Shizhuang Weng, Cong Wang, Rui Zhu, Yehang Wu, Rui Yang, Ling Zheng, Pan Li, Jinling Zhao, Shouguo Zheng
Surface-enhanced Raman Spectroscopy (SERS) is extensively implemented in drug detection due to its sensitivity and non-destructive nature. Deep learning methods, which are represented by convolutional neural network (CNN), have been widely applied in identifying the spectra from SERS for powerful learning ability. However, the local receptive field of CNN limits the feature extraction of sequential spectra for suppressing the analysis results. In this study, a hybrid Transformer network, TMNet, was developed to identify SERS spectra by integrating the Transformer encoder and the multi-layer perceptron...
April 16, 2024: Spectrochimica Acta. Part A, Molecular and Biomolecular Spectroscopy