Fall detection with distributed floor-mounted accelerometers: An overview of the development and evaluation of a fall detection system within the project eHome
Franz Werner, Josef Diermaier, Sebastian Schmid, P. Panek
{"title":"Fall detection with distributed floor-mounted accelerometers: An overview of the development and evaluation of a fall detection system within the project eHome","authors":"Franz Werner, Josef Diermaier, Sebastian Schmid, P. Panek","doi":"10.4108/ICST.PERVASIVEHEALTH.2011.246088","DOIUrl":null,"url":null,"abstract":"Within the project \"eHome\" a prototype of an assistive home system was developed, aiming to prolong the independent life of elderly people at home. Besides communication, e-access and safety relevant features, a core part of this system is an automatic fall detection, which utilizes floor-mounted accelerometers to gather body-sound signals that typically occur during a human fall. This approach targets to avoid acceptance, usability and reliability issues of available body-mounted fall detectors. The system was developed with focus on practical applicability, reliability and exploitability. The prototype was evaluated successfully in laboratory and during 507 days in real-life at homes of persons from the target group. During the laboratory trials a sensitivity of 87% and a specificity of 97.7% could be achieved for a defined fall scenario and across four tested floors. Further research is suggested to investigate floor dependencies of the fall detection performance.","PeriodicalId":444978,"journal":{"name":"2011 5th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth) and Workshops","volume":"35 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"39","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2011 5th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth) and Workshops","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4108/ICST.PERVASIVEHEALTH.2011.246088","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 39
Abstract
Within the project "eHome" a prototype of an assistive home system was developed, aiming to prolong the independent life of elderly people at home. Besides communication, e-access and safety relevant features, a core part of this system is an automatic fall detection, which utilizes floor-mounted accelerometers to gather body-sound signals that typically occur during a human fall. This approach targets to avoid acceptance, usability and reliability issues of available body-mounted fall detectors. The system was developed with focus on practical applicability, reliability and exploitability. The prototype was evaluated successfully in laboratory and during 507 days in real-life at homes of persons from the target group. During the laboratory trials a sensitivity of 87% and a specificity of 97.7% could be achieved for a defined fall scenario and across four tested floors. Further research is suggested to investigate floor dependencies of the fall detection performance.