In this Chapter, the state-of-the-art approaches for the classification of multi-way data is presented and discussed. The theoretical basis and applicative guidelines for multilinear (or multi-way) Partial Least Squares Discriminant Analysis (NPLS-DA) and Multi-way Soft Independent Modelling of Class Analogy (NSIMCA) are detailed. Furthermore, two-dimensional linear discriminant analysis (2DLDA) and a proposal for truly multilinear discriminant analysis are illustrated. The truly multi-way methods are compared to unfolding and feature extraction followed by bilinear classification. Practical hints are depicted through discussion of a case of study.
Multi Way Classification / Cocchi, Marina; Li Vigni, Mario; Durante, Caterina. - 3:3.34(2020), pp. 701-721. [10.1016/B978-0-12-409547-2.14590-1]
Multi Way Classification
Cocchi, Marina
;Li Vigni, Mario;Durante, Caterina
2020
Abstract
In this Chapter, the state-of-the-art approaches for the classification of multi-way data is presented and discussed. The theoretical basis and applicative guidelines for multilinear (or multi-way) Partial Least Squares Discriminant Analysis (NPLS-DA) and Multi-way Soft Independent Modelling of Class Analogy (NSIMCA) are detailed. Furthermore, two-dimensional linear discriminant analysis (2DLDA) and a proposal for truly multilinear discriminant analysis are illustrated. The truly multi-way methods are compared to unfolding and feature extraction followed by bilinear classification. Practical hints are depicted through discussion of a case of study.File | Dimensione | Formato | |
---|---|---|---|
MultiwayClassification3.34.pdf
Accesso riservato
Tipologia:
Versione pubblicata dall'editore
Dimensione
3.42 MB
Formato
Adobe PDF
|
3.42 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris