TY - JOUR
T1 - Benchmark and application of unsupervised classification approaches for univariate data
AU - El Abbassi, Maria
AU - Overbeck, Jan
AU - Braun, Oliver
AU - Calame, Michel
AU - van der Zant, Herre S.J.
AU - Perrin, Mickael L.
PY - 2021
Y1 - 2021
N2 - Unsupervised machine learning, and in particular data clustering, is a powerful approach for the analysis of datasets and identification of characteristic features occurring throughout a dataset. It is gaining popularity across scientific disciplines and is particularly useful for applications without a priori knowledge of the data structure. Here, we introduce an approach for unsupervised data classification of any dataset consisting of a series of univariate measurements. It is therefore ideally suited for a wide range of measurement types. We apply it to the field of nanoelectronics and spectroscopy to identify meaningful structures in data sets. We also provide guidelines for the estimation of the optimum number of clusters. In addition, we have performed an extensive benchmark of novel and existing machine learning approaches and observe significant performance differences. Careful selection of the feature space construction method and clustering algorithms for a specific measurement type can therefore greatly improve classification accuracies.
AB - Unsupervised machine learning, and in particular data clustering, is a powerful approach for the analysis of datasets and identification of characteristic features occurring throughout a dataset. It is gaining popularity across scientific disciplines and is particularly useful for applications without a priori knowledge of the data structure. Here, we introduce an approach for unsupervised data classification of any dataset consisting of a series of univariate measurements. It is therefore ideally suited for a wide range of measurement types. We apply it to the field of nanoelectronics and spectroscopy to identify meaningful structures in data sets. We also provide guidelines for the estimation of the optimum number of clusters. In addition, we have performed an extensive benchmark of novel and existing machine learning approaches and observe significant performance differences. Careful selection of the feature space construction method and clustering algorithms for a specific measurement type can therefore greatly improve classification accuracies.
UR - http://www.scopus.com/inward/record.url?scp=85102515014&partnerID=8YFLogxK
U2 - 10.1038/s42005-021-00549-9
DO - 10.1038/s42005-021-00549-9
M3 - Article
AN - SCOPUS:85102515014
SN - 2399-3650
VL - 4
JO - Communications Physics
JF - Communications Physics
IS - 1
M1 - 50
ER -