发表机构
Manchester Metropolitan University（曼彻斯特城市大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对低成本MOX气体传感器信号漂移等问题，提出LDAC-Net网络，在SmellNet等数据集上的识别准确率优于现有方法，证明可学习预处理比固定差分更有效。
AI 中文摘要
基于低成本金属氧化物（MOX）气体传感器的便携式电子鼻系统为气体和气味识别提供了实用解决方案，但其信号会受到缓慢化学瞬变、传感器偏移漂移、尺度变化及跨通道相关性的影响。现有处理流程通常使用固定一阶时间差分（FOTD），该方法需要手动选择滞后量，且可能丢弃有用的响应信息。本文提出LDAC-Net，这是一种端到端可学习的多滞后差分注意力-卷积网络，可直接处理多通道MOX信号。其可学习差分特征增强前端结合了窗口条件统计仿射归一化（用于补偿窗口特定的偏移和尺度变化）与可学习多滞后差分（用于对多个滞后的时间差分进行加权和组合）；随后，紧凑的注意力-卷积主干网络对局部瞬变和长程时间依赖关系进行建模。在50类SmellNet-Base任务上，LDAC-Net达到68.2%的top-1准确率，比采用FOTD预处理的最优对比模型高出约14个百分点，比原始输入Transformer高出30多个百分点。 ablation研究证实了所提出两个组件的贡献。该表示还可迁移至SmellNet-Mixtures，将准确率从45.4%提升至50.5%，并在强长期漂移下泛化至62通道的eNose-Drift基准，达到70.6%的top-1准确率和69.6%的macro-F1。这些结果比采用数据集微调FOTD预处理的最优对比模型分别高出8.0和3.0个百分点，表明对于低成本MOX气体传感器识别，可学习的、感知传感器的预处理比固定手工设计的差分方法更有效。
英文摘要
Portable electronic-nose systems based on low-cost metal-oxide (MOX) gas sensors offer a practical solution for gas and odour recognition, but their signals are affected by slow chemical transients, drifting sensor offsets, scale variation, and cross-channel correlations. Existing pipelines commonly use fixed first-order temporal differencing (FOTD), which requires a manually selected lag and may discard useful response information. We propose LDAC-Net, an end-to-end learnable multi-lag differencing attention-convolution network that operates directly on multi-channel MOX signals. Its learnable differential feature enhancement front-end combines window-conditioned statistical affine normalisation, which compensates for window-specific offset and scale variation, with learnable multi-lag differencing, which weights and combines temporal differences across multiple lags. A compact attention-convolution backbone subsequently models local transients and longer-range temporal dependencies. On the 50-class SmellNet-Base task, LDAC-Net achieves 68.2% top-1 accuracy, exceeding the best FOTD-preprocessed comparison model by approximately 14 percentage points and the raw-input Transformer by more than 30 points. Ablation studies confirm the contributions of both proposed components. The representation also transfers to SmellNet-Mixtures, improving accuracy from 45.4% to 50.5%, and generalises to the 62-channel eNose-Drift benchmark under strong long-term drift, achieving 70.6% top-1 accuracy and 69.6% macro-F1. These results outperform the best comparison model with dataset-retuned FOTD preprocessing by 8.0 and 3.0 points, respectively, demonstrating that learnable, sensor-aware preprocessing is more effective than fixed handcrafted differencing for low-cost MOX gas-sensor recognition.
