Human Activity Recognition through Weighted Finite Automata

Salomón García, Sergio; Tirnauca, Cristina

doi:10.3390/proceedings2191263

dc.contributor.author	Salomón García, Sergio
dc.contributor.author	Tirnauca, Cristina
dc.contributor.other	Universidad de Cantabria	es_ES
dc.date.accessioned	2019-03-06T13:07:27Z
dc.date.available	2019-03-06T13:07:27Z
dc.date.issued	2018
dc.identifier.issn	2504-3900
dc.identifier.other	MTM2014-55262-P	es_ES
dc.identifier.uri	http://hdl.handle.net/10902/15810
dc.description.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.+	es_ES
dc.description.sponsorship	This research was funded by Ministerio de Ciencia e Innovación (MICINN), Spain grant number MTM2014-55262-P and by Sociedad para el Desarrollo Regional de Cantabria (SODERCAN) grant number TI16IN-007.	es_ES
dc.format.extent	11 p.	es_ES
dc.language.iso	eng	es_ES
dc.publisher	MDPI	es_ES
dc.rights	Attribution 4.0 International	es_ES
dc.rights.uri	http://creativecommons.org/licenses/by/4.0/	*
dc.source	Proceedings 2018, 2(19), 1263	es_ES
dc.title	Human Activity Recognition through Weighted Finite Automata	es_ES
dc.type	info:eu-repo/semantics/conferenceObject	es_ES
dc.rights.accessRights	openAccess	es_ES
dc.identifier.DOI	10.3390/proceedings2191263
dc.type.version	submittedVersion	es_ES