Deep convolutional neural networks for Raman spectrum recognition: a unified solution. Issue 21 (10th October 2017)

• Record Type: Journal Article
• Authors: Liu, Jinchao; Osadchy, Margarita; Ashton, Lorna; Foster, Michael; Solomon, Christopher J.; Gibson, Stuart J.
• Is Part Of: Analyst. Volume 142:Issue 21(2017)
• Page Start: 4067
• Page End: 4074
• Publication Date: 2017-10-10
• Subjects: Chemistry, Analytic -- Periodicals; 543
• DOI: 10.1039/c7an01371j
• Languages: English
• ISSNs: 0003-2654

Abstract

Abstract : Classification of unprocessed Raman spectra using a convolutional neural network. Abstract : Machine learning methods have found many applications in Raman spectroscopy, especially for the identification of chemical species. However, almost all of these methods require non-trivial preprocessing such as baseline correction and/or PCA as an essential step. Here we describe our unified solution for the identification of chemical species in which a convolutional neural network is trained to automatically identify substances according to their Raman spectrum without the need for preprocessing. We evaluated our approach using the RRUFF spectral database, comprising mineral sample data. Superior classification performance is demonstrated compared with other frequently used machine learning algorithms including the popular support vector machine method.