RT info:eu-repo/semantics/article
T1 Identifying users from the interaction with a door handle
A1 Vegas Hernández, Jesús María
A1 Llamas Bello, César
A1 González Delgado, Manuel Ángel
A1 Hernández Díez, María Carmen
K1 Ambient Intelligence
K1 User Identification
K1 IoT
K1 Sensors
K1 Pattern Matching
K1 Access Control
AB Ambient intelligence pursues the integration of intelligent approaches onan IoT infrastructure, mainly using everyday objects of the environment.The main hypothesis of the work is that the way in which a user interactswith a door handle is suitable to be used in the identification task. Our proposal contributes with a new method to identify persons in a seamless andun-obstrusive way, suitable to be used in a smart building scenery withoutthe need to bring any additional device. In this case, we embed accelerometersand gyroscopes in a door handle in order to obtain a data set comprisingsamples of 47 individuals. A parametric approximation is adopted to reduceeach sample to a feature vector by using a dynamic time warping technique.A study has been made of the outcomes of different classification techniquesover six different feature sets in order to assess the feasibility of this identification challenge. The AUC values observed with the selected feature setshow promising results above 0.90 using neural networks and SVM classifiers.
PB Elsevier
YR 2020
FD 2020
LK http://uvadoc.uva.es/handle/10324/43604
UL http://uvadoc.uva.es/handle/10324/43604
LA eng
NO Pervasive and Mobile Computing S1574-1192(20)30128-0
DS UVaDOC
RD 25-dic-2024