摘要
With the development of Raman spectroscopy and the expansion of its application domains, conventional methods for spectral data analysis have manifested many limitations. Exploring new approaches to facilitate Raman spectroscopy and analysis has become an area of intensifying focus for research. It has been demonstrated that machine learning techniques can more efficiently extract valuable information from spectral data, creating unprecedented opportunities for analytical science. This paper outlines traditional and more recently developed statistical methods that are commonly used in machine learning (ML) and ML-algorithms for different Raman spectroscopy-based classification and recognition applications. The methods include Principal Component Analysis, K-Nearest Neighbor, Random Forest, and Support Vector Machine, as well as neural network-based deep learning algorithms such as Artificial Neural Networks, Convolutional Neural Networks, etc. The bulk of the review is dedicated to the research advances in machine learning applied to Raman spectroscopy from several fields, including material science, biomedical applications, food science, and others, which reached impressive levels of analytical accuracy. The combination of Raman spectroscopy and machine learning offers unprecedented opportunities to achieve high throughput and fast identification in many of these application fields. The limitations of current studies are also discussed and perspectives on future research are provided.
学科与关键词
- Application of machine learning-assisted surface-enhanced Raman spectroscopy in medical laboratories: Principles, opportunities, and challengesTang, Jia-Wei; Yuan, Quan; Zhang, Li; Marshall, Barry J.; Tay, Alfred Chin Yen*; Wang, Liang*TrAC - Trends in Analytical Chemistry, 2025, 184: 118135.
- Application Progress of Chemometrics and Deep Learning Methods in Raman Spectroscopy Signal ProcessingZhou, Can-Ru; Wang, Zhe-Tao; Yang, Si-Wei; Xie, Yu-Hao; Liang, Pei*; Cao, Dan; Chen, Qiang*CHINESE JOURNAL OF ANALYTICAL CHEMISTRY, 2023, 51(8): 1232-1242.被引 2
- Pushing the Limits of Surface-Enhanced Raman Spectroscopy (SERS) with Deep Learning: Identification of Multiple Species with Closely Related Molecular StructuresLebrun, Alexis; Fortin, Hubert; Fontaine, Nicolas; Fillion, Daniel; Barbier, Olivier; Boudreau, Denis*Applied Spectroscopy, 2022, 76(5): 609-619.被引 9
