A Trainable Open-Source Machine Learning Accelerometer Activity Recognition Toolbox: Deep Learning Approach.
Options
BORIS DOI
Publisher DOI
PubMed ID
38875548
Description
BACKGROUND
The accuracy of movement determination software in current activity trackers is insufficient for scientific applications, which are also not open-source.
OBJECTIVE
To address this issue, we developed an accurate, trainable, and open-source smartphone-based activity-tracking toolbox that consists of an Android app (HumanActivityRecorder) and 2 different deep learning algorithms that can be adapted to new behaviors.
METHODS
We employed a semisupervised deep learning approach to identify the different classes of activity based on accelerometry and gyroscope data, using both our own data and open competition data.
RESULTS
Our approach is robust against variation in sampling rate and sensor dimensional input and achieved an accuracy of around 87% in classifying 6 different behaviors on both our own recorded data and the MotionSense data. However, if the dimension-adaptive neural architecture model is tested on our own data, the accuracy drops to 26%, which demonstrates the superiority of our algorithm, which performs at 63% on the MotionSense data used to train the dimension-adaptive neural architecture model.
CONCLUSIONS
HumanActivityRecorder is a versatile, retrainable, open-source, and accurate toolbox that is continually tested on new data. This enables researchers to adapt to the behavior being measured and achieve repeatability in scientific studies.
The accuracy of movement determination software in current activity trackers is insufficient for scientific applications, which are also not open-source.
OBJECTIVE
To address this issue, we developed an accurate, trainable, and open-source smartphone-based activity-tracking toolbox that consists of an Android app (HumanActivityRecorder) and 2 different deep learning algorithms that can be adapted to new behaviors.
METHODS
We employed a semisupervised deep learning approach to identify the different classes of activity based on accelerometry and gyroscope data, using both our own data and open competition data.
RESULTS
Our approach is robust against variation in sampling rate and sensor dimensional input and achieved an accuracy of around 87% in classifying 6 different behaviors on both our own recorded data and the MotionSense data. However, if the dimension-adaptive neural architecture model is tested on our own data, the accuracy drops to 26%, which demonstrates the superiority of our algorithm, which performs at 63% on the MotionSense data used to train the dimension-adaptive neural architecture model.
CONCLUSIONS
HumanActivityRecorder is a versatile, retrainable, open-source, and accurate toolbox that is continually tested on new data. This enables researchers to adapt to the behavior being measured and achieve repeatability in scientific studies.
Date of Publication
2023-06-08
Publication Type
Article
Keyword(s)
accelerometry activity classification activity recognition activity recorder deep learning deep learning algorithm digital health application machine learning open source sensor device smartphone app
Language(s)
en
Additional Credits
Series
Journal of Medical Internet Research - Artificial Intelligence
Publisher
JMIR Publications
ISSN
2817-1705
Access(Rights)
open.access