Abstract
[Objective] To achieve rapid traceability detection of soybeans from different geographical origins. [Methods] A novel method for rapid soybean origin traceability is proposed based on the fusion of information from electronic tongue and electronic eye. The electronic tongue and electronic eye are used to collect taste fingerprint and visual image information, respectively, from soybeans of different origins. To address the differences between the temporal sequence features of electronic tongue signals and the spatial image features of electronic eye data, Informer and Swin Transformer are respectively employed to extract key features from the two types of data. A dual -modal feature interaction module is designed to perform deep interaction between the two types of features, thereby obtaining multi -scale inter -layer mutual information. A cross -attention fusion module is then applied to integrate the inter -layer mutual information, enabling efficient cross -modal information fusion and classification recognition. [Results] The proposed model has good discriminative ability for soybeans from different origins, achieving an accuracy of 98.33%, precision of 98.34%, recall of 98.33%, and F1-Score of 0.983 3. [Conclusion] This method provides an efficient and reliable new approach for the rapid traceability detection of soybean geographical origin.
Publication Date
10-21-2026
First Page
65
Last Page
73
DOI
10.13652/j.spjx.1003.5788.2025.81005
Recommended Citation
Xin, Li; Zhiqiang, Wang; Tianrui, Han; and Suchao, Xu
(2026)
"Geographical origin tracing of soybeans using electronic tongue and electronic eye combined with multi-level information fusion based on Informer-Swin Transformer,"
Food and Machinery: Vol. 42:
Iss.
9, Article 8.
DOI: 10.13652/j.spjx.1003.5788.2025.81005
Available at:
https://www.ifoodmm.cn/journal/vol42/iss9/8
References
[1] 张兴政,刘鑫,黄浩捷,等.大豆 ACO家族基因鉴定、生物信息学分析及盐胁迫下表达模式分析 [J].大豆科学,2025,44(3):27-38.Zhang X Z,Liu X,Huang H J,et al.Identification,bioinformatics analysis and expression pattern analysis of ACO family gene in Glycine max L.under salt stress [J].Soybean Science,2025,44(3):27-38.
[2] Huang Z M,Xin J X,Sun S S,et al.Rapid identification of adulteration in edible vegetable oils based on low-field nuclear magnetic resonance relaxation fingerprints [J].Foods,2021,10(12):3 068.
[3] 雷渊雄,夏阿林,黄炜,等.基于近红外光谱结合化学计量学的转基因大豆产地判别 [J].食品与发酵工业,2022,48(12):275-280.Lei Y X,Xia A L,Huang W,et al.Origin discrimination of transgenic soybean based on near infrared spectroscopy and chemometrics [J].Food and Fermentation Industries,2022,48(12):275-280.
[4] 苗辰.超高效液相色谱法测量大豆中大豆异黄酮含量 [J].食品安全导刊,2025 (15):55-57.Miao C.Determination of soybean isoflavones in soybeans by ultra high performance liquid chromatography [J].China Food Safety Magazine,2025 (15):55-57.
[5] 刘川正,马景余,白雪瑞,等.基于电子舌和电子鼻结合 CNN-Transformer 模型的绿茶种类识别 [J].食品与机械,2024,40(6):34-42,52.Liu C Z,Ma J Y,Bai X R,et al.Green tea species recognition based on electronic tongue and electronic nose combined with CNN-Transformer model [J].Food & Machinery,2024,40(6):34-42,52.
[6] 马泽亮,刘雅倩,程琦峰,等.电子鼻和电子舌结合 LSTM-AM-M 1DCNN检测枸杞产地 [J].食品与机械,2024,40(12):51-58.Ma Z L,Liu Y Q,Cheng Q F,et al.Detection of the origin of wolfberry based on electronic nose and electronic tongue combined with LSTM-AM-M 1DCNN [J].Food & Machinery,2024,40(12):51-58.
[7] Cetó X,Del Valle M.Electronic tongue applications for wastewater and soil analysis [J].iScience,2022,25(5):104304.
[8] Wang Y J,Liu Y,Cui Q Q,et al.Monitoring the withering condition of leaves during black tea processing via the fusion of electronic eye (E-eye ),colorimetric sensing array (CSA ),and micro-near-infrared spectroscopy (NIRS ) [J].Journal of Food Engineering,2021,300:110534.
[9] 查天,张承吉,朱磊,等.基于电子眼和电子鼻的不同包装片烟醇化品质差异分析 [J].烟草科技,2024,57(12):15-24.Zha T,Zhang C J,Zhu L,et al.Differences in aging quality of tobacco strips packaged by different methods based on electronic eyes and electronic noses [J].Tobacco Science & Technology,2024,57(12):15-24.
[10] Orlandi G,Calvini R,Foca G,et al.Data fusion of electronic eye and electronic tongue signals to monitor grape ripening [J].Talanta,2019,195:181-189.
[11] Zhou Y F,Zhang Z L,He Y,et al.Integration of electronic nose,electronic tongue,and colorimeter in combination with chemometrics for monitoring the fermentation process of Tremella fuciformis [J].Talanta,2024,274:126006.
[12] Li Y H,Daho M E H,Conze P H,et al.A review of deep learning-based information fusion techniques for multimodal medical image classification [J].Computers in Biology and Medicine,2024,177:108635.
[13] 金鑫宁,刘铭,桑恒亮,等.基于电子舌和电子眼结合改进MobileNetv 3的黄芪快速溯源检测 [J].食品与机械,2023,39(6):37-47.Jin X N,Liu M,Sang H L,et al.Fast traceability detection of Astragalus membranaceus based on the combination of electronic tongue and electronic eye to improve MobileNetv 3[J].Food & Machinery,2023,39(6):37-47.
[14] Yang Z W,Gao J Y,Wang S C,et al.Synergetic application of E-tongue and E-eye based on deep learning to discrimination of Pu-erh tea storage time [J].Computers and Electronics in Agriculture,2021,187:106297.
[15] Wang S C,Zhang Q,Liu C Z,et al.Synergetic application of an E-tongue,E-nose and E-eye combined with CNN models and an attention mechanism to detect the origin of black pepper[J].Sensors and Actuators A:Physical,2023,357:114417.
[16] Peng Z L,Huang W,Gu S Z,et al.Conformer:local features coupling global representations for visual recognition [C]// Proceedings of the IEEE/CVF International Conference on Computer Vision.Montreal,Canada:IEEE,2021:367-376.
[17] 蒋雷,汤海林,陈瑜瑾.基于 Transformer 模型的自然语言处理研究综述 [J].现代计算机,2024,30(14):31-35.Jiang L,Tang H L,Chen Y J.A review of natural language processing research based on Transformer model [J].Modern Computer,2024,30(14):31-35.
[18] 赵小芬,彭朋.基于多模态视听融合的 Transformer 语音识别算法研究 [J].传感器与微系统,2025,44(2):48-52.Zhao X F,Peng P.Research on Transformer speech recognition algorithm based on multimodal audio-visual fusion [J].Transducer and Microsystem Technologies,2025,44(2):48-52.
[19] Zhou H Y,Zhang S H,Peng J Q,et al.Informer:beyond efficient transformer for long sequence time-series forecasting[J].Proceedings of the AAAI Conference on Artificial Intelligence,2021,35(12):11 106-11 115.
[20] Liu Z,Lin Y T,Cao Y,et al.Swin transformer:hierarchical vision transformer using shifted windows [C]// Proceedings of the IEEE/CVF International Conference on Computer Vision.Montreal,Canada:IEEE,2021:10 012-10 022.
[21] Rao X,Xiao S Y,Li J X,et al.LSBO-NAS:latent space Bayesian optimization for neural architecture search [C]// 2022 4th International Conference on Control and Robotics (ICCR ).Guangzhou:IEEE,2023:22-27.
