wenmin-wu/timeseries-imu-gravity-removal
skills/timeseries/imu-gravity-removal/SKILL.md
Remove gravity component from raw accelerometer data using quaternion rotation to yield linear acceleration
$ install --global
skillsauthnpx skillsauth add wenmin-wu/ds-skills timeseries-imu-gravity-removalInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 22, 2026, 10:49 AM118.3s1 file scanned
SKILL.md
- name:
- timeseries-imu-gravity-removal
- description:
- Remove gravity component from raw accelerometer data using quaternion rotation to yield linear acceleration
- domain:
- timeseries
IMU Gravity Removal
Overview
Raw accelerometer readings include gravitational acceleration (~9.81 m/s^2). Use the device's quaternion orientation to rotate the world-frame gravity vector into sensor frame, then subtract it. Essential preprocessing for any wearable/IMU activity recognition task.
Quick Start
import numpy as np
from scipy.spatial.transform import Rotation as R
def remove_gravity(acc_xyz, quaternions, g=9.81):
"""Remove gravity from accelerometer using quaternion orientation.
Args:
acc_xyz: (N, 3) raw accelerometer [x, y, z]
quaternions: (N, 4) orientation [x, y, z, w]
Returns:
(N, 3) linear acceleration
"""
gravity_world = np.array([0, 0, g])
linear = np.zeros_like(acc_xyz)
for i in range(len(acc_xyz)):
rot = R.from_quat(quaternions[i])
gravity_sensor = rot.apply(gravity_world, inverse=True)
linear[i] = acc_xyz[i] - gravity_sensor
return linear
Key Decisions
- Quaternion format: scipy uses
[x, y, z, w]— check your sensor's convention - inverse=True: transforms world→sensor frame (not sensor→world)
- Vectorized option:
R.from_quat(all_quats).apply(gravity, inverse=True)for speed
References
- Source: cmi25-imu-thm-tof-tf-blendingmodel-lb-82
- Competition: CMI - Detect Behavior with Sensor Data
Related Skills
wenmin-wu/timeseries-scaled-pinball-loss
data-ai
VerifiedTrustedCommunity
Scaled Pinball Loss (SPL) metric for evaluating quantile forecasts, normalized by mean absolute successive differences of training data
31SKILL.mdUpdated Apr 23, 2026
wenmin-wu/timeseries-retroactive-outlier-rescaling
data-ai
VerifiedTrustedCommunity
Walk backward through a time series and multiplicatively rescale segments when jumps exceed a fraction of the running mean to correct data collection anomalies
31SKILL.mdUpdated Apr 23, 2026
wenmin-wu/timeseries-ratio-target-for-smape
testing
VerifiedTrustedCommunity
Transform forecasting target to next/current ratio minus one so that optimizing MAE or squared error implicitly minimizes SMAPE
31SKILL.mdUpdated Apr 23, 2026
wenmin-wu/timeseries-quantile-ratio-scaling
tools
VerifiedTrustedCommunity
Convert point forecasts to prediction intervals by scaling with logit-transformed quantile ratios passed through a Normal CDF
31SKILL.mdUpdated Apr 23, 2026