Cargando…
Feature selection for elderly faller classification based on wearable sensors
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...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
BioMed Central
2017
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5450084/ https://www.ncbi.nlm.nih.gov/pubmed/28558724 http://dx.doi.org/10.1186/s12984-017-0255-9 |
_version_ | 1783239886540636160 |
---|---|
author | Howcroft, Jennifer Kofman, Jonathan Lemaire, Edward D. |
author_facet | Howcroft, Jennifer Kofman, Jonathan Lemaire, Edward D. |
author_sort | Howcroft, Jennifer |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-5450084 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2017 |
publisher | BioMed Central |
record_format | MEDLINE/PubMed |
spelling | pubmed-54500842017-06-01 Feature selection for elderly faller classification based on wearable sensors Howcroft, Jennifer Kofman, Jonathan Lemaire, Edward D. J Neuroeng Rehabil Research 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. BioMed Central 2017-05-30 /pmc/articles/PMC5450084/ /pubmed/28558724 http://dx.doi.org/10.1186/s12984-017-0255-9 Text en © The Author(s). 2017 Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated. |
spellingShingle | Research Howcroft, Jennifer Kofman, Jonathan Lemaire, Edward D. Feature selection for elderly faller classification based on wearable sensors |
title | Feature selection for elderly faller classification based on wearable sensors |
title_full | Feature selection for elderly faller classification based on wearable sensors |
title_fullStr | Feature selection for elderly faller classification based on wearable sensors |
title_full_unstemmed | Feature selection for elderly faller classification based on wearable sensors |
title_short | Feature selection for elderly faller classification based on wearable sensors |
title_sort | feature selection for elderly faller classification based on wearable sensors |
topic | Research |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5450084/ https://www.ncbi.nlm.nih.gov/pubmed/28558724 http://dx.doi.org/10.1186/s12984-017-0255-9 |
work_keys_str_mv | AT howcroftjennifer featureselectionforelderlyfallerclassificationbasedonwearablesensors AT kofmanjonathan featureselectionforelderlyfallerclassificationbasedonwearablesensors AT lemaireedwardd featureselectionforelderlyfallerclassificationbasedonwearablesensors |