You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This 'sleep_processing_pipeline.predict_pipeline_acceleration()' function shows the legacy algorithm based on Cole/Kripke as the default. Right?
And look at the tutorial right after.
In 'Cut Data to Wear Period' part, the wear_detection.WearDetection() function is used, and the internal logic shows that it is based on van hees heuristic. So the plot underneath is a picture obtained by van hees?
In some papers, applied a band pass filter to 50hz acceleration sensor data and processed the signal. The filtering code is not visible in the internal logic, but I wonder if it doesn't matter because it's heuristic.
This 'get_major_wear_block(data)' function is analyzed by wearing the imu for the longest time, and the sample data is only at night. If it is worn long during the day, how can I judge it?
Thank you!
The text was updated successfully, but these errors were encountered:
I have additional questions on this site.
https://biopsykit.readthedocs.io/en/latest/examples/_notebooks/Sleep_IMU_Example.html
And look at the tutorial right after.
In 'Cut Data to Wear Period' part, the wear_detection.WearDetection() function is used, and the internal logic shows that it is based on van hees heuristic. So the plot underneath is a picture obtained by van hees?
In some papers, applied a band pass filter to 50hz acceleration sensor data and processed the signal. The filtering code is not visible in the internal logic, but I wonder if it doesn't matter because it's heuristic.
This 'get_major_wear_block(data)' function is analyzed by wearing the imu for the longest time, and the sample data is only at night. If it is worn long during the day, how can I judge it?
Thank you!
The text was updated successfully, but these errors were encountered: