dc.creator | Georgakopoulos S.V., Tasoulis S.K., Mallis G.I., Vrahatis A.G., Plagianakos V.P., Maglogiannis I.G. | en |
dc.date.accessioned | 2023-01-31T07:40:21Z | |
dc.date.available | 2023-01-31T07:40:21Z | |
dc.date.issued | 2020 | |
dc.identifier | 10.1007/s00521-020-05208-8 | |
dc.identifier.issn | 09410643 | |
dc.identifier.uri | http://hdl.handle.net/11615/72070 | |
dc.description.abstract | Accurate fall detection is a crucial research challenge since the time delay from fall to first aid is a key factor that determines the consequences of a fall. Wearable sensors allow a reliable way for motion tracking, allowing immediate detection of high-risk falls via a machine learning framework. Toward this direction, accelerometer devices are widely used for the assessment of fall risk. Although there exist a plethora of studies under this perspective, several challenges still remain, such as dealing simultaneously with extremely demanding data management, power consumption and prediction accuracy. In this work, we propose a complete methodology based on the cooperation of deep learning for signal classification along with a lightweight control chart method for change detection. Our basic assumption is that it is possible to control computational resources by selectively allowing the operation of a relatively heavyweight, but very efficient classifier, when it is truly required. The proposed methodology was applied to real experimental data providing the reliable results that justify the original hypothesis. © 2020, Springer-Verlag London Ltd., part of Springer Nature. | en |
dc.language.iso | en | en |
dc.source | Neural Computing and Applications | en |
dc.source.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85088698957&doi=10.1007%2fs00521-020-05208-8&partnerID=40&md5=947e65b1767002890129072fdd6f07f3 | |
dc.subject | Deep learning | en |
dc.subject | Delay control systems | en |
dc.subject | Information management | en |
dc.subject | Motion tracking | en |
dc.subject | Neural networks | en |
dc.subject | Risk assessment | en |
dc.subject | Change detection | en |
dc.subject | Computational resources | en |
dc.subject | Convolution neural network | en |
dc.subject | Fall recognition | en |
dc.subject | Prediction accuracy | en |
dc.subject | Reliable results | en |
dc.subject | Research challenges | en |
dc.subject | Signal classification | en |
dc.subject | Learning systems | en |
dc.subject | Springer Science and Business Media Deutschland GmbH | en |
dc.title | Change detection and convolution neural networks for fall recognition | en |
dc.type | journalArticle | en |