Open Access

ARTICLE

Cluster Analysis for IR and NIR Spectroscopy: Current Practices to Future Perspectives

Simon Crase^1,2, Benjamin Hall², Suresh N. Thennadil^3,*

1 College of Engineering, IT & Environment, Charles Darwin University, Casuarina, NT 0810, Australia
2 Defence Science and Technology Group, Edinburgh, 5111, Australia
3 Energy and Resources Institute, Charles Darwin University, Casuarina, NT 0810, Australia

* Corresponding Author: Suresh N. Thennadil. Email:

Computers, Materials & Continua 2021, 69(2), 1945-1965. https://doi.org/10.32604/cmc.2021.018517

Received 10 March 2021; Accepted 11 April 2021; Issue published 21 July 2021

Abstract

Supervised machine learning techniques have become well established in the study of spectroscopy data. However, the unsupervised learning technique of cluster analysis hasn’t reached the same level maturity in chemometric analysis. This paper surveys recent studies which apply cluster analysis to NIR and IR spectroscopy data. In addition, we summarize the current practices in cluster analysis of spectroscopy and contrast these with cluster analysis literature from the machine learning and pattern recognition domain. This includes practices in data pre-processing, feature extraction, clustering distance metrics, clustering algorithms and validation techniques. Special consideration is given to the specific characteristics of IR and NIR spectroscopy data which typically includes high dimensionality and relatively low sample size. The findings highlighted a lack of quantitative analysis and evaluation in current practices for cluster analysis of IR and NIR spectroscopy data. With this in mind, we propose an analysis model or workflow with techniques specifically suited for cluster analysis of IR and NIR spectroscopy data along with a pragmatic application strategy.

---

Keywords

---

Citations