GT3X Posture Prediction Algorithm
Function to predict body posture from ActiGraph GT3X raw data
You are now following this Submission
- You will see updates in your followed content feed
- You may receive emails, depending on your communication preferences
This function predicts body posture from hip-worn ActiGraph wGT3X-BT accelerometer raw data recorded at 30 Hz. The development of this function is described in Kuster et al. 2019, doi: 10.1111/sms.13601, published in Scandinavian Journal of Medicine & Science in Sports. If using this function, please cite the aforementioned study. Please follow the instructions provided in README.txt and Screenshot.jpg. The copyright notice and disclaimer can be found in README.txt.
The Function "LoadCSVandPredictPosture.m" loads the ActiGraph raw data as exported with ActiLife (.csv) and uses the "PosturePredictionModel" to predict body posture on a minute by minute level. The output is saved as .csv file in the same style than the input file.
For questions and suggestions to improve, contact roman.kuster@alumni.ethz.ch.
Cite As
Roman Kuster (2026). GT3X Posture Prediction Algorithm (https://au.mathworks.com/matlabcentral/fileexchange/73517-gt3x-posture-prediction-algorithm), MATLAB Central File Exchange. Retrieved .
General Information
- Version 1.0.1 (626 KB)
MATLAB Release Compatibility
- Compatible with any release
Platform Compatibility
- Windows
- macOS
- Linux
