Chen Jianghai, Ling Jie, Lei Nana, Li Lingqiao
School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin 541004, China.
Sensors (Basel). 2025 Jun 27;25(13):4008. doi: 10.3390/s25134008.
Near-Infrared Spectroscopy (NIRS) analysis technology faces numerous challenges in industrial applications. Firstly, the generalization capability of models is significantly affected by instrumental heterogeneity, environmental interference, and sample diversity. Traditional modeling methods exhibit certain limitations in handling these factors, making it difficult to achieve effective adaptation across different scenarios. Specifically, data distribution shifts and mismatches in multi-scale features hinder the transferability of models across different crop varieties or instruments from different manufacturers. As a result, the large amount of previously accumulated NIRS and reference data cannot be effectively utilized in modeling for new instruments or new varieties, thereby limiting improvements in modeling efficiency and prediction accuracy. To address these limitations, this study proposes a novel transfer learning framework integrating multi-scale network architecture with Balanced Distribution Adaptation (BDA) to enhance cross-instrument compatibility. The key contributions include: (1) RX-Inception multi-scale structure: Combines Xception's depthwise separable convolution with ResNet's residual connections to strengthen global-local feature coupling. (2) Squeeze-and-Excitation (SE) attention: Dynamically recalibrates spectral band weights to enhance discriminative feature representation. (3) Systematic evaluation of six transfer strategies: Comparative analysis of their impacts on model adaptation performance. Experimental results on open corn and pharmaceutical datasets demonstrate that BDSER-InceptionNet achieves state-of-the-art performance on primary instruments. Notably, the proposed Method 6 successfully enables NIRS model sharing from primary to secondary instruments, effectively mitigating spectral discrepancies and significantly improving transfer efficacy.
近红外光谱（NIRS）分析技术在工业应用中面临诸多挑战。首先，模型的泛化能力受到仪器异质性、环境干扰和样本多样性的显著影响。传统建模方法在处理这些因素时存在一定局限性，难以在不同场景下实现有效适配。具体而言，多尺度特征中的数据分布偏移和不匹配阻碍了模型在不同作物品种或不同制造商的仪器之间的可迁移性。因此，大量先前积累的NIRS和参考数据无法在新仪器或新品种的建模中得到有效利用，从而限制了建模效率和预测准确性的提升。为解决这些局限性，本研究提出了一种新颖的迁移学习框架，将多尺度网络架构与平衡分布自适应（BDA）相结合，以增强跨仪器兼容性。主要贡献包括：（1）RX-Inception多尺度结构：将Xception的深度可分离卷积与ResNet的残差连接相结合，以加强全局-局部特征耦合。（2）挤压与激励（SE）注意力：动态重新校准光谱带权重，以增强判别性特征表示。（3）对六种迁移策略的系统评估：对它们对模型适配性能的影响进行比较分析。在开放玉米和药物数据集上的实验结果表明，BDSER-InceptionNet在主要仪器上取得了领先性能。值得注意的是，所提出的方法6成功实现了NIRS模型从主要仪器到次要仪器的共享，有效减轻了光谱差异并显著提高了迁移效果。
