|
|
|
|
|
|
An Improved XGBoosting Algorithm Based on Fat Content in Infant Milk Powder Prediction Model |
ZHANG Wen-jing1, 2, XUE He-ru1, 2*, JIANG Xin-hua1, 2, LIU Jiang-ping1, 2, HUANG Qing1 |
1. College of Computer and Information Engineering, Inner Mongolia Agricultural University, Huhhot 010018, China
2. Inner Mongolia Key Laboratory of Big Date Research and Application in Agriculture and Animal Husbandry Agricultural University, Huhhot 010018, China
|
|
|
Abstract Fat plays an essential role in the composition of infant formula. Not only is fat a vital component of a baby's growth and development, but it also provides essential energy for growth. It is crucial for the development of the infant brain and the formation of nerve myelin. Chemical methods for determining the fat content of infant milk powder, such as ether extraction, are sensitive but have the disadvantage of destroying samples and having a long detection period. In this paper, the hyperspectral data undergoes preprocessing processes with standard normal transform (SNV), multiple scattering corrections (MSC), Savitzky-Golay smoothing, and Roust method using different stages of infant milk powder in Inner Mongolia, China. A competitive adaptive re-weighting algorithm, CARS, was used to sift out redundant wavelengths from the spectroscopic data at 125 feature wavelengths, leaving 66 valid wavelengths. The Bayesian optimization algorithm optimizes the XGBoosting prediction model, leading to a BO-XGBoosting model that predicts the fat content of infant formula better than the original model. The experimental results show that the model predicts better than the traditional partial least squares regression (PLSR) and support vector machine (SVR) regression model, outperforming the Bagging and GrdientBoosting algorithms in the integrated algorithm. In the BO-XGBoosting model in the test set experiments, the decision coefficient R2 and root mean square error of prediction (RMSEP) obtained are 0.953 7 and 0.577 3, which are 2.91% higher and 19.2% lower than the determination coefficient R2 and root mean squared error of prediction (RMSEP) of the XGBoosting model's R2 and RMSEP, respectively. This study provides algorithmic support and a theoretical foundation for BO-XGBooting based rapid, non-destructive detection of infant formula fat content.
|
Received: 2023-02-19
Accepted: 2023-08-06
|
|
Corresponding Authors:
XUE He-ru
E-mail: xuehr@imau.edu.cn
|
|
[1] CUI Bao-wei, SONG Jing-cheng, GAO Yue, et al(崔保威,宋京城,高 岳,等). Food Industry(食品工业), 2020, 41(8): 293.
[2] ZONG Jing, BO Han-ping, CHEN Da, et al(宗 婧,卜汉萍,陈 达,等). Journal of Instrumental Analysis(分析测试), 2019, 38(10): 1187.
[3] Liang Wenting, Wei Yuqiang, Meng Jie, et al. Food Analytical Methods, 2020, 13: 2059.
[4] Asma Khan, Munir M T, Yu W, et al. Food and Bioprocess Technology,2020, 13(5):739.
[5] SUN Zong-bao, WANG Tian-zhen, LIU Xiao-yu, et al(孙宗保,王天真,刘小裕,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2020, 40(10): 3224.
[6] Woodcock T, Fagan C C, O'Donnell C P, et al. Food Bioprocess Technol., 2008, 1 (2): 117.
[7] Debora A P, Forchetti P, Ronei J, et al. LWT-Food Science and Technology, 2017, (76): 337.
[8] ZHAO Zi-zhu, WEI Yong, ZHANG Nai-qian, et al(赵紫竹,卫 勇,张乃迁,等). China Dairy Industry(中国乳品工业), 2018, 46(2): 45.
[9] Asma Khan, Muhammad Tajammal Munir, Wei Yu, et al. Sensors, 2020, 20: 4645.
[10] Munir M T, David I Wilson, Yu W, et al. Journal of Food Engineering, 2018, (211): 1.
[11] Liu Jiangping, Hu Pengwei, Xue Heru, et al. Spectroscopy Letters, 2022, 55(4): 229.
[12] Lee H, Kim Moon S, Lohumi Santosh, et al. Food Additives & Contaminants. Part A, Chemistry, Analysis, Control, Exposure & Risk Assessment, 2018, (35): 1027.
[13] YU Shuang, LIU Guo-hai, MEI Cong-ling, et al(于 霜,刘国海,梅从立,等). Computer and Applied Chemistry(计算机与应用化学), 2014, 31(9): 1143.
[14] Huang M, Kim M S, Delwiche S R, et al. Journal of Food Engineering, 2016, 181: 10.
[15] CUI Jia-xu,YANG Bo(崔佳旭,杨 博). Journal of Software(软件学报),2018, 29(10): 3068.
[16] LI Ya-ru, ZHANG Yu-lai, WANG Jia-chen(李亚茹,张宇来,王佳晨). Computer Science(计算机科学), 2022, 49(6A): 86.
[17] XU Zhou-bo, YANG Jian, LIU Hua-dong(徐周波, 杨 健,刘华东,等). Journal of Computer Applications(计算机应用), 2020, 40(5):1510.
[18] YANG Ze, FENG Jia-li, ZHANG Hong, et al(杨 泽,冯佳丽,张 宏,等). Journal of Anhui Science and Technology University(安徽科技学院学报),2019, 33(2): 70.
|
[1] |
LIU Zhen-fang, HUANG Min*, ZHU Qi-bing, ZHAO Xin, YAN Sheng-qi. Spatially Offset Raman Spectroscopy Analysis Technology and Application in Food Subsurface Detection[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(05): 1201-1208. |
[2] |
WANG Cong1, 2, Mara Camaiti3, LIU Dai-yun4, TIE Fu-de2, 5, CAO Yi-jian5, 6*. Recent Advances in the Application of the Field-Portable Hyperspectral Radiometer to Characterize Materials Concerning Cultural Heritage[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(05): 1218-1226. |
[3] |
WANG Xiao-bin, ZHANG Ao-lin, ZOU Ying-fang, YANG Lei. Spectral Pattern Recognition of Erasable Ink Based on Hilbert Filter[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(05): 1338-1345. |
[4] |
SONG Shao-zhong1, LIU Yuan-yuan2, ZHOU Zi-yang3, TENG Xing3, LI Ji-hong3, LIU Jun-ling1, GAO Xun2*. Identification of Sorghum Breed by Hyperspectral Image Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(05): 1392-1397. |
[5] |
BAI Zong-fan1, HAN Ling1*, JIANG Xu-hai1, WU Chun-lin2. Effect of Differential Spectral Transformation on Soil Heavy
Metal Content Inversion Accuracy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(05): 1449-1456. |
[6] |
LIU Zi-yang1, 2, FENG Shuai1, 2, ZHAO Dong-xue1, 2, LI Jin-peng1, 2, GUAN Qiang1, 2, XU Tong-yu1, 2*. Research on Spectral Feature Extraction and Detection Method of Rice Leaf Blast by UAV Hyperspectral Remote Sensing[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(05): 1457-1463. |
[7] |
NING Jing1, 2, ZOU Bin1, 2*, TU Yu-long1, 2, ZHANG Xia3, WANG Yu-long1, 2, TIAN Rong-cai1, 2. Evaluation of Soil As Concentration Estimation Method Based on Spectral Indices[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(05): 1472-1481. |
[8] |
XIE Bai-heng1, MA Jin-fang1, ZHOU Yong-xin1, HAN Xue-qin1, CHEN Jia-ze1, ZHU Si-qi1, YANG Mao-xun2, 3*, HUANG Fu-rong1*. Identification of Citri Grandis Fructus Immaturus Based on Hyperspectral Combined With HHO-KELM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(05): 1494-1500. |
[9] |
JIANG Yue-peng, CAO Yun-hua*, WU Zhen-sen, CAO Yi-sen, HU Sui-jing. Measurement of Mid-Wave Infrared Hyperspectral Imaging
Characteristics of Ground Targets[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(04): 937-944. |
[10] |
WANG Xue-ying1, 2, LIU Shi-bo4, ZHU Ji-wei1, 3*, MA Ting-ting3. Inversion of Chemical Oxygen Demand in Surface Water Based on Hyperspectral Data[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(04): 997-1004. |
[11] |
ZHANG Fu1, 2, YU Huang1, XIONG Ying3, ZHANG Fang-yuan1, WANG Xin-yue1, LÜ Qing-feng4, WU Yi-ge4, ZHANG Ya-kun1, FU San-ling5*. Hyperspectral Non-Destructive Detection of Heat-Damaged Maize Seeds[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(04): 1165-1170. |
[12] |
ZHANG Li-xiu, ZHANG Shu-juan*, SUN Hai-xia, XUE Jian-xin, JING Jian-ping, CUI Tian-yu. Determination of Soluble Solid Content in Peach Based on Hyperspectral Combination With BPSO[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(03): 656-662. |
[13] |
LI Hui1, LIU Xu-sheng2, JIANG Jin-bao3*, CHEN Xu-hui4, ZHANG Shuai5, TANG Ke1, ZHAO Xin-wei1, DU Xing-qiang1, YU LONG Fei-xue1. Extraction of Natural Gas Microleakage Stress Regions Based on Hyperspectral Images of Winter Wheat[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(03): 770-776. |
[14] |
WANG Mao-cheng1, LI Gan1, CHENG Hao2, JIANG Wei1, CHEN Guang1, LI Hai-bo1*. Double-Wavelength NIR Raman Spectroscopy and the Application on
Corrosion Products[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(03): 756-761. |
[15] |
HU Cheng-hao1, WU Wen-yuan1, 2*, MIAO Ying1, XU Lin-xia1, FU Xian-hao1, LANG Xia-yi1, HE Bo-wen1, QIAN Jun-feng3, 4. Study on Hyperspectral Rock Classification Based on Initial Rock
Classification System[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(03): 784-792. |
|
|
|
|