Accelerometer

Latest version: v7.2.1.post0

Safety actively analyzes 722032 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 3 of 7

6.2.3

What's Changed
* Fix/no stationary points by chanshing in https://github.com/OxWearables/biobankAccelerometerAnalysis/pull/221


**Full Changelog**: https://github.com/OxWearables/biobankAccelerometerAnalysis/compare/v6.2.2...v6.2.3

6.2.2

What's Changed
- Fixed missing `--timeShift` support for GENEActiv files.

6.2.1

What's Changed
- Output summary file with all the numerical precision. That is, no more rounding.

6.2.0

What's Changed
- Restructured the model directories & URLs
- Separate Chan's model:
- `--activityModel chan` classifies "sleep", "sedentary", and "other". Then, "other" is split into "light" and "moderate-vigorous" using cutpoints.
- `--activityModel chanw` classifies "sleep", "sedentary", "walking", and "other". Then, "other" split using cutpoints.

6.1.0

What's Changed

* Updated Chan classifier to include "walking". Similar to the previous model, this will first classify "sleep", "sedentary", "walking", and "other". Then, "other" is further split according to ENMO cutpoints (>100mg then "moderate-vigorous", otherwise "light").

6.0.0

What's Changed

* New Chan's activity classification model: Pass `--activityModel chan` to use. The model classifies "sleep", "sedentary" and "other" activities. "other" is then further split based on simple ENMO cutpoints:
* "other" & <100mg = "light"
* "other" & >=100mg = "moderate-vigorous"
* Simple heuristic to smooth sleep outputs to reduce spurious false positive sleep bouts. Currently only applies to Chan's model.
* Cleanups 024e656fa372fffdbc4eeea5f55017446f8acb37

Page 3 of 7

© 2025 Safety CLI Cybersecurity Inc. All Rights Reserved.