数字农科院2.0

PLSELM: A lightweight modeling approach for low-data calibration in near-infrared spectroscopy

文献类型： 外文期刊

作者： Xiaqiong Fan;Lijin Shang;Shuo Zhao;Jixing Fan;Senlin Zhang;Qiong Yang;Chengyang Wu;Yulin Liu;Tiejun Yang;Hongchao Ji

作者机构：

关键词： （0-1-4）Extreme learning machine;Multivariate calibration;NIR;Partial least squares

期刊名称： Analytica Chimica Acta

ISSN： 0003-2670

年卷期： 2025 年 1379 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Background: Near infrared (NIR) spectroscopy is widely used as a rapid analytical technique in various fields for its advantages of on-line monitoring and non-destructive testing. It can provide rich chemical information and is of great significance for studying the structure, composition and changes of substances. Reliable calibration remains a major challenge in near-infrared (NIR) spectroscopy, especially under low-data conditions or across instruments with varying configurations. To address this, we propose PLSELM, a lightweight modeling calibration method, which combines Partial Least Squares (PLS) score matrices and Ensemble Extreme Learning Machine (ELM). Results: To address this, we propose PLSELM, a lightweight modeling calibration method, which combines Partial Least Squares (PLS) score matrices and Ensemble Extreme Learning Machine (ELM). By modeling the relationship between latent PLS features and concentration values, PLSELM provides a fast, robust, and transferable calibration framework. To evaluating the performance, five diverse NIR spectral data, including 21 sets of concentration indicators from 10 different spectrometers, were used for benchmarking comparison. These NIR spectra have different wavelength ranges, resolutions, lengths, and a wide range of concentrations. Results demonstrate that PLSELM has excellent calibration performance, outperforming conventional PLS, Support Vector Regression, and deep learning-based models. PLSELM also has great suitability in low-data learning and calibration transfer analysis. In addition, PLSELM model has good robustness, which is manifested in that it is not sensitive to the randomness of sample division and the randomness of hidden layer nodes. PLSELM only took 0.5 s to finished the PLSELM and PLS models on corn data. Significance: The comprehensive comparison results indicate that the PLSELM method is a robust NIR calibration method, which performs well in various spectral wavelength ranges, resolutions, lengths, and a wide range of concentrations. In summary, PLSELM offers a practical and scalable solution for NIR calibration, with excellent potential for use in real-world analytical applications involving limited data or heterogeneous instruments.

分类号：

  • 相关文献

[1]近红外分析技术在中药检测体系中的应用. 张瑞,王英平,许世泉,闫梅霞,赵景辉. 2010

[2]Determination of Quality Parameters of Rapeseeds by Infrared Photoacoustic Spectroscopy. Lu Yu-Zhen,Du Chang-Wen,Zhou Jian-Min,Yu Chang-Bin. 2014

[3]Improvement on enhanced Monte-Carlo outlier detection method. Zhang, Liangxiao,Wang, Du,Li, Peiwu,Zhang, Wen,Mao, Jin,Yu, Li,Ding, Xiaoxia,Zhang, Qi,Zhang, Wen,Li, Peiwu,Zhang, Qi,Zhang, Liangxiao,Li, Peiwu,Mao, Jin,Ding, Xiaoxia,Zhang, Liangxiao,Wang, Du,Li, Peiwu,Zhang, Wen,Yu, Li,Zhang, Liangxiao,Gao, Rongrong.

[4]The Quantified Analysis of Fresh Mutton Tenderness Using PLS Methods and Fourier Transform Near-Infrared Spectroscopy. Zhang De-quan,Li Chun-hong,Li Yong,Li Shu-rong,Li Qing-peng,Zhou Hong-jie,Chen Xiao-na,Zhang Bo-lin,Sun Su-qin. 2008

[5]Quantitative determination of nutrient content in poultry manure by near infrared spectroscopy based on artificial neural networks. Chen, L. J.,Han, L. J.,Xing, L.. 2009

[6]Study on Identification and Traceability of Tea Material Cultivar by Combined Analysis of Multi-Partial Least Squares Models Based on Near Infrared Spectroscopy. Zhou Jian,Cheng Hao,Zeng Jian-ming,Wang Li-yuan,Wei Kang,He Wei,Wang Wei-feng,Liu Xu. 2010

[7]Determination of Melamine in Soybean Meal by Near-Infrared Imaging and Chemometrics. Li, Qingbo,Kang, Xue,Shi, Dongdong,Liu, Qingsheng.

[8]A new approach to LST modeling and normalization under clear-sky conditions based on a local optimization strategy. Majid Kiavarz,Mohammad Karimi Firozjaei,Seyed Kazem Alavipanah,Quazi K. Hassan,Yoann Malbéteau,Si Bo Duan. 2022

[9]Assessment of Peanut Protein Powder Quality by Near-Infrared Spectroscopy and Generalized Regression Neural Network-Based Approach. Haofan Cui,Fengying Gu,Jingjing Qin,Zhenyuan Li,Yu Zhang,Qin Guo,Qiang Wang. 2024

[10]Determination of Dry-Matter Content of Kiwifruit before Harvest Based on Hyperspectral Imaging. Han Yang,Qian Chen,Jianping Qian,Jiali Li,Xintao Lin,Zihan Liu,Nana Fan,Wei Ma. 2024

[11]An efficient method for tracing the geographic origin of Enshi Yulu fresh tea leaves based on near infrared spectroscopy combined with synergy interval PLS and genetic algorithm. Shengpeng Wang,Lin Feng,Panpan Liu,Anhui Gui,Shiwei Gao,Jing Teng,Fei Ye,Zixiang Jiang,Xueping Wang,Jinjin Xue,Pengcheng Zheng,Zhiyu Song. 2024

[12]Rapid determination of oil content of single peanut seed by near-infrared hyperspectral imaging. Shunting Zhang,Xue Li,Du Wang,Li Yu,Fei Ma,Xuefang Wang,Mengxue Fang,Huiying Lyu,Liangxiao Zhang,Zhiyong Gong,Peiwu Li. 2024

[13]Classification of Orange Growing Locations Based on the Near-infrared Spectroscopy Using Data Mining. Dan, Songjian,Tian, Fengchun,Yang, Simon X.,Dan, Songjian,Den, Lie. 2016

[14]Quality analysis of Chinese bacon with near infrared spectroscopy. Zhao Li-li,Zhang Lu-da,Song Zhong-xiang,Li Yong,Yan Yan-lu,Ma Chang-wei. 2007

[15]Study on quality detection of milk powder based on near infrared spectroscopy (NIR). Wu Jing-zhu,Wang Yi-ming,Zhang Xiao-chao,Xu Yun. 2007

[16]Nondestructive detection of moldy chestnut based on near infrared spectroscopy. Liu, J.,Li, X. Y.,Wang, W.,Zhang, J.,Zhang, R.,Liu, P.,Li, P. W.,Zhang, J.. 2010

[17]Nondestructive detection of moldy chestnut based on near infrared spectroscopy. Liu, J.,Li, X. Y.,Wang, W.,Zhang, J.,Zhang, R.,Liu, P.,Li, P. W.,Zhang, J.. 2010

[18]Effects of grown origin, genotype, harvest year, and their interactions of wheat kernels on near infrared spectral fingerprints for geographical traceability. Zhao, Haiyan,Guo, Boli,Wei, Yimin,Zhang, Bo,Zhao, Haiyan.

[19]Near infrared reflectance spectroscopy for determination of the geographical origin of wheat. Zhao, Haiyan,Guo, Boli,Wei, Yimin,Zhang, Bo.

[20]Tumor-Penetrating and Mitochondria-Targeted Drug Delivery Overcomes Doxorubicin Resistance in Lung Cancer. Zhou, Meng-Xue,Zhang, Jia-Yu,Cai, Xiao-Meng,Dou, Rui,Ruan, Li-Fo,Yang, Wen-Jiang,Lin, Wen-Chu,Chen, Jun,Hu, Yi. 2022

作者其他论文 更多>>