A paper from the BD4QoL partner DEUSTO, “Behavior Modeling for a Beacon-Based Indoor Location System”, has been published in the peer-reviewed, open access, Sensors Journal, including part of the work carried out in the hybrid activity recognition system of the project.

The paper illustrates a comparison performed between two different approaches to track a person in indoor environments using a locating system, with a smartphone and a smartwatch as monitoring devices. It also evaluates the system's performance, and presents a novel location prediction system and a soft-attention mechanism (able to predict user's next location with 67% accuracy).

Reference: Aritz Bilbao Jayo, Aitor Almeida, Ilaria Sergi, Teodoro Montanaro, Luca Fasano, Mikel Emaldi, Luigi Patrono. (2021) "Behavior Modeling for a Beacon-Based Indoor Location System" In Sensors. vol. 21. p. 4839. DOI: 10.3390/s21144839.

Read the full paper