|
|
|
|
|
|
| Optimization of Prediction Model for Milk Fat Content Based on Improved Whale Optimization Algorithm |
| LI Xin1, LIU Jiang-ping1, 2*, HUANG Qing1, HU Peng-wei1, 2 |
1. College of Computer and Information Engineering of the Inner Mongolia Agricultural University, Huhhot 010018, China
2. Inner Mongolia Autonomous Region Key Laboratory of Big Data Research and Application of Agriculture and Animal Husbandry, Huhhot 010030, China
|
|
|
|
|
Abstract Milk fat content of high and low will affect people's health. The experiment in milk fat content analysis indicators, application of image processing technology analysis of hyperspectral data, extracting the region of interest (ROI) from hyperspectral images using the ENVI software, different preprocessing methods were used to establish Partial Least Squares Regression (PLSR) model for spectral data and the best preprocessing method was obtained by comparison, Then, different numbers of principal components were used for feature extraction of the pre-processed data and Support Vector Regression (SVR) model was established. The optimal number of principal components was obtained through comparison. Finally, the SVR prediction model was established for the data after feature extraction to analyze the fat content in milk. Since the traditional SVR model has a poor prediction effect and cannot meet people's basic requirements, this paper proposes a hybrid strategy improved whale optimization algorithm to optimize the SVR prediction model. The evaluation parameters of the SVR model optimized by hybrid strategy whale optimization algorithm are compared with those optimized by genetic algorithm, traditional whale optimization algorithm and elite reverse learning whale optimization algorithm. The results show that the training set and prediction set coefficient of determination (R2) of the SVR model optimized by hybrid strategy modified Whale optimization algorithm are 0.998 and 0.995, respectively. The reciprocal 1/RMSE values of Root Mean Square Error (RMSE) were 13.766 and 6.191, and the reciprocal 1/MAE values of Mean Absolute Error (MAE) were 13.910 and 11.422, respectively. The training set and prediction set parameters R2 of the SVR model optimized by the traditional whale optimization algorithm are 0.998 and 0.989, 1/RMSE is 13.526 and 5.849, and 1/MAE is 13.616 and 7.037, respectively. The training set and prediction set parameters R2 of the SVR model optimized by the whale optimization algorithm improved by reverse learning strategy are 0.998 and 0.988, 1/RMSE is 12.474 and 6.421, and 1/MAE is 15.003 and 10.554, respectively. The above results show that the hybrid strategy improved whale optimization algorithm is feasible to optimize the SVR prediction model, and the optimized SVR model has a better prediction effect.
|
|
Received: 2022-04-20
Accepted: 2022-09-28
|
|
|
|
Corresponding Authors:
LIU Jiang-ping
E-mail: liujiangping@imau.edu.cn
|
|
[1] YANG Jin-hui, BU Deng-pan, WANG Jia-qi, et al(杨晋辉, 卜登攀, 王加启, 等). Food Science(食品科学)，2013, 34(20): 153.
[2] ZHAO Ming-fu, SHI Yu-jia, LUO Bin-bin, et al(赵明富, 施玉佳, 罗彬彬, 等). Laser Journal(激光杂志), 2014, 35(1): 44.
[3] 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.
[4] HU Peng-wei, LIU Jiang-ping, XUE He-ru, et al(胡鹏伟, 刘江平, 薛河儒, 等). Journal of Opoelectronics·Laser(光电子·激光), 2022, 33(1): 23.
[5] CHEN Jin-yin, XIONG Hui, ZHENG Hai-bin(陈晋音, 熊 晖, 郑海斌). Computer Science(计算机科学), 2018, 45(6): 197.
[6] PAN Hai-zhu, GE Hai-miao, SU Xiao-hong, et al(潘海珠, 葛海淼, 苏小红, 等). Research and Exploration in Laboratory(实验室研究与探索), 2021, 40(10): 6.
[7] WANG Li-wen, LIU Jian-hua, CHEN Bin, et al(王立文, 刘建华, 陈 斌, 等). Computer Simulation(计算机仿真), 2021, 38(9): 45.
[8] LI Ping, NI Zhi-wei, ZHU Xu-hui, et al(李 萍, 倪志伟, 朱旭辉, 等). Journal of Systems Science and Mathematical Sciences(系统科学与数学), 2020, 40(6): 1020.
[9] LU Xue-qin, LI Chang-an, WU Zhong-qiang(卢雪琴, 李长安, 吴忠强). Smart Power(智慧电力), 2022, 50(2): 15.
[10] XU Jian-zhong, YAN Fu(徐建中, 晏 福). Operations Research and Management Science(运筹与管理), 2020, 29(9): 149.
[11] WU Zi-ke, PAN Pan, PENG Cheng, et al(武子科, 潘 攀, 彭 诚). Computer Engineering and Design(计算机工程与设计), 2022, 43(3): 814.
[12] GUO Qi-cheng, DU Xiao-yu, ZHANG Yan-yu, et al(郭启程, 杜晓玉, 张延宇, 等). Computer Science(计算机科学), 2021, 48(12): 304.
[13] SUN Zong-bao, WANG Tian-zhen, LI Jun-kui, et al(孙宗保, 王天真, 李君奎, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2020, 40(7): 2208.
[14] WANG Yang-ping, JIAO Jian-jun(王养平, 焦建军). Journal of Food Safety and Quality(食品安全质量检测学报), 2022, 13(5): 1405.
[15] HE Xiao-long, ZHANG Gang, CHEN Yue-hua, et al(何小龙, 张 刚, 陈跃华, 等). Application Research of Computers(计算机应用研究), 2021, 38(12): 3640.
[16] GENG Zhao-li, LI Mu, CAO Shu-rui, et al(耿召里, 李 目, 曹淑睿, 等). Computer Engineering & Science(计算机工程与科学), 2022, 44(2): 355.
[17] XIAO Zi-ya, LIU Sheng(肖子雅, 刘 升). Acta Electronica Sinica(电子学报), 2019, 47(10): 2177.
|
| [1] |
YAN Zhong-wei1, 2, 3, TIAN Xi2, 3, ZHANG Yi-fei2, 3, LI Lian-jie2, 3, LIU San-qing1, 2, 3, HUANG Wen-qian2, 3*. Online Detection of Soluble Solids Content in Different Parts of
Watermelons Based on Full Transmission Near Infrared
Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(06): 1800-1808. |
| [2] |
GUO Yang1, GUO Jun-xian1*, SHI Yong1, LI Xue-lian1, HUANG Hua2, LIU Yan-cen1. Estimation of Leaf Moisture Content in Cantaloupe Canopy Based on
SiPLS-CARS and GA-ELM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(08): 2565-2571. |
| [3] |
ZHANG Yan-jun1, 2, ZHANG Fang-cao1, FU Xing-hu1*, JIN Pei-jun1, HOU Jiao-ru1. Detection of Fatty Acid Content in Mixed Oil by Raman Spectroscopy Based on ABC-SVR Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(07): 2147-2152. |
| [4] |
WANG Yu-tian1, LIU Ling-fei1*, ZHANG Li-juan1,2, ZHANG Zheng-shuai1, LIU Ting-ting1, WANG Shu-tao1, SHANG Feng-kai1. Determination of 1-Naphthol and 2-Naphthol Based on Fluorescence Spectrometry Combined with Improved FastICA-SVR[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(01): 142-149. |
| [5] |
MO Xin-xin1, ZHOU Ying2, SUN Tong1*, WU Yi-qing1, LIU Mu-hua1 . Model Optimization of Ternary System Adulteration Detection in Camellia Oil Based on Visible/Near Infrared Spectroscopy [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(12): 3881-3884. |
| [6] |
FENG Yan-chun, ZHANG Qi, HU Chang-qin* . Study on the Selection of Parameters for Evaluating Drug NIR Universal Quantitative Models [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(08): 2447-2454. |
| [7] |
GENG Ying1, XIANG Bing-ren2, HE Lan1* . Study on the Application of NAS-Based Algorithm in the NIR Model Optimization[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2015, 35(10): 2730-2733. |
| [8] |
ZHANG Bing, DENG Zhi-yin, ZHENG Jing-kui, WANG Xiao-ping*. Determination of Gasoline Composition Based on Raman Spectroscopy [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2015, 35(06): 1577-1581. |
| [9] |
DENG Zhi-yin, ZHANG Bing, DONG Wei, WANG Xiao-ping* . Research on Prediction Method of Fatty Acid Content in Edible Oil Based on Raman Spectroscopy and Multi-Output Least Squares Support Vector Regression Machine [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2013, 33(11): 2997-3001. |
| [10] |
ZHAO Long-lian1,2,LI Jun-hui1,ZHANG Wen-juan1,WANG Jian-cai1,ZHANG Lu-da3*. Calibration Transfer between Two FTNIR Spectrophotometers Using SVR[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2008, 28(10): 2299-2303. |
| [11] |
WU De-hui1,2. Online Soft Sensing Method for Freezing Point of Diesel Fuel Based on NIR Spectrometry[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2008, 28(07): 1530-1534. |
| [12] |
HAO Hui-min1,2,TANG Xiao-jun1,BAI Peng1,3,LIU Jun-hua1,ZHU Chang-chun1. Quantitative Analysis of Multi-Component Gas Mixture Based on KPCA and SVR[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2008, 28(06): 1286-1289. |
| [13] |
WU Jing-zhu1,3, WANG Yi-ming1*, ZHANG Xiao-chao2, XU Yun1 . Study on Quality Detection of Milk Powder Based on Near Infrared Spectroscopy (NIR)[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2007, 27(09): 1735-1738. |
| [14] |
LI Jun-xia1, 4,MIN Shun-geng2, ZHANG Hong-liang1, YAN Yan-lu3, LUO Chang-bing3, LI Zi-chao1* . The PLS Calibration Model Optimization and Determination of Rice Protein Content by Near-Infrared Reflectance Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2006, 26(05): 833-837. |
| [15] |
MIN Shun-geng, LI Ning, ZHANG Ming-xiang. Outlier Diagnosis and Calibration Model Optimization for Near Infrared Spectroscopy Analysis [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2004, 24(10): 1205-1209. |
|
|
|
|
