Rights statement: This is an Accepted Manuscript of an article published by Taylor & Francis in Applied Spectroscopy Reviews on 23/12/2020, available online: https://www.tandfonline.com/doi/abs/10.1080/05704928.2020.1859525
Accepted author manuscript, 1.19 MB, PDF document
Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Applications of machine learning in spectroscopy
AU - Meza Ramirez, C.A.
AU - Greenop, M.
AU - Ashton, L.
AU - Rehman, I.U.
N1 - This is an Accepted Manuscript of an article published by Taylor & Francis in Applied Spectroscopy Reviews on 23/12/2020, available online: https://www.tandfonline.com/doi/abs/10.1080/05704928.2020.1859525
PY - 2021/9/30
Y1 - 2021/9/30
N2 - The way to analyze data in spectroscopy has changed substantially. At the same time, data science has evolved to the point where spectroscopy can find space to be housed, adapted and be functional. The integration of the two sciences has introduced a knowledge gap between data scientists who know about advanced machine learning techniques and spectroscopists who have a solid background in chemometrics. To reach a symbiosis, the knowledge gap requires bridging. This review article focuses on introducing data science subjects to non-specialist spectroscopists, or those unfamiliar with the subject. The article will explain concepts that are covered in machine learning, such as supervised learning, unsupervised learning, deep learning, and most importantly, the difference between machine learning and artificial intelligence. This article also includes examples of published spectroscopy research, in which some of the concepts explained here are applied. Machine learning together with spectroscopy can provide a useful, fast, and efficient tool to analyze samples of interest both for industrial and research purposes. © 2020 Taylor & Francis Group, LLC.
AB - The way to analyze data in spectroscopy has changed substantially. At the same time, data science has evolved to the point where spectroscopy can find space to be housed, adapted and be functional. The integration of the two sciences has introduced a knowledge gap between data scientists who know about advanced machine learning techniques and spectroscopists who have a solid background in chemometrics. To reach a symbiosis, the knowledge gap requires bridging. This review article focuses on introducing data science subjects to non-specialist spectroscopists, or those unfamiliar with the subject. The article will explain concepts that are covered in machine learning, such as supervised learning, unsupervised learning, deep learning, and most importantly, the difference between machine learning and artificial intelligence. This article also includes examples of published spectroscopy research, in which some of the concepts explained here are applied. Machine learning together with spectroscopy can provide a useful, fast, and efficient tool to analyze samples of interest both for industrial and research purposes. © 2020 Taylor & Francis Group, LLC.
KW - artificial intelligence
KW - chemometrics
KW - data science
KW - Infrared and Raman spectroscopy
KW - Machine learning
KW - Data Science
KW - Deep learning
KW - Industrial research
KW - Chemometrics
KW - Knowledge gaps
KW - Machine learning techniques
KW - Research purpose
KW - Spectroscopy research
KW - Learning systems
U2 - 10.1080/05704928.2020.1859525
DO - 10.1080/05704928.2020.1859525
M3 - Journal article
VL - 56
SP - 733
EP - 763
JO - APPLIED SPECTROSCOPY REVIEWS
JF - APPLIED SPECTROSCOPY REVIEWS
SN - 0570-4928
IS - 8-10
ER -