Zhou Wei, Tang Yujun, Qian Ziheng, Wang Junwei, Guo Hanming
College of Optical-Electrical and Computer Engineering, University of Shanghai for Science & Technology Shanghai China
RSC Adv. 2022 Feb 10;12(8):5053-5061. doi: 10.1039/d1ra08804a. eCollection 2022 Feb 3.
Raman spectroscopy has been widely used in various fields due to its unique and superior properties. For achieving high spectral identification speeds and high accuracy, machine learning methods have found many applications in this area, with convolutional neural network-based methods showing great advantages. In this study, we propose a Raman spectral identification method using a deeply-recursive convolutional neural network (DRCNN). It has a very deep network structure (up to 16 layers) for improving performance without introducing more parameters for recursive layers, which eases the difficulty of training. We also propose a recursive-supervision extension to ease the difficulty of training. By testing several different open-source spectral databases, DRCNN has achieved higher prediction accuracies and better performance in transfer learning compared with other CNN-based methods. Superior identification performance is demonstrated, especially by identification, for characteristically similar and indistinguishable spectra.
拉曼光谱因其独特且卓越的特性已在各个领域得到广泛应用。为了实现高光谱识别速度和高精度，机器学习方法在该领域有诸多应用，其中基于卷积神经网络的方法展现出巨大优势。在本研究中，我们提出一种使用深度递归卷积神经网络（DRCNN）的拉曼光谱识别方法。它具有非常深的网络结构（多达16层），用于在不引入更多递归层参数的情况下提高性能，这减轻了训练难度。我们还提出了递归监督扩展以减轻训练难度。通过测试几个不同的开源光谱数据库，与其他基于卷积神经网络的方法相比，DRCNN在迁移学习中取得了更高的预测准确率和更好的性能。特别是在对特征相似且难以区分的光谱进行识别时，展现出了卓越的识别性能。
