This would seem to be useful for our therapists to use the information from this to use their fall resiliency protocol to prevent falls.
Feature selection for elderly faller classification based on wearable sensors
- Jennifer Howcroft,
- Jonathan Kofman and
- Edward D. LemaireEmail author
Journal of NeuroEngineering and Rehabilitation201714:47
DOI: 10.1186/s12984-017-0255-9
© The Author(s). 2017
Received: 20 April 2016
Accepted: 15 May 2017
Published: 30 May 2017
Abstract
Background
Wearable sensors can be used
to derive numerous gait pattern features for elderly fall risk and
faller classification; however, an appropriate feature set is required
to avoid high computational costs and the inclusion of irrelevant
features. The objectives of this study were to identify and evaluate
smaller feature sets for faller classification from large feature sets
derived from wearable accelerometer and pressure-sensing insole gait
data.
Methods
A convenience sample of 100
older adults (75.5 ± 6.7 years; 76 non-fallers, 24 fallers based on
6 month retrospective fall occurrence) walked 7.62 m while wearing
pressure-sensing insoles and tri-axial accelerometers at the head,
pelvis, left and right shanks. Feature selection was performed using
correlation-based feature selection (CFS), fast correlation based filter
(FCBF), and Relief-F algorithms. Faller classification was performed
using multi-layer perceptron neural network, naïve Bayesian, and support
vector machine classifiers, with 75:25 single stratified holdout and
repeated random sampling.
Results
The best performing model was a
support vector machine with 78% accuracy, 26% sensitivity, 95%
specificity, 0.36 F1 score, and 0.31 MCC and one posterior pelvis
accelerometer input feature (left acceleration standard deviation). The
second best model achieved better sensitivity (44%) and used a support
vector machine with 74% accuracy, 83% specificity, 0.44 F1 score, and
0.29 MCC. This model had ten input features: maximum, mean and standard
deviation posterior acceleration; maximum, mean and standard deviation
anterior acceleration; mean superior acceleration; and three impulse
features. The best multi-sensor model sensitivity (56%) was achieved
using posterior pelvis and both shank accelerometers and a naïve
Bayesian classifier. The best single-sensor model sensitivity (41%) was
achieved using the posterior pelvis accelerometer and a naïve Bayesian
classifier.
Conclusions
Feature selection provided
models with smaller feature sets and improved faller classification
compared to faller classification without feature selection. CFS and
FCBF provided the best feature subset (one posterior pelvis
accelerometer feature) for faller classification. However, better
sensitivity was achieved by the second best model based on a Relief-F
feature subset with three pressure-sensing insole features and seven
head accelerometer features. Feature selection should be considered as
an important step in faller classification using wearable sensors.
No comments:
Post a Comment