Home > Research > Publications & Outputs > Deep convolutional neural networks for Raman sp...

Research

Associated organisational unit

Electronic data

  • 2017Liu_AuthorAcceptedManuscript

    Rights statement: © The Royal Society of Chemistry 2017

    Accepted author manuscript, 1.05 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Deep convolutional neural networks for Raman spectrum recognition: a unified solution

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Deep convolutional neural networks for Raman spectrum recognition: a unified solution. / Liu, Jinchao; Osadchy, Margarita; Ashton, Lorna et al.
In: Analyst, Vol. 142, No. 21, 4067, 07.11.2017.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Liu, J, Osadchy, M, Ashton, L, Foster, M, Solomon, CJ & Gibson, SJ 2017, 'Deep convolutional neural networks for Raman spectrum recognition: a unified solution', Analyst, vol. 142, no. 21, 4067. https://doi.org/10.1039/C7AN01371J

APA

Liu, J., Osadchy, M., Ashton, L., Foster, M., Solomon, C. J., & Gibson, S. J. (2017). Deep convolutional neural networks for Raman spectrum recognition: a unified solution. Analyst, 142(21), Article 4067. https://doi.org/10.1039/C7AN01371J

Vancouver

Liu J, Osadchy M, Ashton L, Foster M, Solomon CJ, Gibson SJ. Deep convolutional neural networks for Raman spectrum recognition: a unified solution. Analyst. 2017 Nov 7;142(21):4067. Epub 2017 Sept 28. doi: 10.1039/C7AN01371J

Author

Liu, Jinchao ; Osadchy, Margarita ; Ashton, Lorna et al. / Deep convolutional neural networks for Raman spectrum recognition : a unified solution. In: Analyst. 2017 ; Vol. 142, No. 21.

Bibtex

@article{6b7fa4597a3e48859ea66394c1c1dbb2,
title = "Deep convolutional neural networks for Raman spectrum recognition: a unified solution",
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.",
author = "Jinchao Liu and Margarita Osadchy and Lorna Ashton and Michael Foster and Solomon, {Christopher J.} and Gibson, {Stuart J.}",
note = "{\textcopyright} The Royal Society of Chemistry 2017",
year = "2017",
month = nov,
day = "7",
doi = "10.1039/C7AN01371J",
language = "English",
volume = "142",
journal = "Analyst",
issn = "0003-2654",
publisher = "Royal Society of Chemistry",
number = "21",

}

RIS

TY - JOUR

T1 - Deep convolutional neural networks for Raman spectrum recognition

T2 - a unified solution

AU - Liu, Jinchao

AU - Osadchy, Margarita

AU - Ashton, Lorna

AU - Foster, Michael

AU - Solomon, Christopher J.

AU - Gibson, Stuart J.

N1 - © The Royal Society of Chemistry 2017

PY - 2017/11/7

Y1 - 2017/11/7

N2 - 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.

AB - 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.

U2 - 10.1039/C7AN01371J

DO - 10.1039/C7AN01371J

M3 - Journal article

VL - 142

JO - Analyst

JF - Analyst

SN - 0003-2654

IS - 21

M1 - 4067

ER -