Falls Risk Classification of Older Adults Using Deep Neural Networks and Transfer Learning

Prior research in falls risk classification using inertial sensors has relied on the use of engineered features, which has resulted in a feature space containing hundreds of features that are likely redundant and possibly irrelevant. In this paper, we propose using fully convolutional neural network...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of biomedical and health informatics 2020-01, Vol.24 (1), p.144-150
Main Authors: Martinez, Matthew, De Leon, Phillip L.
Format: Article
Language:English
Subjects:
60 APPLIED LIFE SCIENCES
accelerometers
Accelerometry - methods
Accidental Falls - prevention & control
Activity recognition
Adolescent
Adult
Adults
Aged
Aged, 80 and over
Artificial neural networks
Biological system modeling
Biomedical measurement
Classification
Classifiers
Data models
Data models Multi-layer neural networks
Datasets
Falls
Female
Gait
gyroscopes
Humans
Inertial sensing devices
Informatics
Kernel
Learning algorithms
Machine learning
Male
Middle Aged
Multi-layer neural networks
Neural networks
Neural Networks, Computer
Older people
Risk
ROC Curve
Sensors
Signal Processing, Computer-Assisted
Smartphone
Time series analysis
Transfer learning
Young Adult
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Prior research in falls risk classification using inertial sensors has relied on the use of engineered features, which has resulted in a feature space containing hundreds of features that are likely redundant and possibly irrelevant. In this paper, we propose using fully convolutional neural networks (FCNNs) to classify older adults at low or high risk of falling using inertial sensor data collected from a smartphone. Due to the limited nature of older adult inertial gait datasets, we first pre-train the FCNN models using a publicly available dataset for pedestrian activity recognition. Then via transfer learning, we train the network for falls risk classification. We show that via transfer learning, our falls risk classifier obtains an area under the receiver operating characteristic curve of 93.3%, which is 10.6% higher than the equivalent model trained without the use of transfer learning. Additionally, we show that our method outperforms other standard machine learning classifiers trained on features developed in prior research.
ISSN:2168-2194
2168-2208
DOI:10.1109/JBHI.2019.2906499