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

作     者：Simon Crase Benjamin Hall Suresh N.Thennadil 

作者机构：College of EngineeringIT&EnvironmentCharles Darwin UniversityCasuarinaNT 0810Australia Defence Science and Technology GroupEdinburgh5111Australia Energy and Resources InstituteCharles Darwin UniversityCasuarinaNT 0810Australia 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2021年第69卷第11期

页      面：1945-1965页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This research is supported by the Commonwealth of Australia as represented by the Defence Science and Technology Group of the Department of Defence and by an Australian Government Research Training Program(RTP)Scholarship 

主　　题：Chemometrics cluster analysis Fourier transform infrared spectroscopy machine learning near infrared spectroscopy unsupervised learning 

摘      要：Supervised machine learning techniques have become well established in the study of spectroscopy ***,the unsupervised learning technique of cluster analysis hasn’t reached the same level maturity in chemometric *** paper surveys recent studies which apply cluster analysis to NIR and IR spectroscopy *** 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 *** includes practices in data pre-processing,feature extraction,clustering distance metrics,clustering algorithms and validation *** consideration is given to the specific characteristics of IR and NIR spectroscopy data which typically includes high dimensionality and relatively low sample *** findings highlighted a lack of quantitative analysis and evaluation in current practices for cluster analysis of IR and NIR spectroscopy *** 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.