数字农科院2.0

Fusing band and feature attention in CNN-LSTM: A dual-attention framework for Hyperspectral-based precise prediction of nicotine levels in cured tobacco leaves

文献类型： 外文期刊

作者： Fukang Xing;Chengzong Dai;Lingfeng Meng;Songfeng Wang;Jie Ren;Rongguang Zhu;Kesu Wei

作者机构：

关键词： Attention mechanisms;Cured tobacco;Deep learning;Hyperspectral imaging;Nicotine;Quality assessment

期刊名称： Industrial Crops and Products

ISSN： 0926-6690

年卷期： 2025 年 236 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Rapid and reliable quantification of key chemical constituents in cured tobacco leaves remains a critical challenge in industrial processing. This study introduced an intelligent prediction framework that combines hyperspectral imaging (HSI) with a deep neural network model enhanced by dual-attention modules. A multi-region spectral acquisition strategy was employed to capture representative reflectance data from different leaf areas. To improve feature learning, a Dual-Attention-enhanced CNN-LSTM (DACL) model was developed by incorporating a Band Attention (BA) module for adaptive spectral band selection and a Self-Attention (SA) module for deep feature refinement. The DACL model was trained on multi-region averaged spectra and systematically evaluated against classical machine learning models (PLSR, SVR) and deep learning baselines (CNN, LSTM, CNN-LSTM). The DACL approach achieved superior performance, with an R² of 0.857, an RMSE of 0.443, and an RPD of 2.642 on the independent test set. Visualization of the attention modules confirmed that the model consistently prioritized wavelengths corresponding to nicotine's characteristic absorption bands, thereby enhancing both predictive accuracy and interpretability. The results demonstrate that the fusion of spectral and deep feature attention within a CNN-LSTM architecture, together with multi-ROI spectral acquisition, provides a robust and interpretable solution for real-time nicotine assessment in cured tobacco. The proposed method offers new insights for quality control in tobacco processing and highlights the broader potential of AI-driven hyperspectral analysis in agricultural product evaluation.

分类号：

  • 相关文献

[1]A novel dual-branch spatial-spectral attention fusion model and method: A case study for the detection of nicotine content in tobacco leaves. Fukang Xing,Rongguang Zhu,Shichang Wang,Lingfeng Meng,Fujia Dong,Songfeng Wang,Jie Ren,Zongxiu Bai,Yapeng Kang. 2025

[2]DAFFnet: Seed classification of soybean variety based on dual attention feature fusion networks. Lingyu Zhang,Laijun Sun,Xiuliang Jin,Xiangguang Zhao,Shujia Li. 2025

[3]Estimation of wheat biomass based on phenological identification and spectral response. Tao Liu,Tianle Yang,Shaolong Zhu,Nana Mou,Weijun Zhang,Wei Wu,Yuanyuan Zhao,Zhaosheng Yao,Jianjun Sun,Chen Chen,Chengming Sun,Zujian Zhang. 2024

[4]Progress in machine learning-supported electronic nose and hyperspectral imaging technologies for food safety assessment: A review. Mogos Girmatsion,Xiaoqian Tang,Qi Zhang,Peiwu Li. 2025

[5]Hyperspectral Imaging-Based Deep Learning Method for Detecting Quarantine Diseases in Apples. Hang Zhang,Naibo Ye,Jingru Gong,Huajie Xue,Peihao Wang,Binbin Jiao,Liping Yin,Xi Qiao. 2025

[6]Characteristics of Hydro-Geochemistry and Groundwater Pollution in Songnen Plain in Northeastern China. Chen, Ruihui,Liu, Linmei,Li, Yi,Zhai, Yuanzheng,Chen, Haiyang,Hu, Bin,Zhang, Qianru,Teng, Yanguo. 2022

[7]Comparison of different pretreatments on drying characteristics, physical properties, nutritional compounds and antioxidant activity of heat pump-dried longan pulp. Zhu, Jingnan,Peng, Jian,Li, Jun,Li, Lu,Bi, Jinfeng,Yang, Wanyuan,Yi, Jianyong,Chen, Shupeng,Xu, Yujuan,Gu, Qingqing. 2023

[8]Effect of salt-induced supercooling stability on the quality of chicken breast during supercooled storage. Yang, Yiping,Lin, Hengxun,Chen, Yong,Cui, Liye,Li, Hongliang,Xia, Shuangmei,Zhang, Chunhui,Huang, Junrong,Zhang, Hui,He, Jiansheng,Sun, Xuemei,Li, Xia. 2024

[9]Genome-wide investigation of the genes involved in nicotine metabolism in Pseudomonas putida J5 by Tn5 transposon mutagenesis. Xia, Zhenyuan,Lei, Liping,Zhang, Wei,Liu, Xingzhong,Wei, Hai-Lei.

[10]Water use efficiency, yield and quality of tobacco (Nicotiana tabacum L.) using negative pressure irrigation. Pingguo Yang,Patrick J. Drohan,Huai Yu Long,Miao Yang,Yun Bian,Erdeng Ma. 2022

[11]Exposure to nicotine regulates prostaglandin E2 secretion and autophagy of granulosa cells to retard follicular maturation in mammals. Zhou X.,He Y.,Quan H.,Yang J.,Li S.,Jiang Y.,Li J.,Yuan X.. 2024

[12]Transcription factors NtNAC028 and NtNAC080 form heterodimers to regulate jasmonic acid biosynthesis during leaf senescence in Nicotiana tabacum. Lu, Mingyue,Fu, Boyang,Meng, Xiao,Jia, Tiantian,Lu, Xiaoyue,Yang, Chaosha,Li, Ke,Yin, Pengcheng,Guo, Yongfeng,Li, Wei,Chi, Jina,Wang, Geng,Zhou, Chunjiang. 2024

[13]Effects of different proportions of fruit tree branches on nicotine content and microbial diversity during composting of tobacco waste. Xiaoping Zhu,Jiali Yuan,Haoli Qu,Fuen Hou,Chunlong Mao,Jun Lei,Xiuli Cao,Lei Li. 2024

[14]Optimization Of Fish Quality By E.valuation Of Total Volatile B asic Nitrogen (Tvb-N) And Texture Profile Analysis (Tpa) By Near-Infrared (Nir) Hyperspectral Imaging. Zhao, Junbo,Zhang, Yituo,Wang, Xue,Shan, Jiajia,Han, Shuqing. 2019

[15]Identification Of Adulterated Cooked Millet F.lour With Hyperspectral Imaging A nalysis. Xuan, Guantao,Shao, Yuanyuan,Shao, Yuanyuan,Hu, Zhichao,Gao, Xuemei. 2018

[16]Early Detection Of Aspergillus Parasiticus I.nfection In Maize Kernels U sing Near-Infrared Hyperspectral Imaging And Multivariate Data Analysis. Wang, Wei,Zhao, Xin,Li, Chunyang,Chu, Xuan,Kimuli, Daniel. 2017

[17]Identification of Pummelo Cultivars Based on Hyperspectral Imaging Technology. Li Xun-lan,Li Xun-lan,Yi Shi-lai,He Shao-lan,Lu Qiang,Zheng Yong-qiang,Deng Lie,Yi Shi-lai,He Shao-lan,Lu Qiang,Zheng Yong-qiang,Deng Lie. 2015

[18]Prediction of nitrogen and phosphorus contents in citrus leaves based on hyperspectral imaging. Liu Yanli,Liu Yanli,Lyu Qiang,He Shaolan,Yi Shilai,Liu Xuefeng,Xie Rangjin,Zheng Yongqiang,Deng Lie. 2015

[19]Study on Varieties Identification of Kentucky Bluegrass Using Hyperspectral Imaging and Discriminant Analysis. Xiao Bo,Liang Xiao-hong,Zhang Li-juan,Han Lie-bao,Xiao Bo,Han Lie-bao,Mao Wen-hua. 2012

[20]Research Process on Hyperspectral Imaging Detection Technology for the Quality and Safety of Grain and Oils. Yu Hong-wei,Wang Qiang,Liu Li,Shi Ai-min,Hu Hui,Liu Hong-zhi. 2016

作者其他论文 更多>>