Automatic hierarchical model builder
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Automatic hierarchical model builder. / Marchi, Lorenzo; Krylov, Ivan; Roginski, Robert T.; Wise, Barry; Di Donato, Francesca; Nieto-Ortega, Sonia; Pereira, José Francielson Q.; Bro, Rasmus.
In: Journal of Chemometrics, Vol. 36, No. 12, e3455, 2022.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Automatic hierarchical model builder
AU - Marchi, Lorenzo
AU - Krylov, Ivan
AU - Roginski, Robert T.
AU - Wise, Barry
AU - Di Donato, Francesca
AU - Nieto-Ortega, Sonia
AU - Pereira, José Francielson Q.
AU - Bro, Rasmus
N1 - Funding Information: The contribution of Ivan Krylov to the study was partially funded by Russian Foundation for Basic Research (RFBR), project number 20‐33‐90280, and Danish Government Scholarship under the Cultural Agreements. Publisher Copyright: © 2022 The Authors. Journal of Chemometrics published by John Wiley & Sons Ltd.
PY - 2022
Y1 - 2022
N2 - When building classification models of complex systems with many classes, the traditional chemometric approaches such as discriminant analysis or soft independent modeling of class analogy often fail. Some people resort to advanced deep neural network, but this is only an option if there is access to very many samples. Another alternative often used is to build hierarchical models where subclasses are sort of peeled off one or a few at a time. Such approaches often outperform classical classification as well as deep neural network on small multi-class problems. The downside though is that it is very cumbersome to build such hierarchies of models. It requires substantial work of a skilled person. In this paper, we develop a fully automated approach for building hierarchical models and test the performance on a number of classification problems.
AB - When building classification models of complex systems with many classes, the traditional chemometric approaches such as discriminant analysis or soft independent modeling of class analogy often fail. Some people resort to advanced deep neural network, but this is only an option if there is access to very many samples. Another alternative often used is to build hierarchical models where subclasses are sort of peeled off one or a few at a time. Such approaches often outperform classical classification as well as deep neural network on small multi-class problems. The downside though is that it is very cumbersome to build such hierarchies of models. It requires substantial work of a skilled person. In this paper, we develop a fully automated approach for building hierarchical models and test the performance on a number of classification problems.
KW - automation
KW - classification
KW - hierarchical
U2 - 10.1002/cem.3455
DO - 10.1002/cem.3455
M3 - Journal article
AN - SCOPUS:85142277908
VL - 36
JO - Journal of Chemometrics
JF - Journal of Chemometrics
SN - 0886-9383
IS - 12
M1 - e3455
ER -
ID: 327671914