Rapid classification of rice according to storage duration via near-infrared spectroscopy and machine learning

被引:2
|
作者
Zhai, Chen [1 ]
Wang, Wenxiu [3 ]
Zhang, Shengjie [3 ]
Qian, Chengjing [2 ]
Gao, Man [4 ]
Feng, Xiaohui [1 ]
机构
[1] Chinese Acad Agr Sci, State Key Lab Anim Nutr, Inst Anim Sci, Beijing 100193, Peoples R China
[2] COFCO Corp, Nutr & Hlth Res Inst, Beijing Key Lab Nutr & Hlth & Food Safety, Beijing 102209, Peoples R China
[3] Hebei Agr Univ, Coll Food Sci & Technol, Baoding 071000, Peoples R China
[4] Beijing Univ Technol, Dept Environm & Life, Beijing 100124, Peoples R China
来源
TALANTA OPEN | 2024年 / 10卷
关键词
Near-infrared spectroscopy; Machine learning algorithms; Rice; Storage duration; IDENTIFICATION;
D O I
10.1016/j.talo.2024.100343
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Rice is the most important staple crop for more than half of the world's population. As rice quality can deteriorate during storage, methods that can effectively classify rice according to its storage duration are essential. However, existing methods of assessing rice storage time are time-consuming, laborious, and incompatible with modern industrial processing technologies. Therefore, we investigated the ability of near-infrared spectroscopy combined with machine learning algorithms to distinguish rice storage duration. A total of 482 rice samples were analyzed, which included 74, 100, and 308 samples produced during 2015-2016, 2017-2018, and 2020-2021, respectively. Five pre-processing methods were initially applied to the spectra to enhance the accuracy of the discrimination model. Subsequently, two-dimensional correlation spectroscopy and competitive adaptive reweighted sampling (CARS) were used to extract the characteristic spectra associated with storage time. Finally, three pattern recognition methods (K-nearest neighbor analysis, linear discriminant analysis, and least squares support vector machine (LS-SVM)) were compared for their effectiveness in constructing classification models. The results indicated that the best model for identifying the storage duration of rice was established after spectral pre-processing with the standard normal variate and first derivative, using the CARS algorithm to select feature wavelengths, and applying the LS-SVM modeling method, which together yielded correct identification rates of 99.72 % and 91.67 % for the calibration and validation sets, respectively. Thus, we propose near-infrared spectroscopy coupled with machine learning algorithms as an effective approach for classifying rice according to storage duration, which can facilitate evaluations of rice freshness in the market.
引用
收藏
页数:7
相关论文
共 50 条
  • [31] Machine learning-assisted near-infrared spectroscopy for rapid discrimination of apricot kernels in ground almond
    Menevseoglu, A.
    Entrenas, J. A.
    Gunes, N.
    Dogan, M. A.
    Perez-Marin, D.
    FOOD CONTROL, 2024, 159
  • [32] Rapid Detection of Fertilizer Information Based on Near-Infrared Spectroscopy and Machine Learning and the Design of a Detection Device
    Ma, Yongzheng
    Wu, Zhuoyuan
    Cheng, Yingying
    Chen, Shihong
    Li, Jianian
    AGRICULTURE-BASEL, 2024, 14 (07):
  • [33] Rapid and non-invasive detection of malaria parasites using near-infrared spectroscopy and machine learning
    Sikulu-Lord, Maggy T.
    Edstein, Michael D.
    Goh, Brendon
    Lord, Anton R.
    Travis, Jye A.
    Dowell, Floyd E.
    Birrell, Geoffrey W.
    Chavchich, Marina
    PLOS ONE, 2024, 19 (03): : 1 - 18
  • [34] Visual/Near-Infrared Spectroscopy Combined with Linear Discriminant Analysis and Machine Learning for Classification of Apple Damage
    Zhang, Yu
    Zhang, Chongyang
    Duan, Xinxin
    Ma, Shaoge
    Zhao, Fu
    Wang, Juxia
    Shipin Kexue/Food Science, 2024, 45 (22): : 255 - 261
  • [35] Machine Learning Applied to Near-Infrared Spectra for Chicken Meat Classification
    Barbon Jr, Sylvio
    Ayub da Costa Barbon, Ana Paula
    Mantovani, Rafael Gomes
    Barbin, Douglas Fernandes
    JOURNAL OF SPECTROSCOPY, 2018, 2018
  • [36] Near-Infrared Spectroscopy with Machine Learning for Classifying and Quantifying Nutmeg Adulteration
    Sitorus, Agustami
    Pambudi, Suluh
    Boodnon, Wutthiphong
    Lapcharoensuk, Ravipat
    ANALYTICAL LETTERS, 2024, 57 (02) : 285 - 306
  • [37] Near-Infrared Spectroscopy with Supervised Machine Learning as a Screening Tool for Neutropenia
    Raposo-Neto, Jose Joaquim
    Kowalski-Neto, Eduardo
    Luiz, Wilson Barros
    Fonseca, Estherlita Almeida
    Cedro, Anna Karla Costa Logrado
    Singh, Maneesh N.
    Martin, Francis L.
    Vassallo, Paula Frizera
    Campos, Luciene Cristina Gastalho
    Barauna, Valerio Garrone
    JOURNAL OF PERSONALIZED MEDICINE, 2024, 14 (01):
  • [38] Near-Infrared Spectroscopy and Machine Learning for Accurate Dating of Historical Books
    Coppola, Floriana
    Frigau, Luca
    Markelj, Jernej
    Malesic, Jasna
    Conversano, Claudio
    Strlic, Matija
    JOURNAL OF THE AMERICAN CHEMICAL SOCIETY, 2023, 145 (22) : 12305 - 12314
  • [39] Rapid detection of colored and colorless macro-and micro-plastics in complex environment via near-infrared spectroscopy and machine learning
    Zou, Hui-Huang
    He, Pin-Jing
    Peng, Wei
    Lan, Dong-Ying
    Xian, Hao-Yang
    Lu, Fan
    Zhang, Hua
    JOURNAL OF ENVIRONMENTAL SCIENCES, 2025, 147 : 512 - 522
  • [40] Near-Infrared Spectroscopy for Neonatal Sleep Classification
    Hakimi, Naser
    Arasteh, Emad
    Zahn, Maren
    Horschig, Jorn M.
    Colier, Willy N. J. M.
    Dudink, Jeroen
    Alderliesten, Thomas
    SENSORS, 2024, 24 (21)