000046966 001__ 46966
000046966 005__ 20161006102700.0
000046966 0247_ $$2doi$$a10.3390/s16010117
000046966 0248_ $$2sideral$$a93437
000046966 037__ $$aART-2016-93437
000046966 041__ $$aeng
000046966 100__ $$0(orcid)0000-0001-7671-7540$$aMedrano Sánchez, Carlos Tomás$$uUniversidad de Zaragoza
000046966 245__ $$aThe effect of personalization on smartphone-based fall detectors
000046966 260__ $$c2016
000046966 5060_ $$aAccess copy available to the general public$$fUnrestricted
000046966 5203_ $$aThe risk of falling is high among different groups of people, such as older people, individuals with Parkinson''s disease or patients in neuro-rehabilitation units. Developing robust fall detectors is important for acting promptly in case of a fall. Therefore, in this study we propose to personalize smartphone-based detectors to boost their performance as compared to a non-personalized system. Four algorithms were investigated using a public dataset: three novelty detection algorithms—Nearest Neighbor (NN), Local Outlier Factor (LOF) and One-Class Support Vector Machine (OneClass-SVM)—and a traditional supervised algorithm, Support Vector Machine (SVM). The effect of personalization was studied for each subject by considering two different training conditions: data coming only from that subject or data coming from the remaining subjects. The area under the receiver operating characteristic curve (AUC) was selected as the primary figure of merit. The results show that there is a general trend towards the increase in performance by personalizing the detector, but the effect depends on the individual being considered. A personalized NN can reach the performance of a non-personalized SVM (average AUC of 0.9861 and 0.9795, respectively), which is remarkable since NN only uses activities of daily living for training.
000046966 536__ $$9info:eu-repo/grantAgreement/ES/MINECO/TEC2013-50049-EXP
000046966 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttp://creativecommons.org/licenses/by/3.0/es/
000046966 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000046966 700__ $$0(orcid)0000-0001-7550-6688$$aPlaza García, Inmaculada$$uUniversidad de Zaragoza
000046966 700__ $$0(orcid)0000-0002-1561-0536$$aIgual Catalán, Raúl$$uUniversidad de Zaragoza
000046966 700__ $$aSánchez, Á.
000046966 700__ $$aCastro, M.
000046966 7102_ $$15009$$2535$$aUniversidad de Zaragoza$$bDepartamento de Ingeniería Eléctrica$$cIngeniería Eléctrica
000046966 7102_ $$15008$$2785$$aUniversidad de Zaragoza$$bDepartamento de Ingeniería Electrónica y Comunicaciones$$cTecnología Electrónica
000046966 773__ $$g16, 1 (2016), 117$$pSensors$$tSENSORS$$x1424-8220
000046966 8564_ $$s822863$$uhttp://zaguan.unizar.es/record/46966/files/texto_completo.pdf$$yVersión publicada
000046966 8564_ $$s107204$$uhttp://zaguan.unizar.es/record/46966/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000046966 909CO $$ooai:zaguan.unizar.es:46966$$particulos$$pdriver
000046966 951__ $$a2016-07-12-08:08:20
000046966 980__ $$aARTICLE