数字农科院2.0

A novel dual-branch spatial-spectral attention fusion model and method: A case study for the detection of nicotine content in tobacco leaves

文献类型： 外文期刊

作者： Fukang Xing;Rongguang Zhu;Shichang Wang;Lingfeng Meng;Fujia Dong;Songfeng Wang;Jie Ren;Zongxiu Bai;Yapeng Kang

作者机构：

关键词： Attention mechanism;Hyperspectral imaging;Information fusion;Nicotine;Transformer

期刊名称： Computers and Electronics in Agriculture

ISSN： 0168-1699

年卷期： 2025 年 236 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Hyperspectral imaging (HSI) is a powerful tool for crop phenotypic component analysis, but developing efficient collaborative extraction and modeling methods for image and spectral features is a challenge. This study proposed a novel spatial-spectral fusion detection method for nicotine content utilizing hyperspectral imaging (HSI) and deep learning. Spectra of different regions and multi-channel images extracted by two-dimensional correlation analysis (2D-COS) were employed as inputs. A dual-branch spatial-spectral attention fusion model (DSSAM) was developed to enhance the expression ability of different modal information. Among them, two branches designed based on the residual module were used to extract spatial and spectral features, respectively. For the spectral branch, a multi-region spectral attention encoder (MSAE) was added to dynamically adjust the weights of the spectrum across leaf regions. For the spatial branch, a swin window attention (SWA) module was introduced to improve local feature extraction and spatial structure learning. The results demonstrated that MSAE and SWA could improve the spatial-spectral information fusion ability of the DSSAM. Compared with the dual-branch model without the attention modules, the coefficient of determination (R2) and relative prediction deviation (RPD) of the DSSAM model on the test set increased by 7.85% and 2.64%, respectively, and the Root Mean Square Error (RMSE) decreased by 39.29%. In addition, the DSSAM outperformed traditional chemometric and single-modal models, with a R2 of 0.893, a RMSE of 0.289, and a RPD of 3.054. These findings provide a valuable approach for the quality nondestructive detection of cured tobacco leaves and other crop phenotypic components.

分类号：

  • 相关文献

[1]Information fusion of hyperspectral imaging and self-developed electronic nose for evaluating the degree of black tea fermentation. Zhu, Fengle,Yao, Huan,Shen, Yuecheng,Zhang, Yuqian,Li, Xiaoli,Shi, Jiang,Zhao, Zhangfeng. 2024

[2]Fusing band and feature attention in CNN-LSTM: A dual-attention framework for Hyperspectral-based precise prediction of nicotine levels in cured tobacco leaves. Fukang Xing,Chengzong Dai,Lingfeng Meng,Songfeng Wang,Jie Ren,Rongguang Zhu,Kesu Wei. 2025

[3]Enhanced detection of Aspergillus flavus in peanut kernels using a multi-scale attention transformer (MSAT): Advancements in food safety and contamination analysis. Zhen Guo,Jing Zhang,Haifang Wang,Haowei Dong,Shiling Li,Xijun Shao,Jingcheng Huang,Xiang Yin,Qi Zhang,Yemin Guo,Xia Sun,Ibrahim Darwish. 2024

[4]Non-destructive viability detection of naturally-aged large-sample rice seeds using hyperspectral imaging and deep learning. Hubo Xu,Fei Li,Ziqiang Wang,Wei Zhang,Hui Li,Xingyu Xia,Chunmei Li,Xia Xin. 2025

[5]Review of the field environmental sensing methods based on multi-sensor information fusion technology. Yuanyuan Zhang,Bin Zhang,Cheng Shen,Haolu Liu,Jicheng Huang,Kunpeng Tian,Zhong Tang. 2024

[6]番石榴实蝇性别决定基因Bcotra和Bcotra-2的克隆、序列特征及表达分析. 武强,和丹阳,张桂芬,李建伟,万方浩. 2015

[7]基于卷积神经网络与注意力机制的高光谱图像分类. 高玉鹏,闫伟红,潘新. 2024

[8]融合Transformer和LSTM的蓝莓根区土壤含水量预测模型. 王亿,曹姗姗,孙伟,胡博,古丽米拉·克孜尔别克,孔繁涛. 2024

[9]基于RT-WEDT的麦穗检测与计数方法. 李婕,杨子豪,郑权,乔江伟,涂静敏. 2024

[10]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.

[11]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

[12]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

[13]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

[14]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

[15]FE-TCM: Filter-Enhanced Transformer Click Model for Web Search. Yingfei Wang,Jianping Liu,Jian Wang,Xiaofeng Wang,Meng Wang,Xintao Chu. 2023

[16]A Topicality Relevance-Aware Intent Model for Web Search. Wang, Meng,Liu, Jianping,Wang, Jian,Wang, Yingfei,Chu, Xintao. 2023

[17]Protein-protein interaction and site prediction using transfer learning. Tuoyu Liu,Han Gao,Xiaopu Ren,Guoshun Xu,Bo Liu,Ningfeng Wu,Huiying Luo,Yuan Wang,Tao Tu,Bin Yao,Feifei Guan,Yue Teng,Huoqing Huang,Jian Tian. 2023

[18]TransVAE-DTA: Transformer and variational autoencoder network for drug-target binding affinity prediction. Zhou C.,Li Z.,Song J.,Xiang W.. 2024

[19]AECA-FBMamba: A Framework with Adaptive Environment Channel Alignment and Mamba Bridging Semantics and Details. Xin Chai,Wenrong Zhang,Zhaoxin Li,Ning Zhang,Xiujuan Chai. 2025

[20]DeepAT: A Deep Learning Wheat Phenotype Prediction Model Based on Genotype Data. Jiale Li,Zikang He,Guomin Zhou,Shen Yan,Jianhua Zhang. 2024

作者其他论文 更多>>