Autori:
Ciszewski, Michal ![](http://www.bncf.firenze.sbn.it/img/logo-bncf.jpg)
,
Sohl, Jakob ![](http://www.bncf.firenze.sbn.it/img/logo-bncf.jpg)
,
Jongbloed, Geurt ![](http://www.bncf.firenze.sbn.it/img/logo-bncf.jpg)
Titolo:
Improving state estimation through projection post-processing for activity recognition with application to footballPeriodico:
Statistical methods & applications : Journal of the Italian Statistical SocietyAnno:
2023 - Volume:
32 - Fascicolo:
5 - Pagina iniziale:
1509 - Pagina finale:
1538The past decade has seen an increased interest in human activity recognition based on sensor data. Most often, the sensor data come unannotated, creating the need for fast labelling methods. For assessing the quality of the labelling, an appropriate performance measure has to be chosen. Our main contribution is a novel post-processing method for activity recognition. It improves the accuracy of the classification methods by correcting for unrealistic short activities in the estimate. We also propose a new performance measure, the Locally Time-Shifted Measure (LTS measure), which addresses uncertainty in the times of state changes. The effectiveness of the post-processing method is evaluated, using the novel LTS measure, on the basis of a simulated dataset and a real application on sensor data from football. The simulation study is also used to discuss the choice of the parameters of the post-processing method and the LTS measure.
Premi sulle icone
![](http://www.bncf.firenze.sbn.it/img/logo-bncf.jpg)
a fianco dei nomi per visualizzare i libri scritti dall'autore
X
Opere monografiche dal catalogo BNCF
SICI: 1618-2510(2023)32:5<1509:ISETPP>2.0.ZU;2-#
Esportazione dati in Refworks (solo per utenti abilitati)
Record salvabile in Zotero
Biblioteche ACNP che possiedono il periodico