|
|
|
|
|
|
Prediction and Distribution Visualization of Salmon Quality Based on Hyperspectral Imaging Technology |
SUN Zong-bao, LI Jun-kui, LIANG Li-ming, ZOU Xiao-bo*, LIU Xiao-yu, NIU Zeng, GAO Yun-long |
School of Food and Biological Engineering, Jiangsu University,Zhenjiang 212013, China |
|
|
Abstract In this study, color, shear force and K value was used to evaluate the quality of salmon with different freeze-thaw times, and then predicted by hyperspectral imaging technology combined with chemometric methods. Besides, the prediction performance of the PLS model developed with characteristic variables was compared and discussed to select the optimal variable selection method for color, shear force and K value. The prepared salmon samples with different freeze-thaw times were scanned and analyzed to obtain hyperspectral data and the true values of quality indicators (color, shear force, K value). Afterwards, six different pretreatment methods were used to reduce dark current and noise interference in the spectral data. The competitive adaptive reweighting algorithm (CARS), interval variable iterative space shrinkage approach (iVISSA), and iVISSA-CARS algorithms were applied to screen out variables related to the indicators to improve the prediction performance of the model. The optimal variable selection method was determined according to the prediction performance of the PLS model built by the characteristic variables screened by the three-wavelength selection algorithms. The result exhibited that the 1st Der-CARS-PLS model developed by 51 characteristic variables related to a* possessed the best prediction with Rc of 0.931 6, Rp of 0.929 7, RMSECV and RMSEP of 0.72 and 0.74, respectively. Similarly, in shear force prediction, 2nd Der proved to be the best pretreatment method and 2nd Der -CARS -PLS model developed by 61 characteristic variables displayed the best prediction with Rc of 0.885 3, Rp of 0.860 9, RMSECV and RMSEP of 0.69 N and 0.90 N respectively. Besides, the N-CARS-PLS model built by 51 characteristic variables achieved the best predictive effect on K value and obtained Rc of 0.951 3, Rp of 0.946 0, RMSECV and RMSEP of 1.33 and 1.53, respectively. It indicates that CARS can effectively extract variables related to feature indicators and improve the prediction performance of the PLS model. Besides, the combined algorithm iVISSA-CARS-PLS also achieved a significant results in the prediction of the three indicators. The Rp of the test set was 97.48%, 97.02% and 98.98% of the CARS-PLS prediction model. In comparison, the number of variables used was only 60.78%, 62.29% and 60.78% of CARS-PLS, indicating that the variable selection combined algorithm greatly reduces the amount of data. The CARS-PLS and iVISSA-CARS-PLS models of the three indicators show higher prediction performance than iVISSA, which indicates that the feature variable selection strategy of CARS is more advantages than iVISSA in predicting of the above three quality indicators of salmon. Using the optimized PLS model, the visual distribution map of salmon quality indexes with different freezing and thawing time was constructed in the form of a pseudo color images, which provided more detailed and intuitive information for understanding the quality of salmon. In general, the combination of hyperspectral imaging combined with chemometrics, can accurately and non-destructively determine the quality indicators in salmon. This study can provide the same theoretical reference for the simultaneous rapid detection of multiple quality indicators of salmon.
|
Received: 2020-11-16
Accepted: 2021-03-02
|
|
Corresponding Authors:
ZOU Xiao-bo
E-mail: zou_xiaobo@ujs.edu.cn
|
|
[1] Jääskeläinen E, Jakobsen L M A, Hultman J, et al. International Journal of Food Microbiology, 2019, 293: 44.
[2] Mousakhani-Ganjeh A, Hamdami N, Soltanizadeh N. Innovative Food Science & Emerging Technologies, 2016, 36: 42.
[3] Kono S, Kon M, Araki T, et al. Journal of Food Engineering, 2017, 214: 158.
[4] Mørkøre T, Rødbotten M, Vogt G, et al. Food Chemistry, 2010, 119(4): 1417.
[5] Li Q, Zhang L, Lu H, et al. LWT—Food Science and Technology, 2017, 78: 317.
[6] Sun Z B, Liang L M, Li J K, et al. Food Science & Nutrition, 2020, 8(2): 862.
[7] Ali S, Zhang W, Rajput N, et al. Food Chemistry, 2015, 173: 808.
[8] Jiang H, Jiang X, Ru Y, et al. Infrared Physics & Technology, 2020, 110: 103467.
[9] Anderssen K E, Stormo S K, Skåra T, et al. LWT—Food Science and Technology, 2020, 133: 110093.
[10] Wang Y J, Li T H, Li L Q, et al. Journal of Food Engineering, 2021, 290: 110181.
[11] Wan G, Liu G, He J, et al. Journal of Food Engineering, 2020, 287: 110090.
[12] LIU Gui-shan, ZHANG Chong, FAN Nai-yun, et al(刘贵珊,张 翀,樊奈昀,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2020, 40(8): 2558.
[13] Cheng L, Liu G, He J, et al. Meat Science, 2020, 167:107988.
[14] Chan S S, Roth B, Jessen F, et al. Scientific Reports, 2020, 10(1): 17160.
[15] Galvao R K H, Araujo M C U, José G E, et al. Talanta, 2005, 67(4): 736.
[16] Aheto J H, Huang X, Tian X, et al. Journal of Food Process Engineering, 2019, 42(6): e13225. |
[1] |
YUAN Wei-dong1, 2, JU Hao2, JIANG Hong-zhe1, 2, LI Xing-peng2, ZHOU Hong-ping1, 2*, SUN Meng-meng1, 2. Classification of Different Maturity Stages of Camellia Oleifera Fruit
Using Hyperspectral Imaging Technique[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3419-3426. |
[2] |
XU Ya-fen1, LIU Xian-yu1*, CHEN Quan-li2, XU Chang3. Study on Mineral Composition and Spectral Characteristics of “Middle East Turquoise”[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2862-2867. |
[3] |
YU Lian-gang1, LIU Xian-yu2*, CHEN Quan-li3. Gemstone Mineralogical and Spectroscopic Characteristics of
Quartzose Jade (“Mianlv Yu”)[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2543-2549. |
[4] |
LI Ming1, HONG Han-lie2. Gemological and Spectrographic Characteristics of Light-Green Tourmaline of Afghanistan[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2195-2201. |
[5] |
LI Bin, HAN Zhao-yang, WANG Qiu, SUN Zhao-xiang, LIU Yan-de*. Research on Bruise Level Detection of Loquat Based on Hyperspectral
Imaging Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(06): 1792-1799. |
[6] |
ZHANG Qi-yan1, YANG Jie2, 3, LI Jian-guo1*, SHI Wei-xin1, GAO Peng-xin1. Research on Quantitative Identification of Rock Color Using
Spectral Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(06): 1905-1911. |
[7] |
ZHOU Wu-bang1, QIN Dong-mei2, WANG Hao-tian1, CHEN Tao1, WANG Chao-wen1*. The Gemological, Mineralogical, and Spectral Characteristics of Indian Longdan Stone[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(06): 1895-1899. |
[8] |
ZHANG Fan1, WANG Wen-xiu1, ZHANG Yu-fan1, HU Ze-xuan1, ZHAO Dan-yang1, MA Qian-yun1, SHI Hai-yan2, SUN Jian-feng1*. Hyperspectral and Ensemble Learning Method for Rapid Identification of Black Spot in Yali Pear at Gley Stage[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(05): 1541-1549. |
[9] |
FU Wan-lu1, 2, LU Hao3*, CHAI Jun4, SUN Zuo-yu1. Spectroscopic Characteristics of Longxi Nephrite From Sichuan and Its Color Genesis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(05): 1408-1412. |
[10] |
HUANG Hao, LIAO Ning-fang*, ZHAO Chang-ming, WU Wen-min, FAN Qiu-mei. Computational Color Constancy Calculation Method for Spectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(04): 1004-1011. |
[11] |
JIA Meng-meng, YIN Yong*, YU Hui-chun, YUAN Yun-xia, WANG Zhi-hao. Hyperspectral Imaging Combined With Feature Wavelength Screening for Monitoring the Quality Change of Tomato During Storage[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(03): 969-975. |
[12] |
MAO Xiao-tian1, CHEN Chang2, YIN Zuo-wei1*, WANG Zi-min1. Spectra Characterization of Cr-Grossular (Tsavorite) With “Frogspawn” Color Zoning From Canada[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(02): 520-525. |
[13] |
BAO Pei-jin1, CHEN Quan-li1, 2*, WU Yan-han1, LI Xuan1, ZHAO An-di1. Spectroscopy Characteristics of Emerald From Swat Valley, Pakistan[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(01): 213-219. |
[14] |
HAO Jie, DONG Fu-jia, WANG Song-lei*, LI Ya-lei, CUI Jia-rui, LIU Si-jia, LÜ Yu. Rapid Detection of Pesticide Residues on Navel Oranges by Fluorescence Hyperspectral Imaging Technology Combined With Characteristic Wavelength Selection[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(12): 3789-3796. |
[15] |
CAO Su-qiao1, DAI Hui1*, WANG Chao-wen2, YU Lu1, ZUO Rui1, WANG Feng1, GUO Lian-qiao1. Gemological and Spectral Characteristics of Emeralds From Swat Valley, Pakistan[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(11): 3533-3540. |
|
|
|
|