using Near-Infrared Spectroscopy Combined with a Convolutional Neural Network Model[J]. Journal of Dairy Science and Technology, 2026, 49(3): 41-47 https://doi.org/10.7506/rykxyjs1671-5187-20260205-011

邵子祥, 托尔坤・买买提. 卷积神经网络模型结合近红外光谱对特种乳掺水的鉴别[J]. 乳业科学与技术, 2026, 49(3): 41-47 https://doi.org/10.7506/rykxyjs1671-5187-20260205-011

[1]	LIU Yuru, LI Xinyi, CHEN Xiaomin, ZHANG Shuli, ZHANG Dexi. Correlation between Feed Types and the Beany Odor of Raw Milk [J]. Journal of Dairy Science and Technology, 2025, 48(2): 20-29.
[2]	JIA Hongxin, SU Miya, CHEN Wenliang, QU Yezhi. Research Progress on Vitamin C Health Effects on Infants and Vitamin C in Human Milk [J]. Journal of Dairy Science and Technology, 2025, 48(1): 41-45.
[3]	SHEN Yufei, ZHANG Yan, TONG Fenfen, WANG Shuangshuang, HU Qisheng, XU Liqing, SONG Yuxuan, GE Wupeng. Correlation between Physicochemical Indexes and Acidity of Sheep Milk in Different Lactation Periods [J]. Journal of Dairy Science and Technology, 2024, 47(6): 8-14.
[4]	WU Lanjun, YANG Mei, WANG Manxia, MI Shuhui, WU Yongfeng, WU Junrui, WU Rina, LIU Biao, YUE Xiqing. Comparative Analysis of Composition and Functionality of Milk Fat Globule Membrane Proteins in Bovine Colostrum and Milk [J]. Journal of Dairy Science and Technology, 2016, 39(5): 7-12.
[5]	WANG Qinbo, YANG Yan, QI Xiaoyan. Antimicrobial Activities of Ethanol Extracts from Phellinus baumii.towards Harmful Microorganisms in Dairy Products [J]. Journal of Dairy Science and Technology, 2016, 39(1): 1-4.
[6]	YU Xiaoping, LI Na, WANG Dawei. Optimization of the Formulation for a Milk Beverage Supplemented with Lentinus edodes-Derived Peptide [J]. Journal of Dairy Science and Technology, 2015, 38(5): 16-20.
[7]	ZHANG Wei, SONG Chun-chun, XU Yu-juan, YU Lei. Formulation and Emulsion Stability of a Composite Rice Bran Protein-Dairy Beverage [J]. Journal of Dairy Science and Technology, 2013, 36(4): 7-10.
[8]	LI Liang-yu, CAO Rong-an, YU Wei, JIA Peng-yu. Formulation of a Wheat Germ-Based Dairy Beverage [J]. Journal of Dairy Science and Technology, 2013, 36(4): 11-13.
[9]	ZHAO Jinde, ZHANG Shuli, HE Kairu, CHEN Xiaomin, LIU Yuru, ZHANG Yanliang, WU Rina, ZHANG Dexi, WU Junrui. Research Progress on the Hazards and Control of Bacillus subtilis in Sterilized Milk [J]. Journal of Dairy Science and Technology, 2024, 47(4): 59-65.

Identification of Water Adulteration in Non-bovine Milks Using Near-Infrared Spectroscopy Combined with a Convolutional Neural Network Model

卷积神经网络模型结合近红外光谱对特种乳掺水的鉴别

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 9

Recommended Articles

Metrics