Buscar

 Detalle_Publicacion

Human activity recognition through weighted finite automata

Abstract: ABSTRACT: This work addresses the problem of human activity identification in an ubiquitous environment, where data is collected from a wide variety of sources. In our approach, after filtering noisy sensor entries, we learn user?s behavioral patterns and activities? sensor patterns through the construction of weighted finite automata and regular expressions respectively, and infer the inhabitant?s position for each activity through frequency distribution of floor sensor data. Finally, we analyze the prediction results of this strategy, which obtains 90.65% accuracy for the test data.+

 Congreso: International Conference on Ubiquitous Computing and Ambient Intelligence: UCAmI (12º : 2018 : Punta Cana)

Editorial: MDPI

 Año de publicación: 2018

Nº de páginas: 11

Tipo de publicación: Comunicación a Congreso

 DOI: 10.3390/proceedings2191263

ISSN: 2504-3900

Proyecto español: MTM2014-55262-P

Autores/as

SALOMÓN GARCÍA, SERGIO