In semi-supervised classification, class memberships are learnt from a trustworthy set of units. Despite careful data collection, some labels in the learning set could be unreliable (label noise). Further, a proportion of observations might depart from the main structure of the data (outliers) and new groups may appear in the test set, which were not encountered earlier in the training phase (unobserved classes). Therefore, we present here a robust and adaptive version of the Discriminant Analysis rule, capable of handling situations in which one or more of the aforementioned problems occur. The proposed approach is successfully employed in performing anomaly and novelty detection on geometric features recorded from X-ray photograms of grain kernels from different varieties.

Cappozzo, A., Greselin, F., Murphy, T. (2021). Robust Model-Based Learning to Discover New Wheat Varieties and Discriminate Adulterated Kernels in X-Ray Images. In S. Balzano, G.C. Porzio, R. Salvatore, D. Vistocco, M. Vichi (a cura di), Statistical Learning and Modeling in Data Analysis (pp. 29-36). Springer Science and Business Media Deutschland GmbH [10.1007/978-3-030-69944-4_4].

Robust Model-Based Learning to Discover New Wheat Varieties and Discriminate Adulterated Kernels in X-Ray Images

Cappozzo A.
;
Greselin F.;
2021

Abstract

In semi-supervised classification, class memberships are learnt from a trustworthy set of units. Despite careful data collection, some labels in the learning set could be unreliable (label noise). Further, a proportion of observations might depart from the main structure of the data (outliers) and new groups may appear in the test set, which were not encountered earlier in the training phase (unobserved classes). Therefore, we present here a robust and adaptive version of the Discriminant Analysis rule, capable of handling situations in which one or more of the aforementioned problems occur. The proposed approach is successfully employed in performing anomaly and novelty detection on geometric features recorded from X-ray photograms of grain kernels from different varieties.
Capitolo o saggio
Anomaly detection; Impartial trimming; Label noise; Model-based classification; Novelty detection; Robust estimation
English
Statistical Learning and Modeling in Data Analysis
978-3-030-69943-7
Cappozzo, A., Greselin, F., Murphy, T. (2021). Robust Model-Based Learning to Discover New Wheat Varieties and Discriminate Adulterated Kernels in X-Ray Images. In S. Balzano, G.C. Porzio, R. Salvatore, D. Vistocco, M. Vichi (a cura di), Statistical Learning and Modeling in Data Analysis (pp. 29-36). Springer Science and Business Media Deutschland GmbH [10.1007/978-3-030-69944-4_4].
Cappozzo, A; Greselin, F; Murphy, T
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/335945
Citazioni
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
Social impact