浏览全部资源
扫码关注微信
1.温州大学 生命与环境科学学院,浙江 温州 325035
2.温州大学 电气与电子工程学院, 浙江 温州 325035
石文,博士,副教授,研究方向:信号与图像处理,E-mail:shiwen@wzu.edu.com
黄光造,博士,副教授,研究方向:光谱分析与机器学习,E-mail:guangzh@wzu.edu.cn
收稿日期:2024-11-18,
修回日期:2024-12-22,
录用日期:2025-01-13,
网络出版日期:2025-05-22,
纸质出版日期:2025-06-15
移动端阅览
吴琪,陈孝敬,石文,谢忠好,苏来金,黄光造.结合近红外光谱和模型更新的苹果品质无损检测[J].分析测试学报,2025,44(06):1-7.
WU Qi,CHEN Xiao-jing,SHI Wen,XIE Zhong-hao,SU Lai-jin,HUANG Guang-zao.Combining Near-infrared Spectroscopy and Model Updating for Nondestructive Testing of Apple Quality[J].Journal of Instrumental Analysis,2025,44(06):1-7.
吴琪,陈孝敬,石文,谢忠好,苏来金,黄光造.结合近红外光谱和模型更新的苹果品质无损检测[J].分析测试学报,2025,44(06):1-7. DOI: 10.12452/j.fxcsxb.241118535.
WU Qi,CHEN Xiao-jing,SHI Wen,XIE Zhong-hao,SU Lai-jin,HUANG Guang-zao.Combining Near-infrared Spectroscopy and Model Updating for Nondestructive Testing of Apple Quality[J].Journal of Instrumental Analysis,2025,44(06):1-7. DOI: 10.12452/j.fxcsxb.241118535.
品种的差异会影响苹果的可溶性固形物含量(SSC)和近红外光谱(NIRS)特征,进而导致在实际应用中以一个品种苹果建立的SSC光谱校正模型难以较好地预测其他品种的苹果。该研究使用阿克苏红富士苹果(批次1)开发了偏最小二乘回归(PLSR)校正模型,利用模型更新方法对青岛绯红苹果(批次2)进行预测。结果显示,以一阶导数(1D)和竞争自适应重加权采样(CARS)相结合开发的PLSR校正模型可以有效预测批次1的SSC,预测相关系数(
R
p
)和预测均方根误差(RMSEP)分别为0.972 8和0.383 8 °Brix,但批次1的 PLSR 模型难以预测批次2的SSC。因此使用校准更新、斜率/偏差校正(SBC)、动态正交投影(DOP)3种方法更新模型,同时研究不同更新样本数对更新效果的影响。结果显示,3种方法更新后模型预测结果的RMSEP均明显下降。其中,SBC方法取得最好的结果,使用20个新样本进行更新后,模型对批次2样本测试集预测的RMSEP从1.075 6 °Brix下降至0.233 4 °Brix。从实验结果可以看出,模型更新方法能够有效解决模型在预测不同品种苹果时表现不佳的问题,提升模型稳健性,为实际应用中SSC检测模型的更新维护提供重要指导。
Varietal differences significantly affect the soluble solid content(SSC) and near-infrared spectroscopy(NIRS) characteristics of apples,creating challenges when applying SSC spectral calibration models developed for one variety to others. This study developed a partial least squares regression(PLSR) calibration model using Aksu Fuji apples(Batch 1) and addressed the practical challenge of predicting SSC in Qingdao Scarlet apples(Batch 2) through model updating methods. The PLSR model,created with a combination of first derivative(1D) preprocessing and competitive adaptive reweighted sampling(CARS),effectively predicted SSC for Batch 1,achieving a correlation coefficient of prediction(
R
p
) of 0.972 8 and a root mean square error of prediction(RMSEP) of 0.383 8 °Brix. However,the Batch 1 model performed poorly in predicting SSC for Batch 2. To address this limitation,three model updating methods—calibration updating,slope/bias correction(SBC),and dynamic orthogonal projection(DOP)—were applied,and the impact of different update sample sizes was evaluated. Results showed that RMSEP significantly decreased after model updating. Among the methods,SBC performed best,reducing the RMSEP for Batch 2 from 1.075 6 °Brix to 0.233 4 °Brix with 20 new samples. These findings demonstrate that model updating effectively improves prediction performance across different apple varieties,enhancing model robustness and offering valuable guidance for maintaining and updating SSC detection models in practical applications.
Zhang Y K , Hartemink A E . Eur. J. Soil Sci. , 2020 , 71 ( 3 ): 316 - 333 .
Jiang H Z , Zhuang H , Sohn M , Wang W . Appl . Sci.-Basel , 2017 , 7 ( 1 ): 97 .
Kandpal L M , Tewari J , Gopinathan N , Stolee J , Strong R , Boulas P , Cho B K . Infrared Phys. Technol. , 2017 , 85 : 300 - 306 .
Chu X L , Chen P , Li J Y , Liu D , Xu Y P . J. Instrum. Anal. (褚小立,陈瀑,李敬岩,刘丹,许育鹏. 分析测试学报), 2020 , 39 ( 10 ): 1181 - 1188 .
Jia B , Chen Q W , Lai J M , Zhang L K , Xiang C Q , Guo T , Cheng M , Xiao X . J. Instrum. Anal. (贾彬,陈启文,赖嘉敏,张龙开,向超群,郭拓,程敏,肖雪. 分析测试学报), 2024 , 43 ( 3 ): 481 - 488 .
Cao X Q , Zeng L , Huang J , Wei S S , Tong H B , Zhang X , Wu M J , Yang Y . J. Instrum. Anal. (曹小青,曾丽,黄静,韦思思,佟海滨,张旭,吴明江,杨越. 分析测试学报), 2023 , 42 ( 9 ): 1119 - 1126 .
Lyu Q , Liao Q H , Liu Y L , Lan Y B . Intell. Autom. Soft Comput. , 2015 , 21 ( 3 ): 305 - 317 .
Zheng Y J , Cao Y C , Yang J , Xie L J . Postharvest Biol. Technol. , 2023 , 205 : 10 .
Lu Z H , Lu R T , Chen Y , Fu K , Song J X , Xie L L , Zhai R , Wang Z G , Yang C Q , Xu L F . Foods , 2022 , 11 ( 8 ): 15 .
Xie Z H , Feng X , Chen X J . Chemom. Intell. Lab. Syst. , 2022 , 221 : 10 .
Xie Z H , Feng X A , Li L M , Chen X J . J. Chemom. , 2022 , 36 ( 8 ): 14 .
Xie Z H , Chen X J , Roger J M , Ali S , Huang G Z , Shi W . Anal. Chim. Acta , 2024 , 1298 : 10 .
Mishra P , Woltering E , Brouwer B , Echtelt E H V . Postharvest Biol. Technol. , 2021 , 171 : 8 .
Tian S J , Liu W , Xu H R . Food Res. Int. , 2023 , 170 : 11 .
Zeaiter M , Roger J M , Bellon-Maurel V . Chemom. Intell. Lab. Syst. , 2006 , 80 ( 2 ): 227 - 235 .
Sun J H , Zhang W , Shi J Q , Li Y K . Acta Metrol. Sin. (孙嘉豪,张伟,施鉴芩,李艳坤. 计量学报), 2023 , 44 ( 8 ): 1284 - 1292 .
Rabatel G , Marini F , Walczak B , Roger J M . J. Chemom. , 2020 , 34 ( 2 ): 16 .
Yun Y H , Wang W T , Tan M L , Liang Y Z , Li H D , Cao D S , Lu H M , Xu Q S . Anal. Chim. Acta , 2014 , 807 : 36 - 43 .
Li H D , Liang Y Z , Xu Q S , Cao D S . Anal. Chim. Acta , 2009 , 648 ( 1 ): 77 - 84 .
Soares S F C , Gomes A A , Galvao A R , Araujo M C U , Galvao R K H . TrAC-Trends Anal . Chem. , 2013 , 42 : 84 - 98 .
Cai W S , Li Y K , Shao X G . Chemom. Intell. Lab. Syst. , 2008 , 90 ( 2 ): 188 - 194 .
Zude-Sasse M , Truppel I , Herold B . Postharvest Biol. Technol. , 2002 , 25 ( 2 ): 123 - 133 .
Jamshidi B , Minaei S , Mohajerani E , Ghassernian H . Comput. Electron. Agric. , 2012 , 85 : 64 - 69 .
Li Y K , Dong R N , Zhang J , Huang K N , Mao Z Y . Spectrosc . Spectral Anal. (李艳坤,董汝南,张进,黄克楠,毛志毅. 光谱学与光谱分析), 2021 , 41 ( 11 ): 3331 - 3338 .
0
浏览量
21
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构