|
|
|
|
|
|
| Optimizations of Sample and Wavelength for Apple Brix Prediction Model Based on LASSOLars Algorithm |
| WANG Yu-qi, LI Bin, ZHU Ming-wang, LIU Yan-de* |
School of Intelligent Electromechanical Equipment Innovation Research Institute, East China Jiaotong University, Nanchang 330013, China
|
|
|
|
|
Abstract Sugar degree, one of the important indicators, is evaluating apples’ internal quality. When establishing a parsimonious model for analyzing apple sugar degree, the quality of calibrated samples and wavelengths affect the model’s accuracy, later update and maintenance.In this paper, 90 apples were taken as objects, a total of 1 044 wavelength points in the 350~1 150 nm spectra bands were collected. This paper studied the efficiency and feasibility of the Lasso implemented Least Angle Regression (LASSOLars) on sample and wavelength optimization.A combination of Norris derivative filtering, first-derivation and Variable Sorting for Normalization was used to preprocess. Considering the concentration ranking, split 75% of the sample dataset into the original train dataset (68 apples) and 25% into the test dataset (22 apples), and obtained the optimal train subset by LASSOLars. Compared LASSOLars with other two variables selection methods such as Monte Carlo Uninformative Variable Elimination and Competitive Adaptive Reweight Sampling respectively. Analyzing the model results, samples and wavelength sizes & distributions. The result shows that the optimal train subset compressed 16% of the original train dataset. At the same time, not changing the average level of the original train dataset, and the distribution was closer to the test dataset, the model quality was not weakened after reducing calibrated samples.The RMSECV of the optimal train subset and original train dataset were 0.460 and 0.491, the R2CV were 0.913 and 0.916, the RMSEP were 0.462 and 0.471, R2P were 0.909 and 0.906. LASSOLars selected out 40 wavelength points, the least size with the best results and highest signal-to-noise ratio, RMSECV, R2CV, RMSEP, R2P and RPD were 0.933, 0.400, 0.944, 0.373, 2.838. Based on the samples and wavelengths optimization by LASSOLars, which expanded the application of LASSOLars in subset selection, and provides ideas for optimizing, updating and maintaining the model.
|
|
Received: 2022-02-26
Accepted: 2022-06-01
|
|
|
|
Corresponding Authors:
LIU Yan-de
E-mail: jxliuyd@163.com
|
|
[1] ZHOU Yu, SUN Hong-yu, ZHU Wen-hao, et al(周 玉, 孙红玉, 朱文豪, 等). Application Research of Computers (计算机应用研究), 2021, 38(6): 1683.
[2] HE Kai-xun, CAO Peng-fei(贺凯迅, 曹鹏飞). Chemical Industry and Engineering Progress(化工进展), 2018, 37(7): 2516.
[3] Zhao Xin, Zhao Xiaokang, Huang Min, et al, Chemometrics and Intelligent Laboratory Systems, 2021, 217(15): 104426.
[4] Zhou Zhihua, Wu Jianxin, Tang Wei. Artificial Intelligence, 2002, 137: 239.
[5] Shetty Nisha, Rinnan Asmund, Gislum René. Chemometrics and Intelligent Laboratory Systems, 2012, 111(1): 59.
[6] YU Xin, ZHENG Zhao-bao, LI Lin-yi(虞 欣, 郑肇葆, 李林宜). Geomatics and Information Science of Wuhan University[武汉大学学报(信息科学版)], 2022，47(11): 1870.
[7] LI Jiang-bo, GUO Zhi-ming, HUANG Wen-qian, et al(李江波, 郭志明, 黄文倩, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2015, 35(2): 372.
[8] YU Wei, PENG Kuan-kuan, CHEN Wei, et al(余 伟, 彭宽宽, 陈 伟, 等). Chinese Journal of Analytical Chemistry(分析化学), 2016, 44(8): 1221.
[9] LI Hong, ZHANG Kai, CHEN Chao, et al(李 红, 张 凯, 陈 超, 等). Transactions of the Chinese Society for Agricultural Machinery (农业机械学报), 2021, 52(2): 211.
[10] WANG Jun-chao, GE Jun-feng(王骏超, 葛俊锋). Foreign Electronic Measurement Technology(国外电子测量技术), 2019, 38(3): 1.
[11] XIAO Yun-fei, GAO Xiao-hong, LI Guan-wen(肖云飞, 高小红, 李冠稳). Soils(土壤), 2020, 52(2): 404.
[12] Kump Paul, Bai Er-wei, Chan Kung-sik, et al. Automatica, 2012, 48(9): 2107.
[13] Yun Yonghuan, Li Hongdong, Deng Baichuan, et al. TrAC Trends in Analytical Chemistry, 2019, 113: 102.
[14] LIU Yan-de, XU Hai, SUN Xu-dong, et al(刘燕德, 徐 海, 孙旭东，等). Chinese Optics(中国光学), 2020, 13(3): 482.
[15] Rabatel Gilles, Marini Federico, Walczak Beata, et al. Journal of Chemometrics, 2020, 34(2): http://doi.org/10.1002/cem.3164. |
| [1] |
GAO Xi-ya1, 2, 3, ZHANG Zhu-shan-ying1, 2, 3*, LU Cui-cui1, 2, 3, MENG Yong-ji1, 2, 3, CAO Hui-min1, 2, 3, ZHENG Dong-yun1, 2, 3, ZHANG Li1, 2, 3, XIE Qin-lan1, 2, 3. Quantitative Analysis of Hemoglobin Based on SiPLS-SPA
Wavelength Optimization[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(01): 50-56. |
| [2] |
JIANG Xiao-gang1, ZHU Ming-wang1, YAO Jin-liang1, LI Bin1, LIAO Jun1, LIU Yan-de1*, ZHANG Jian-yi2, JING Han-song2. Research on Parameter Optimization of Apple Sugar Model Based on Near-Infrared On-Line Device[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(01): 116-121. |
| [3] |
MA Ben-xue1,2*, YU Guo-wei1,2, WANG Wen-xia1,2, LUO Xiu-zhi1,2, LI Yu-jie1,2, LI Xiao-zhan1,2, LEI Sheng-yuan1,2. Recent Advances in Spectral Analysis Techniques for Non-Destructive Detection of Internal Quality in Watermelon and Muskmelon: A Review[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(07): 2035-2041. |
| [4] |
ZHEN Huan-yi, MA Rui-jun*, CHEN Yu*, SUN Xiao-peng, MA Chuang-li. Study on Prediction Model of Malathion Pesticide Concentration Absorption Spectra Based on CARS and K-S[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(05): 1601-1606. |
| [5] |
CHEN Yi-fan, LI Yun-jing, PENG Miao-miao, YANG Chun-yong*, HOU Jin, CHEN Shao-ping. Improvements of VIS-NIR Spectroscopy Model in the Prediction of TVB-N Using MIV Wavelength Selection[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(05): 1413-1419. |
| [6] |
MEI Cong-li1，2, CHEN Yao2, YIN Liang2, JIANG Hui2, CHEN Xu2, DING Yu-han2, LIU Guo-hai2. Wavelength Selection by siPLS-LASSO for NIR Spectroscopy and Its Application[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(02): 436-440. |
| [7] |
YUAN Jing-ze1, 2, LU Qi-peng1*, WU Chun-yang1, 2, DING Hai-quan1, GAO Hong-zhi1, LI Wan-xia1, 2, WANG Yang3. Noninvasive Human Triglyceride Detecting with Near-Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(01): 42-48. |
| [8] |
LIU Guo-hai, XIA Rong-sheng, JIANG Hui*, MEI Cong-li, HUANG Yong-hong . A Wavelength Selection Approach of Near Infrared Spectra Based on SCARS Strategy and Its Application [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2014, 34(08): 2094-2097. |
| [9] |
LEI Meng, LI Ming*, MA Xiao-ping, MIAO Yan-zi, WANG Jian-sheng . Spectral Scatter Correction of Coal Samples Based on Quasi-Linear Local Weighted Method [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2014, 34(07): 1816-1820. |
| [10] |
WANG Li-qi1, GE Hui-fang1, LI Gui-bin1, YU Dian-yu2, HU Li-zhi2, JIANG Lian-zhou2* . Characteristic Wavelength Variable Optimization of Near-Infrared Spectroscopy Based on Kalman Filtering[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2014, 34(04): 958-961. |
| [11] |
LEI Meng1, LI Ming1*, WU Nan2, LI Ying-na3, CHENG Yu-hu1 . Influence of Different Coal Particle Sizes on Near-Infrared Spectral Quantitative Analytical Models[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2013, 33(01): 65-68. |
| [12] |
HONG Wen-xue1*, ZHANG Zhong-peng1, SONG Jia-lin1, LI Shao-xiong1, LUAN Jing-min1, CHEN Ning2, TAN Jian-qiang3. Research Progress in Using Functional Near-Infrared Spectroscopy for Monitoring Depth of Anesthesia[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2012, 32(11): 2939-2945. |
| [13] |
XU Tian-shuang1, XU Tao1, LAN Yu-bin2, WU Wen-fu3, ZHANG Hui-hui4, ZHU Hang1* . Study on a Method for Fast Selecting Feature Wavelengths from the Spectral Information of Crop Nitrogen [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2012, 32(08): 2185-2189. |
| [14] |
WANG Li1,2,MENG Qing-xiang1, REN Li-ping1*,YANG Jian-song1 . Near Infrared Reflectance Spectroscopy (NIRS) and Its Application in the Determination for the Quality of Animal Feed and Products [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2010, 30(06): 1482-1487. |
| [15] |
JIA Dong-yao1,YANG Wen-kao2,LIU Ze1. Metamerism Breakdown Characteristic and Its Application in Detection of Foreign Materials[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2008, 28(11): 2596-2600. |
|
|
|
|
