000065611 001__ 65611 000065611 005__ 20231116120807.0 000065611 0247_ $$2doi$$a10.1007/s11517-017-1632-z 000065611 0248_ $$2sideral$$a98183 000065611 037__ $$aART-2017-98183 000065611 041__ $$aeng 000065611 100__ $$0(orcid)0000-0001-7671-7540$$aMedrano, C.$$uUniversidad de Zaragoza 000065611 245__ $$aCombining novelty detectors to improve accelerometer-based fall detection 000065611 260__ $$c2017 000065611 5060_ $$aAccess copy available to the general public$$fUnrestricted 000065611 5203_ $$aResearch on body-worn sensors has shown how they can be used for the detection of falls in the elderly, which is a relevant health problem. However, most systems are trained with simulated falls, which differ from those of the target population. In this paper, we tackle the problem of fall detection using a combination of novelty detectors. A novelty detector can be trained only with activities of daily life (ADL), which are true movements recorded in real life. In addition, they allow adapting the system to new users, by recording new movements and retraining the system. The combination of several detectors and features enhances performance. The proposed approach has been compared with a traditional supervised algorithm, a support vector machine, which is trained with both falls and ADL. The combination of novelty detectors shows better performance in a typical cross-validation test and in an experiment that mimics the effect of personalizing the classifiers. The results indicate that it is possible to build a reliable fall detector based only on ADL. 000065611 536__ $$9info:eu-repo/grantAgreement/ES/MINECO/TEC2013-50049-EXP 000065611 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/ 000065611 590__ $$a1.971$$b2017 000065611 591__ $$aMATHEMATICAL & COMPUTATIONAL BIOLOGY$$b19 / 59 = 0.322$$c2017$$dQ2$$eT1 000065611 591__ $$aENGINEERING, BIOMEDICAL$$b41 / 77 = 0.532$$c2017$$dQ3$$eT2 000065611 591__ $$aMEDICAL INFORMATICS$$b14 / 25 = 0.56$$c2017$$dQ3$$eT2 000065611 591__ $$aCOMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS$$b52 / 105 = 0.495$$c2017$$dQ2$$eT2 000065611 592__ $$a0.661$$b2017 000065611 593__ $$aComputer Science Applications$$c2017$$dQ2 000065611 593__ $$aBiomedical Engineering$$c2017$$dQ2 000065611 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion 000065611 700__ $$0(orcid)0000-0002-1561-0536$$aIgual, R.$$uUniversidad de Zaragoza 000065611 700__ $$0(orcid)0000-0002-2726-6760$$aGarcía-Magariño, I.$$uUniversidad de Zaragoza 000065611 700__ $$0(orcid)0000-0001-7550-6688$$aPlaza, I.$$uUniversidad de Zaragoza 000065611 700__ $$0(orcid)0000-0003-3270-5462$$aAzuara, G.$$uUniversidad de Zaragoza 000065611 7102_ $$15008$$2785$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cÁrea Tecnología Electrónica 000065611 7102_ $$15009$$2535$$aUniversidad de Zaragoza$$bDpto. Ingeniería Eléctrica$$cÁrea Ingeniería Eléctrica 000065611 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf. 000065611 7102_ $$15008$$2560$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cÁrea Ingeniería Telemática 000065611 773__ $$g55, 10 (2017), 1849–1858$$pMed. biol. eng. comput.$$tMEDICAL & BIOLOGICAL ENGINEERING & COMPUTING$$x0140-0118 000065611 8564_ $$s1065431$$uhttps://zaguan.unizar.es/record/65611/files/texto_completo.pdf$$yPostprint 000065611 8564_ $$s91045$$uhttps://zaguan.unizar.es/record/65611/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint 000065611 909CO $$ooai:zaguan.unizar.es:65611$$particulos$$pdriver 000065611 951__ $$a2023-11-16-12:00:05 000065611 980__ $$aARTICLE