Modeling effect of visible-near infrared spectrum on mutton glucose content based on SNV and MSC combined with genetic algorithm

YIN Chengcheng; KANG Jing; LIU Jianxin; NIAN Fang; TANG Defu

doi:10.11829/j.issn.1001-0629.2023-0348

Pratacultural Science > 2024 > 41(10): 2427-2434. > DOI: 10.11829/j.issn.1001-0629.2023-0348

YIN C C, KANG J, LIU J X, NIAN F, TANG D F. Modeling effect of visible-near infrared spectrum on mutton glucose content based on SNV and MSC combined with genetic algorithm. Pratacultural Science, 2024, 41(10): 2427-2434. DOI: 10.11829/j.issn.1001-0629.2023-0348

Citation:

PDF (2000 KB)

Modeling effect of visible-near infrared spectrum on mutton glucose content based on SNV and MSC combined with genetic algorithm

College of Science, Gansu Agricultural University, Lanzhou 730070, Gansu, China

More Information

Corresponding author:
NIAN Fang　E-mail: nianf@gsau.edu.cn
Received Date: June 28, 2023
Accepted Date: August 10, 2023
Available Online: September 22, 2024

Graphical Abstract

Abstract

Abstract

To improve the stability and prediction ability of the visible-near infrared spectral model for mutton nutrients, taking glucose (GLU) as an example, the characteristic wavelength was extracted by genetic algorithm (GA) and a prediction model was established. Two preprocessing methods, standard normal transformation (SNV) and multivariate scattering correction (MSC), were used to directly model the partial least squares regression and the results were compared. Genetic partial least squares model under SNV (GA-SNV-PLS) was better than the direct partial least squares model under SNV (FS-SNV-PLS). After cross-validation, the root mean square error (RMSE) of the model was 0.122, determinant coefficient R² was 0.930, and relative analysis error (RPD) was 2.295. Compared with the full spectrum, the R² and RPD for MSC and genetic partial least square model under MSC increased by 95.80%, 50.21%, 85.05%; 62.65%, 37.08%, and 52.54%, respectively.
- near infrared spectrum,
- fresh mutton,
- glucose,
- standard normal transformation,
- multivariate scattering correction,
- genetic algorithm

FullText(HTML)

References (23)

References

[1]	王芳, 王宏博, 席斌, 杨晓玲, 李维红, 高雅琴. 不同品种绵羊肉品质比较与分析. 食品与发酵工业, 2021, 47(1): 229-235. WANG F, WANG H B, XI B, YANG X L, LI W H, GAO Q Y. Comparison and analysis of meat quality of different breeds of sheep. Food and Fermentation Industries, 2021, 47(1): 229-235.
[2]	孔园园, 张雪莹, 李发弟,乐祥鹏. 羊肉主要风味前体物质与羊肉风味的关系及影响因素的研究进展. 农业生物技术学报, 2021, 29(8): 1612-1621. KONG Y Y, ZHANG X Y, LI F D, YUE X P. Research progress on the relationship between muton flavor precursors and mutton flavor and influencing factors. Journal of Agricultural Biotechnology, 2021, 29(8): 1612-1621.
[3]	李泽, 靳烨, 马霞. 不同贮藏温度下宰后羊肉的肉质变化及其影响因素. 农业工程学报, 2010, 26(S1): 338-342. LI Z, JIN H, MA X. Variation of postmortem lamb quality and its influencing factors in different store temperatures. Transactions of the Chinese Society of Agricultural Engineering, 2010, 26(S1): 338-342.
[4]	熊春晖, 佘永新, 焦逊, 邵勇, 贾莉, 王淼, 肖明, 王静. 高光谱成像技术在农产品无损检测中的应用. 粮油食品科技, 2023, 31(1): 109-122. XIONG C H, YU Y X, JIAO X, SHAO Y, JIA L, WANG M, XIAO M, WANG J. Application of hyperspectral imaging technology in nondestructive testing of agricultural products. Science and Technology of Cereals, Oils and Foods, 2023, 31(1): 109-122.
[5]	刘翠玲, 吴静珠, 孙晓荣. 近红外光谱技术在食品品质检测方法中的研究. 北京: 机械工业出版社, 2015. LIU C L, WU J S, SUN X R. Study on Near Infrared Spectroscopy Technology in Food Quality Detection. Beijing: Machinery Industry Press, 2015.
[6]	孙晓荣, 王赋腾, 刘翠玲, 张颖, 付新鑫. 基于MicroNir-2200的小麦粉水分含量快速检测. 传感器与微系统, 2018, 37(6): 139-141. SUN X R, WANG F T, LIU C L, ZHANG Y, FU X X. Rapid detection of moisture content in wheat flour based on MicroNir-2200. Transducer and Microsystem Technologies, 2018, 37(6): 139-141.
[7]	周倩, 冉玉钊, 刘欣, 李坤, 余孝其. 酯酶激活的近红外荧光前体药物设计与研究. 西华大学学报(自然科学版), 2020, 39(5): 42-48. ZHOU Q, RAN Y Z, LIU X, LI K, YU Q X. Design and research of near infrared fluorescence prodrug activated by esterase. Journal of Xihua University (Natural Science Edition), 2020, 39(5): 42-48.
[8]	褚小立, 袁洪福. 近红外光谱分析技术发展和应用现状. 现代仪器, 2011, 17(5): 1-4. CHU X L, YUAN H F. The research and application status of near infrared spectroscopy analytical technology. Modern Instruments, 2021, 17(5): 1-4.
[9]	DURAND A, DEVOS O, RUCKEBUSCH C, HUVENNE J P. Genetic algorithm optimisation combined with partial least squares regression and mutual information variable selection procedures in near-infrared quantitative analysis of cotton-viscose textiles. Analytica Chimica Acta, 2007, 595: 72-79. doi: 10.1016/j.aca.2007.03.024
[10]	葛旭通. 水溶葡萄糖近红外光谱测试及特征波长优选算法研究. 秦皇岛: 燕山大学硕士学位论文, 2019. GE X T. The collection for near-infrared spectroscopy of aqueous glucose solutions and research on characteristic wavelength optimization algorithm. Master Thesis. Qinhuangdao: Yanshan University, 2019.
[11]	AFROZ A M, SUMAN S. An adaptive frequency-fixed second-order generalized integrator-quadrature signal generator using fractional-order conformal mapping based approach. IEEE Transactions on Power Electronics, 2020, 35(6): 5548-5552. doi: 10.1109/TPEL.2019.2951427
[12]	张银, 周孟然. 近红外光谱分析技术的数据处理方法. 红外技术, 2007, 174(6): 345-348. ZHANG Y, ZHOU M R. Method of data processing for near infrared spectroscopy analysis. Infrared Technology, 2007, 174(6): 345-348.
[13]	WANG L H, CHEN L H. An improved genetic algorithm for determining the optimal operation strategy of thermal energy storage tank in combined heat and power units. Journal of Energy Storage, 2021, 42: 103313.
[14]	李有堂, 汤雷武, 黄华, 吴荣荣. 基于优化最小二乘支持向量机的数控机床热误差建模分析. 兰州理工大学学报, 2022, 48(3): 35-41. doi: 10.3969/j.issn.1673-5196.2022.03.006 LI Y T, TANG L W, HUANG H, WU R R. Thermal error modeling analysis of CNC machine tool based on optimized least squares support vector machine. Journal of Lanzhou University of Technology, 2022, 48(3): 35-41. doi: 10.3969/j.issn.1673-5196.2022.03.006
[15]	万丽颖. 岭回归分析及其应用. 许昌学院学报, 2016, 35(2): 19-23. WAN L Y. Ridge regression analysis and its application. Journal of Xuchang University, 2016, 35(2): 19-23.
[16]	HU J, LI Y, CHEN R. Establishment and optimization of temperature compensation model for benzoic acid detection based on terahertz metamaterial. Infrared Physics & Technology, 2022, 14: 123.
[17]	张铭明. 并行蛙跳遗传算法的研究及应用. 南宁: 广西大学硕士学位论文, 2017. ZHANG M M. The research and application of parallel frog leaping genetic algorithm. Master Thesis. Nanning: Guangxi University, 2017.
[18]	毛博慧, 孙红, 刘豪杰, 张逸俊, 李明赞, 杨立伟. 基于正交变换与SPXY样本划分的冬小麦叶绿素诊断. 农业机械学报, 2017, 48(S1): 160-165. MAO B H, SUN H, LIU H J. ZHANG Y J, LI M Z, YANG L W. Prediction of winter wheat chlorophyll content based on gram-schmidt and SPXY algorithm. Transactions of the Chinese Society for Agricultural Machinery, 2017, 48(S1): 160-165.
[19]	章海亮, 罗微, 刘雪梅, 何勇. 应用遗传算法结合连续投影算法近红外光谱检测土壤有机质研究. 光谱学与光谱分析, 2017, 37(2): 584-587. ZHANG H L, LUO W, LIU X M, HE Y. Measurement of soil organic matter with near infrared spectroscopy combined with genetic algorithm and successive projection algorithm. Spectroscopy and Spectral Analysis, 2017, 37(2): 584-587.
[20]	王国庆, 邵学广. 离散小波变换−遗传算法−交互检验法用于近红外光谱数据的高倍压缩与变量筛选. 分析化学, 2005(2): 191-194. WANG Q G, SAHO X G. A discrete wavelet transform-genetic algorithm-cross validation approach for high ratio compression and variable selection of near-infrared spectral data. Chinese Journal of Analytical Chemistry, 2005(2): 191-194.
[21]	KURT H, URS S. An evaluation of different NIR-spectral Pre-treatments to derive the soil parameters C and N of a humus-clay-rich soi. Sensors, 2021, 21(4): 1423. doi: 10.3390/s21041423
[22]	NAWAR S, MOUAZEN M M. Optimal sample selection for measurement of soil organic carbon using on-line vis-NIR spectroscopy. Computers and Electronics in Agriculture, 2018, 151: 469-477. doi: 10.1016/j.compag.2018.06.042
[23]	HUANG T C, CAI G M, LIU H B. Selecting near-infrared reflection spectroscopy pretreatment methods by chemical components valid and invalid absorption wavebands. Spectroscopy Letters, 2022, 55(9): 607-617. doi: 10.1080/00387010.2022.2136200

Cited By

Get Citation

PDF

XML

Article views (22) PDF downloads (13)

Turn off MathJax

Article Contents

Abstract

References

Modeling effect of visible-near infrared spectrum on mutton glucose content based on SNV and MSC combined with genetic algorithm

Abstract

References

Catalog

Export File

Citation

Format

Content