skdh.features.JerkMetric

class skdh.features.JerkMetric

The normalized sum of jerk. Assumes the input signal is acceleration, and therefore the jerk is the first time derivative of the input signal.

Methods

compute(signal[, fs, axis])

Compute the jerk metric

Notes

Given an acceleration signal \(a\), the pre-normalized jerk metric \(\hat{J}\) is computed using a 2-point difference of the acceleration, then squared and summed per

\[\hat{J} = \sum_{i=2}^N\left(\frac{a_{i} - a_{i-1}}{\Delta t}\right)^2\]

where \(\Delta t\) is the sampling period in seconds. The jerk metric \(J\) is then normalized using constants and the maximum absolute acceleration value observed per

\[s = \frac{360max(|a|)^2}{\Delta t}\]

\[J = \frac{\hat{J}}{2s}\]

compute(signal, fs=1.0, *, axis=-1)

Compute the jerk metric

Parameters:

signalarray-like

Array-like containing values to compute the jerk metric for.

fsfloat, optional

Sampling frequency in Hz. If not provided, default is 1.0Hz

axisint, optional

Axis along which the signal entropy will be computed. Ignored if signal is a pandas.DataFrame. Default is last (-1).

Returns:

jerk_metricnumpy.ndarray

Computed jerk metric.