申琦;李盎;张晓芋;桑泽农;王志莹;

• 1:郑州大学化学学院

摘要(Abstract)：

在对变量数远大于样本数的红外/近红外光谱数据进行分析时，经常需要对变量进行筛选或降维，为此提出了基于变量重要度指数的离散粒子群优化算法，并应用于五种食用油的偏最小二乘判别分析。变量的重要度指数为偏最小二乘回归系数和光谱纯度的乘积。在粒子群优化算法的初始化阶段引入变量重要度指数，利用轮盘赌算法增大选中重要度大的变量的概率，并且不减少种群的随机性。77个食用油样本的分类实验结果表明，与全变量偏最小二乘和经典粒子群优化算法相比，基于变量重要度指数的离散粒子群优化算法收敛速度较快，并在一定程度上避免了陷入局部最优，利用FT-IR光谱技术并结合化学计量学建立模型是一种有效的食用油分类分析方法。

关键词(KeyWords)： 红外光谱;离散粒子群优化算法;偏最小二乘判别分析;食用油

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(21575131);; 河南省高等学校大学生创新创业训练计划项目(S202110459020)

作者(Authors): 申琦;李盎;张晓芋;桑泽农;王志莹;

DOI: 10.13705/j.issn.1671-6841.2022075

参考文献(References)：

• [1] 罗筱然，邹志威，吴杰，等.对食用油质量检测的研究[J].计量与测试技术，2017,44(6):32-33.LUO X R,ZOU Z W,WU J,et al.Study on the quality inspection of edible oil[J].Metrology & measurement technique,2017,44(6):32-33.
• [2] 高锦红，马咏梅，胡明.基于电导率变化的食用油掺假识别研究[J].食品工业科技，2019,40(19):226-229.GAO J H,MA Y M,HU M.Identification of adulteration in edible oil based on conductivity change[J].Science and technology of food industry,2019,40(19):226-229.
• [3] LIU W,LIU C H,YU J J,et al.Discrimination of geographical origin of extra virgin olive oils using terahertz spectroscopy combined with chemometrics[J].Food chemistry,2018,251:86-92.
• [4] RIFNA E J,PANDISELVAM R,KOTHAKOTA A,et al.Advanced process analytical tools for identification of adulterants in edible oils:a review[J].Food chemistry,2022,369:130898-130914.
• [5] ZHOU X,ZHANG Q H,CHEN X T,et al.In-situ assessment of olive oil adulteration with soybean oil based on thermogravimetric-gas chromatography/mass spectrometry combined with chemometrics[J].Food control,2021,130:108251-108257.
• [6] MANNU A,PODDIGHE M,GARRONI S,et al.Application of IR and UV-VIS spectroscopies and multivariate analysis for the classification of waste vegetable oils[J].Resources,conservation and recycling,2022,178:106088-106094.
• [7] SIUDEM P,WAWER I,PARADOWSKA K.Rapid evaluation of edible hemp oil quality using NMR and FT-IR spectroscopy[J].Journal of molecular structure,2019,1177:204-208.
• [8] JAMWAL R,AMIT,KUMARI S,et al.Recent trends in the use of FTIR spectroscopy integrated with chemometrics for the detection of edible oil adulteration[J].Vibrational spectroscopy,2021,113:103222.
• [9] TERRA L A,FILGUEIRAS P R,TOSE L V,et al.Laser desorption ionization FT-ICR mass spectrometry and CARSPLS for predicting basic nitrogen and aromatics contents in crude oils[J].Fuel,2015,160:274-281.
• [10] CARRERES-PRIETO D,GARCIA J T,CERDAN-CARTAGENA F,et al.Implementing early warning systems in WWTP:an investigation with cost-effective LED-VIS spectroscopy-based genetic algorithms[J].Chemosphere,2022,293:133610-133621.
• [11] ALEKSEEV G V,TERESHKO D A.Particle swarm optimization-based algorithms for solving inverse problems of designing thermal cloaking and shielding devices[J].International journal of heat and mass transfer,2019,135:1269-1277.
• [12] SARKAR B,SHARMA U,ADHIKARI K,et al.Application of artificial neural network and particle swarm optimization for modelling and optimization of biosorption of lead(Ⅱ) and nickel(Ⅱ) from wastewater using dead cyanobacterial biomass[J].Journal of the Indian chemical society,2021,98(3):100039.
• [13] KENNEDY J,EBERHART R.Particle swarm optimization[C]//Proceedings of International Conference on Neural Networks.Piscataway:IEEE Press,1995:1942-1948.
• [14] QU F F,REN D,WANG J H,et al.An ensemble successive project algorithm for liquor detection using near infrared sensor[J].Sensors,2016,16(1):1-14.
• [15] KOENIG L,CARIOU V,SYMONEAUX R,et al.Additive trees for the categorization of a large number of objects,with bootstrapping strategy for stability assessment:application to the free sorting of wine odor terms[J].Food quality and preference,2021,89:104137.