Elderly people are prone to fall due to the high rate of risk factors associated with ageing. Existing fall detection sys- tems are mostly designed for a constrained environment, where various assumptions are applied. To overcome these drawbacks, we opt to use mobile phones with standard built- in sensors. Fall detection is performed on motion data col- lected by sensors in the phone alone. We use Genetic Pro- gramming (GP) to learn a classi er directly from raw sensor data. We compare the performance of GP with the popu- lar approach of using threshold-based algorithm. The result shows that GP-evolved classi ers perform consistently well across di erent fall types and overall more reliable than the threshold-based.
@inproceedings{DBLP:conf/mum/DauSSHH14,
author = {Anh Hoang Dau and
Flora Dilys Salim and
Andy Song and
Lachlan Hedin and
Margaret Hamilton},
bibsource = {dblp computer science bibliography, https://dblp.org},
biburl = {https://dblp.org/rec/conf/mum/DauSSHH14.bib},
booktitle = {Proceedings of the 13th International Conference on Mobile and Ubiquitous
Multimedia, Melbourne, VIC, Australia, November 25-28, 2014},
doi = {10.1145/2677972.2678010},
editor = {Arkady B. Zaslavsky and
Seng W. Loke and
Lars Kulik and
Evaggelia Pitoura},
pages = {256--257},
publisher = {ACM},
timestamp = {Fri, 27 Mar 2020 00:00:00 +0100},
title = {Phone based fall detection by genetic programming},
url = {https://doi.org/10.1145/2677972.2678010},
year = {2014}
}
© 2021 Flora Salim - CRUISE Research Group.