Comparison of variable optimization algorithms for PLS regression models of kerosene content in edible oils

IF 4.3 2区化学 Q1 SPECTROSCOPY

Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy Pub Date : 2025-03-13 DOI:10.1016/j.saa.2025.126045

Wangfei Luo , Jihong Deng , Hui Jiang , Quansheng Chen

{"title":"Comparison of variable optimization algorithms for PLS regression models of kerosene content in edible oils","authors":"Wangfei Luo , Jihong Deng , Hui Jiang , Quansheng Chen","doi":"10.1016/j.saa.2025.126045","DOIUrl":null,"url":null,"abstract":"<div><div>Edible oils may become contaminated with harmful substance residues during transportation, posing a serious threat to food safety and public health. This study utilized Fourier Transform Near-Infrared (FT-NIR) Spectroscopy to extract spectral data for kerosene content in soybean and corn oil. Three feature selection models, Competitive Adaptive Reweighted Sampling (CARS), Bootstrapping Soft Shrinkage (BOSS), and Iteratively Variable Subset Optimization (IVSO), were applied to Savitzky-Golay (SG) preprocessed data. Using the selected features, Partial Least Squares (PLS) regression models were developed. The CARS-optimized PLS model demonstrated superior generalization performance, achieving an RMSEP of 2.4520 <span><math><mrow><mi>m</mi><mi>g</mi><mo>·</mo><msup><mrow><mi>k</mi><mi>g</mi></mrow><mrow><mo>-</mo><mn>1</mn></mrow></msup></mrow></math></span>, a Predictive correlation coefficient (<span><math><msub><mi>R</mi><mi>P</mi></msub></math></span>) of 0.9711, and a relative prediction deviation (RPD) of 4.2562. These results indicate the feasibility of constructing a quantitative model for detecting kerosene content in soybean and corn oil using FT-NIR Spectroscopy with feature selection algorithms.</div></div>","PeriodicalId":433,"journal":{"name":"Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy","volume":"336 ","pages":"Article 126045"},"PeriodicalIF":4.3000,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy","FirstCategoryId":"92","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1386142525003518","RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"SPECTROSCOPY","Score":null,"Total":0}

引用次数: 0

Abstract

Edible oils may become contaminated with harmful substance residues during transportation, posing a serious threat to food safety and public health. This study utilized Fourier Transform Near-Infrared (FT-NIR) Spectroscopy to extract spectral data for kerosene content in soybean and corn oil. Three feature selection models, Competitive Adaptive Reweighted Sampling (CARS), Bootstrapping Soft Shrinkage (BOSS), and Iteratively Variable Subset Optimization (IVSO), were applied to Savitzky-Golay (SG) preprocessed data. Using the selected features, Partial Least Squares (PLS) regression models were developed. The CARS-optimized PLS model demonstrated superior generalization performance, achieving an RMSEP of 2.4520

m g \cdot {k g}^{- 1}

, a Predictive correlation coefficient (

R_{P}

) of 0.9711, and a relative prediction deviation (RPD) of 4.2562. These results indicate the feasibility of constructing a quantitative model for detecting kerosene content in soybean and corn oil using FT-NIR Spectroscopy with feature selection algorithms.

Abstract Image

查看原文本刊更多论文

食用油中煤油含量PLS回归模型的变量优化算法比较

食用油在运输过程中可能被有害物质残留污染，对食品安全和公众健康构成严重威胁。本研究利用傅里叶变换近红外（FT-NIR）光谱法提取大豆油和玉米油中煤油含量的光谱数据。将竞争自适应重加权采样（CARS）、Bootstrapping Soft Shrinkage （BOSS）和迭代变量子集优化（IVSO）三种特征选择模型应用于Savitzky-Golay （SG）预处理数据。利用选取的特征，建立偏最小二乘（PLS）回归模型。优化后的PLS模型具有较好的泛化性能，RMSEP为2.4520 mg·kg-1，预测相关系数（RP）为0.9711，相对预测偏差（RPD）为4.2562。这些结果表明，利用FT-NIR光谱特征选择算法建立定量模型检测大豆油和玉米油中煤油含量是可行的。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy 物理-光谱学

CiteScore

8.40

自引率

11.40%

发文量

1364

审稿时长

40 days

期刊介绍： Spectrochimica Acta, Part A: Molecular and Biomolecular Spectroscopy (SAA) is an interdisciplinary journal which spans from basic to applied aspects of optical spectroscopy in chemistry, medicine, biology, and materials science. The journal publishes original scientific papers that feature high-quality spectroscopic data and analysis. From the broad range of optical spectroscopies, the emphasis is on electronic, vibrational or rotational spectra of molecules, rather than on spectroscopy based on magnetic moments. Criteria for publication in SAA are novelty, uniqueness, and outstanding quality. Routine applications of spectroscopic techniques and computational methods are not appropriate. Topics of particular interest of Spectrochimica Acta Part A include, but are not limited to: Spectroscopy and dynamics of bioanalytical, biomedical, environmental, and atmospheric sciences, Novel experimental techniques or instrumentation for molecular spectroscopy, Novel theoretical and computational methods, Novel applications in photochemistry and photobiology, Novel interpretational approaches as well as advances in data analysis based on electronic or vibrational spectroscopy.