Wieland, Fluri; Nigg, Claudio (2023). A Trainable Open-Source Machine Learning Accelerometer Activity Recognition Toolbox: Deep Learning Approach. Journal of Medical Internet Research - Artificial Intelligence, 2 JMIR Publications 10.2196/42337
|
Text
ai-2023-1-e42337.pdf - Published Version Available under License Creative Commons: Attribution (CC-BY). Download (2MB) | Preview |
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.
Item Type: |
Journal Article (Original Article) |
|---|---|
Division/Institute: |
07 Faculty of Human Sciences > Institute of Sport Science (ISPW) 07 Faculty of Human Sciences > Institute of Sport Science (ISPW) > Health Science |
UniBE Contributor: |
Wieland, Fluri Anton Martin, Nigg, Claudio Renato |
Subjects: |
000 Computer science, knowledge & systems 700 Arts > 790 Sports, games & entertainment |
ISSN: |
2817-1705 |
Publisher: |
JMIR Publications |
Language: |
English |
Submitter: |
Fluri Anton Martin Wieland |
Date Deposited: |
05 Jul 2024 15:59 |
Last Modified: |
05 Jul 2024 16:08 |
Publisher DOI: |
10.2196/42337 |
PubMed ID: |
38875548 |
Uncontrolled Keywords: |
accelerometry activity classification activity recognition activity recorder deep learning deep learning algorithm digital health application machine learning open source sensor device smartphone app |
BORIS DOI: |
10.48350/198576 |
URI: |
https://boris.unibe.ch/id/eprint/198576 |
Actions (login required)
 |
Edit item |