Xie Zhuoheng, Tian Yao, Jia Pengfei
School of Mechanical Electrical and Information Engineering, Shandong University, Weihai 264209, China.
School of Future Technology, Xi'an Jiaotong University, Xi'an 710049, China.
Sensors (Basel). 2025 Aug 3;25(15):4780. doi: 10.3390/s25154780.
We propose an advanced electronic nose based on SE-RelationNet for COPD diagnosis with limited breath samples. The model integrates residual blocks, BiGRU layers, and squeeze-excitation attention mechanisms to enhance feature-extraction efficiency. Experimental results demonstrate exceptional performance with minimal samples: in 4-way 1-shot tasks, the model achieves 85.8% mean accuracy (F1-score = 0.852), scaling to 93.3% accuracy (F1-score = 0.931) with four samples per class. Ablation studies confirm that the 5-layer residual structure and single-hidden-layer BiGRU optimize stability (h_F1-score ≤ 0.011). Compared to SiameseNet and ProtoNet, SE-RelationNet shows superior accuracy (>15% improvement in 1-shot tasks). This technology enables COPD detection with as few as one breath sample, facilitating early intervention to mitigate lung cancer risks in COPD patients.
我们提出了一种基于SE-RelationNet的先进电子鼻，用于在呼吸样本有限的情况下诊断慢性阻塞性肺疾病（COPD）。该模型集成了残差块、双向门控循环单元（BiGRU）层和挤压激励注意力机制，以提高特征提取效率。实验结果表明，在样本量极少的情况下，该模型具有卓越的性能：在4分类单样本任务中，该模型平均准确率达到85.8%（F1分数 = 0.852），当每类有四个样本时，准确率提升至93.3%（F1分数 = 0.931）。消融研究证实，5层残差结构和单隐藏层BiGRU优化了稳定性（h_F1分数≤0.011）。与孪生网络（SiameseNet）和原型网络（ProtoNet）相比，SE-RelationNet显示出更高的准确率（在单样本任务中提高超过15%）。这项技术能够仅凭一次呼吸样本就检测出COPD，有助于早期干预，降低COPD患者患肺癌的风险。
