Multi-Scale Feature Attention Network for Polymer Classification using THz Dual-Comb Spectroscopy

基于太赫兹双光梳光谱的聚合物分类多尺度特征注意力网络

Abstract: Reliable polymer identification is essential for ensuring the quality and safety of recycled plastics, yet conventional sorting and spectroscopic techniques often struggle to deliver robust discrimination. 摘要： 可靠的聚合物识别对于确保再生塑料的质量和安全至关重要，然而传统的分类和光谱技术往往难以实现稳健的区分。

Terahertz Dual-Comb Spectroscopy (THz-DCS) offers a promising alternative, providing rapid, high-resolution, and non-destructive measurements. 太赫兹双光梳光谱（THz-DCS）提供了一种有前景的替代方案，能够实现快速、高分辨率且无损的测量。

In this work, we leverage THz-DCS to classify 12 types of polymers, including pure polymers, multilayer films, commercial blends, and biopolymers. 在这项工作中，我们利用 THz-DCS 对 12 种聚合物进行了分类，包括纯聚合物、多层薄膜、商业混合物和生物聚合物。

To handle the complexity of these spectral signals, we propose the Multi-Scale Feature Attention Network (MSFAN), a novel deep learning architecture tailored for THz-DCS data. 为了处理这些光谱信号的复杂性，我们提出了多尺度特征注意力网络（MSFAN），这是一种专为 THz-DCS 数据量身定制的新型深度学习架构。

The framework integrates feature gating for signal recalibration and multi-scale parallel convolutions to capture diverse frequency patterns. 该框架集成了用于信号重校准的特征门控机制，以及用于捕获不同频率模式的多尺度并行卷积。

These features are further refined through cross-feature attention and attention pooling, enabling the model to intrinsically highlight the most informative THz regions. 这些特征通过跨特征注意力和注意力池化进一步优化，使模型能够从本质上突出最具信息量的太赫兹区域。

MSFAN consistently outperforms state-of-the-art models, reaching a classification accuracy of 85.2%. MSFAN 的表现持续优于当前最先进的模型，分类准确率达到了 85.2%。

This study demonstrates the potential of combining THz-DCS with deep learning techniques for effective, scalable, and interpretable polymer classification. 本研究展示了将 THz-DCS 与深度学习技术相结合，实现高效、可扩展且可解释的聚合物分类的潜力。