Rapid identification of fish species by laser-induced breakdown spectroscopy and Raman spectroscopy coupled with machine learning methods

被引:52
作者
Ren, Lihui [1 ,3 ]
Tian, Ye [1 ]
Yang, Xiaoying [1 ]
Wang, Qi [1 ,3 ]
Wang, Leshan [1 ]
Geng, Xin [1 ]
Wang, Kaiqiang [2 ]
Du, Zengfeng [4 ]
Li, Ying [1 ]
Lin, Hong [2 ]
机构
[1] Ocean Univ China, Coll Phys & Optoelect Engn, Qingdao 266100, Peoples R China
[2] Ocean Univ China, Food Safety Lab, Qingdao 266003, Peoples R China
[3] Chinese Acad Sci, Qingdao Inst BioEnergy & Bioproc Technol, Single Cell Ctr, Qingdao 266101, Peoples R China
[4] Chinese Acad Sci, Key Lab Marine Geol & Environm, Qingdao 266071, Peoples R China
关键词
Fish species identification; laser -induced breakdown spectroscopy (LIBS); Raman spectroscopy; Machine learning; convolutional neural network (CNN); Data fusion; QUALITY ASSESSMENT; BOVINE MEAT; DATA FUSION; FOOD; CLASSIFICATION; QUANTIFICATION; ADULTERATION; CALCIUM; SAMPLES; FRAUDS;
D O I
10.1016/j.foodchem.2022.134043
中图分类号
O69 [应用化学];
学科分类号
081704 ;
摘要
There has been an increasing demand for the rapid verification of fish authenticity and the detection of adul-teration. In this work, we combined LIBS and Raman spectroscopy for the fish species identification for the first time. Two machine learning methods of SVM and CNN are used to establish the classification models based on the LIBS and Raman data obtained from 13 types of fish species. Data fusion strategies including low-level, mid-level and high-level fusions are used for the combination of LIBS and Raman data. It shows that all these data fusion strategies offer a significant improvement in fish classification compared with the individual LIBS or Raman data, and the CNN model works more powerfully than the SVM model. The low-level fusion CNN model provides a best classification accuracy of 98.2%, while the mid-level fusion involved with feature selection improves the computing efficiency and gains the interpretability of CNN.
引用
收藏
页数:9
相关论文
共 50 条
  • [31] Detection of fluorine using laser-induced breakdown spectroscopy and Raman spectroscopy
    Porizka, Pavel
    Kaski, Saara
    Hrdlicka, Ales
    Modlitbova, Pavlina
    Sladkova, Lucia
    Hakkanen, Heikki
    Prochazka, David
    Novotny, Jan
    Gadas, Petr
    Celko, Ladislav
    Novotny, Karel
    Kaiser, Jozef
    [J]. JOURNAL OF ANALYTICAL ATOMIC SPECTROMETRY, 2017, 32 (10) : 1966 - 1974
  • [32] Identification of the animal origin of milk via Laser-Induced Breakdown Spectroscopy
    Nanou, Eleni
    Pliatsika, Nefeli
    Stefas, Dimitrios
    Couris, Stelios
    [J]. FOOD CONTROL, 2023, 154
  • [33] Rapid origin identification of chrysanthemum morifolium using laser-induced breakdown spectroscopy and chemometrics
    Hao, Nan
    Gao, Xin
    Zhao, Qian
    Miao, Peiqi
    Cheng, Jiawei
    Li, Zheng
    Liu, Changqing
    Li, Wenlong
    [J]. POSTHARVEST BIOLOGY AND TECHNOLOGY, 2023, 197
  • [34] Recognition of explosives fingerprints on objects for courier services using machine learning methods and laser-induced breakdown spectroscopy
    Moros, J.
    Serrano, J.
    Gallego, F. J.
    Macias, J.
    Laserna, J. J.
    [J]. TALANTA, 2013, 110 : 108 - 117
  • [35] A study of machine learning regression methods for major elemental analysis of rocks using laser-induced breakdown spectroscopy
    Boucher, Thomas F.
    Ozanne, Marie V.
    Carmosino, Marco L.
    Dyar, M. Darby
    Mahadevan, Sridhar
    Breves, Elly A.
    Lepore, Kate H.
    Clegg, Samuel M.
    [J]. SPECTROCHIMICA ACTA PART B-ATOMIC SPECTROSCOPY, 2015, 107 : 1 - 10
  • [36] Classification of human tooth using laser-induced breakdown spectroscopy combined with machine learning
    Tarai, Akash Kumar
    Junjuri, Rajendhar
    Dhobley, Akshay
    Gundawar, Manoj Kumar
    [J]. JOURNAL OF OPTICS-INDIA, 2024, 53 (04): : 3810 - 3820
  • [37] Rapid classification of archaeological ceramics via laser-induced breakdown spectroscopy coupled with random forest
    Qi, Juan
    Zhang, Tianlong
    Tang, Hongsheng
    Li, Hua
    [J]. SPECTROCHIMICA ACTA PART B-ATOMIC SPECTROSCOPY, 2018, 149 : 288 - 293
  • [38] Identification of type of cement through laser-induced breakdown spectroscopy
    Voelker, Tobias
    Millar, Steven
    Strangfeld, Christoph
    Wilsch, Gerd
    [J]. CONSTRUCTION AND BUILDING MATERIALS, 2020, 258 (258)
  • [39] Detection of organic carbon in shale by laser induced breakdown spectroscopy and Raman spectroscopy combined with partial least squares methods
    Wu, Di
    Wu, Jian
    Shi, Mingxin
    Wang, Ning
    Chen, Yiguo
    Guo, Xinyu
    Zhou, Ying
    Li, Xingwen
    Qiu, Aici
    [J]. ANALYTICA CHIMICA ACTA, 2025, 1333
  • [40] RAPID IDENTIFICATION OF VARIETIES OF WALNUT POWDER BASED ON LASER-INDUCED BREAKDOWN SPECTROSCOPY
    Peng, J.
    Liu, F.
    Kong, W.
    Zhang, C.
    Yu, K.
    He, Y.
    [J]. TRANSACTIONS OF THE ASABE, 2017, 60 (01) : 19 - 28