Analyzing Multiple Accelerometer Configurations to Detect Falls and Motion
The use of wearable devices with accelerometers developed to detect falls and motion has been continuously growing because of their small size, low weight, energy efficiency, and low price. However, the number of sensors, their position in the body and es
- PDF / 917,478 Bytes
- 4 Pages / 595.276 x 790.866 pts Page_size
- 44 Downloads / 205 Views
SISTEMIC, Facultad de Ingeniería, Universidad de Antiquia UDEA, Calle 70 No. 52-21, Tel.: +57-4-2198561, Medellín, Colombia
Abstract— The use of wearable devices with accelerometers developed to detect falls and motion has been continuously growing because of their small size, low weight, energy efficiency, and low price. However, the number of sensors, their position in the body and estimation methodologies are still open issues when tested in uncontrolled conditions. In this paper, we perform a discriminant analysis to determine which combinations of feature extraction characteristics and accelerometer positions are best fitted to estimate falls and particular movements. A dataset of 33 activities recorded with eight accelerometers distributed along the body of six participants is released as part of this work. Our analysis concludes that a waist-arm combination with a statistical feature is best fitted for most cases. But this work, rather than a single conclusion, is intended to provide a benchmark to other authors. The specific tests explain for example that the foot is not a good location for the accelerometer, or that static features are less relevant than dynamic ones. Keywords— Triaxial accelerometer, wearable devices, mobile health-care, elderly fall detection, motion capture.
I
I NTRODUCTION
There is a current impulse in healthcare services for constant monitoring of independent elderly people with minimum intrusion. Real-time fall detection and automatic assistance on physical therapy exercises are good examples of the current needs in the field [1]. Additionally, the demand of wearable devices developed for improving sports performance has increased with the introduction of smart-watches and similar gadgets. However, fall detection and motion capture are complex processes and still an open issue when implemented under uncontrolled conditions. Falls in elderly people have been traditionally detected with environment based (cameras, pressure sensors, etc.) and wearable devices (mainly accelerometers, see [2–4] for reviews). But the indoor constrain of environment based systems makes them infeasible for most activities of daily living (ADL). The most popular sensors used for wearable devices are capacitive accelerometers because of their small size, low weight, energy efficiency, and low price [5]. These characteristics have popularized accelerometers in several electronic devices for a wide range of uses (stabilizing cameras, video-
game pads, smartphone positioning, etc.), and recently in smart-watches or directly attached to clothes. Motion capture with accelerometers has not been broadly studied. Some works have characterized walk and jog by detecting the periodicity of the signal (see [6] and the references therein). Cola et al. [7] detected gait deviation as a fall risk feature. An overview of the field [1] highlights classification of posture and transition, gait, balance and sway, unsupervised monitoring, and general movements (sit, sleep, etc.) as important human motion activities for monitoring clin
Data Loading...
