TY - JOUR
T1 - Fall detection system by machine learning framework for public health
AU - Rodrigues, Thiago B.
AU - Salgado, Débora P.
AU - Cordeiro, Mauricio C.
AU - Osterwald, Katja M.
AU - Filho, Teodiano F.B.
AU - De Lucena, Vicente F.
AU - Naves, Eduardo L.M.
AU - Murray, Niall
N1 - Publisher Copyright:
© 2018 The Authors. Published by Elsevier Ltd.
PY - 2018
Y1 - 2018
N2 - The elderly population is growing every year in Brazil. Consequently, health risks in elderly is a concern for public health system. During the aging process, the mobility is affected, and falls are more frequent causing injuries and even death, whose causes can be prevented, with reduction of financial costs. Therefore, a low-cost inertial sensor-based system is a tool to fulfill the need for detecting falls in elderly. In this paper, we present our system as a proof of concept for the study of fall and we propose a low cost and more accessible system for fall detection using inertial sensors. The inertial sensor collects data, identifies and detect four different ?fall states'. The aim is to use this system in public health. In real-time, it will advise any person around the elder about the fall. Different machine learning classifiers are tested in the train dataset, and the best one was used for training the sensor data. Then, the model was compared with unknown sensor data (captured and from available datasets) to guess at which state the person is. We found out that there were only 15 wrong observations from all trials, thus, the system has potential to be used to detect falls.
AB - The elderly population is growing every year in Brazil. Consequently, health risks in elderly is a concern for public health system. During the aging process, the mobility is affected, and falls are more frequent causing injuries and even death, whose causes can be prevented, with reduction of financial costs. Therefore, a low-cost inertial sensor-based system is a tool to fulfill the need for detecting falls in elderly. In this paper, we present our system as a proof of concept for the study of fall and we propose a low cost and more accessible system for fall detection using inertial sensors. The inertial sensor collects data, identifies and detect four different ?fall states'. The aim is to use this system in public health. In real-time, it will advise any person around the elder about the fall. Different machine learning classifiers are tested in the train dataset, and the best one was used for training the sensor data. Then, the model was compared with unknown sensor data (captured and from available datasets) to guess at which state the person is. We found out that there were only 15 wrong observations from all trials, thus, the system has potential to be used to detect falls.
KW - Fall
KW - Inertial sensors
KW - Machine Learning
KW - Public health
KW - Wearable devices
UR - http://www.scopus.com/inward/record.url?scp=85058268168&partnerID=8YFLogxK
U2 - 10.1016/j.procs.2018.10.189
DO - 10.1016/j.procs.2018.10.189
M3 - Conference article
AN - SCOPUS:85058268168
SN - 1877-0509
VL - 141
SP - 358
EP - 365
JO - Procedia Computer Science
JF - Procedia Computer Science
T2 - 9th International Conference on Emerging Ubiquitous Systems and Pervasive Networks, EUSPN 2018
Y2 - 5 November 2018 through 8 November 2018
ER -