浏览全部资源
扫码关注微信
1.桂林理工大学 数学与统计学院,广西 桂林 541004
2.仲恺农业工程学院 自动化学院,广东 广州 510225
3.广西高校应用统计重点实验室,广西 桂林 541004
陈华舟,教授,研究方向:生物信息与化学计量学,E-mail:hzchengut@foxmail.com
收稿日期:2025-02-18,
修回日期:2025-03-19,
录用日期:2025-03-20,
纸质出版日期:2025-06-15
移动端阅览
林雪梅,蔡肯,黄家立,蒙芳秀,林钦永,陈华舟.基于CNN框架的LSTM融合优化模型用于芒果干物质的近红外光谱分析[J].分析测试学报,2025,44(06):1176-1182.
LIN Xue-mei,CAI Ken,HUANG Jia-li,MENG Fang-xiu,LIN Qin-yong,CHEN Hua-zhou.Fusion Model of LSTM Optimization Based on CNN Framework and Its Application to NIR Spectroscopic Analysis of Mango Dry Matter[J].Journal of Instrumental Analysis,2025,44(06):1176-1182.
林雪梅,蔡肯,黄家立,蒙芳秀,林钦永,陈华舟.基于CNN框架的LSTM融合优化模型用于芒果干物质的近红外光谱分析[J].分析测试学报,2025,44(06):1176-1182. DOI: 10.12452/j.fxcsxb.25021897.
LIN Xue-mei,CAI Ken,HUANG Jia-li,MENG Fang-xiu,LIN Qin-yong,CHEN Hua-zhou.Fusion Model of LSTM Optimization Based on CNN Framework and Its Application to NIR Spectroscopic Analysis of Mango Dry Matter[J].Journal of Instrumental Analysis,2025,44(06):1176-1182. DOI: 10.12452/j.fxcsxb.25021897.
芒果中的干物质(DM)含量是评判芒果品质的重要指标之一。该文利用近红外光谱法(NIR)检验和预测芒果的干物质含量。主要基于卷积神经网络(CNN)框架,研究其结构参数网格数值化筛选方案,融入长短期记忆网络(LSTM)完成参数协同优化,构建CNN-LSTM融合优化模型。实验过程中,通过构建浅层CNN建模框架,针对CNN-LSTM模型的核心参数进行局部规模的超参数联合调试。模型训练和模型测试结果显示,CNN模型和CNN-LSTM模型的最优化预测结果均明显优于常规的线性或非线性模型。该研究除了确定最优模型以外,还提供了更多可选的模型优化参数组合,有望在芒果的生产和培育过程中得到应用。浅层CNN框架融合LSTM优化模型及其参数网格数值化筛选方案能够为快速检测芒果果实中的干物质含量提供化学计量学技术支持。
The content of dry matter(DM) is one of the important indices to determine the quality of mango. In this paper,near-infrared spectroscopy(NIR) is used to predict the dry matter content of mango,so as to achieve rapid evaluation of mango quality. The study launched to propose the grid numericalization scheme for screening structural parameters based on the convolutional neural network(CNN) framework. The parameter optimization strategy was improved by the fusion of long short-term memory(LSTM) network,to propose the CNN-LSTM combined optimization model. In data experiment,a shallow CNN modeling architecture was constructed. The hyperparameters were for refine tuning by testing some local-scale values of the core parameters of CNN-LSTM model. Results showed that the optimal CNN model and CNN-LSTM models were obviously better than the conventional linear or nonlinear models in both the model training and model testing stages. In addition to identifying the most optimal models,we also provided some other appreciating less-optional models as well as their available parameter combinations. These findings are expected to be helpful in the production line of mango cultivation. The modeling framework of a shallow CNN architecture in fusion with the LSTM optimization provides chemometrics technical support for rapid detection of dry matter content in mango fruit.
Ratprakhon K , Neubauer W , Riehn K , Fritsche J , Rohn S . Foods , 2020 , 9 : 1709 .
de Freitas S T , Guimaraes I T , Vilvert J C , do Amaral M H P , Brecht J K , Marques A T B . Postharvest Biol. Technol. , 2022 , 189 : 111917 .
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 .
Liu Y D , Liao J , Li B , Jiang X G , Zhu M W , Yao J L , Wang Q . Spectrosc. Spectral Anal. (刘燕德,廖军,李斌,姜小刚,朱明旺,姚金良,王秋. 光谱学与光谱分析), 2022 , 42 ( 9 ): 2781 - 2787 .
Mishra P , Paillart M , Meesters L , Woltering E , Chauhan A . Postharvest Biol. Technol. , 2022 , 183 : 111739 .
Duarte M S , Pontes M J C , Ramos C S . J. Appl. Spectrosc. , 2016 , 82 : 1042 - 1045 .
Ma H L , Wang J W , Chen Y J , Cheng J L , Lai Z T . Food Chem. , 2017 , 215 : 108 - 115 .
Zhang H , Tan H N , Lin B R , Yang X C , Sun Z Y , Zhong L , Gao L L , Li L , Dong Q , Nie L , Zang H C . Molecules , 2023 , 28 : 406 .
Xu Y , Li M , Feng T , Jiao L , Wu F , Zhang T , Tang H , Li H . Chem. Res. Chin. Univ. , 2022 , 38 : 1057 - 1064 .
Wang J J , Yang J H , Shao X G . J. Instrum. Anal. (王家俊,杨家红,邵学广. 分析测试学报), 2020 , 39 ( 10 ): 1218 - 1224,1230 .
Anderson N T , Walsh K B , Flynn J R , Walsh J P . Postharvest Biol. Technol. , 2021 , 171 : 111358 .
Tosin R , Martins R , Pocas I , Cunha M . Biosyst. Eng. , 2022 , 219 : 235 - 258 .
Yang J , Liu Y , Li J Y , Chen P , Xu Y P , Liu D , Chu X L . Prog. Chem. (杨健,刘宇,李敬岩,陈瀑,许育鹏,刘丹,褚小立. 化学进展), 2024 , 36 ( 12 ): 1874 - 1892 .
Zheng Y , Yang S Y , Wang T , Deng Z W , Lan W J , Yun Y H , Pan L Q . Chin. J. Anal. Chem. (郑运,杨思雨,王涛,邓焯文,兰维杰,云永欢,潘磊庆. 分析化学), 2024 , 52 ( 9 ): 1266 - 1276 .
Cai K , Chen H , Ai W , Miao X , Lin Q , Feng Q . IEEE T. Ind. Inform. , 2022 , 18 ( 2 ): 1200 - 1209 .
Acquarelli J , van Laarhoven T , Gerretzen J , Tran T N , Buydens L M C , Marchiori E . Anal. Chim. Acta , 2017 , 954 : 22 - 31 .
Zhu Z , Qi G , Lei Y , Jiang D , Mazur N , Liu Y , Wang D , Zhu W . Chemosensors , 2022 , 10 ( 5 ): 164 .
Chen C , Yang B , Si R M , Chen C , Chen F F , Gao R , Li Y Z , Tang J , Lv X Y . Optik , 2021 , 242 : 167080 .
Shafik W , Tufail A , Liyanage C D S , Apong R A A H M . J. Sci. Food Agric. , 2023 , 103 : 5849 - 5861 .
Liao F , Feng X , Li Z , Wang D , Xu C , Chu G , Ma H , Yao Q , Chen S . J. Integr. Agric. , 2024 , 23 : 711 - 723 .
Anderson N , Walsh K , Subedi P . Mango DMC and Spectra , Mendeley Data ,V1, 2020 . doi: 10.17632/46htwnp833.1 http://dx.doi.org/10.17632/46htwnp833.1 .
Chen H , Chen A , Xu L , Xie H , Qiao H , Lin Q , Cai K . Agric. Water Manag. , 2020 , 240 : 106303 .
Zhang L . Anal. Methods , 2019 , 11 : 3936 - 3942 .
0
浏览量
77
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构