gaitmap.preprocessing.sensor_alignment.PcaAlignment

class gaitmap.preprocessing.sensor_alignment.PcaAlignment(target_axis: str = 'y', pca_plane_axis: Sequence[str] = ('gyr_x', 'gyr_y'))

Align dataset target axis, to the main foot rotation plane, which is usually the medio-lateral plane.

The Principle Component Analysis (PCA) can be used to determin the coordinate plane where the main movement component is located, which corresponds to the main component of the PCA after fitting to the provided data. This is typically intended to align one axis of the sensor frame to the foot medio-lateral axis. The ML-axis is therefore assumed to correspond to the principle component with the highest explained variance within the 2D projection (“birds eye view”) of the X-Y sensor frame. To ensure a 2D problem the dataset should be aligned roughly to gravity beforhand so we can assume a fixed z-axis of [0,0,1] and solve the alignment as a pure heading issue.

This approach is inspired by [1]

Parameters:

target_axis

axis to which the main component found by the pca analysis will be aligned e.g. “y”

pca_plane_axis

list of axis names which span the 2D-plane where the pca will be performed e.g. (“gyr_x”,”gyr_y”). Note: the order of the axis defining the pca plane will influence also your target axis! So best keep a x-y order.

Other Parameters:

data

The data passed to the align method.

Attributes:

aligned_data_

The rotated sensor data after alignment

rotation_

The Rotation object tranforming the original data to the aligned data

pca_

PCA object after fitting

normalized_pca_components_

These are the PCA componts, but aligned to the coordinate system convention. I.e. the first component is always positive and the second component is positive 90 deg rotation from the first (i.e. they form a right handed coordinate system). These normalized components can be used to estimate the rotation of the sensor frame.

See also

sklearn.decomposition.PCA

Details on the used PCA implementation for this method.

gaitmap.preprocessing.sensor_alignment.ForwardDirectionSignAlignment

Alignment of the forward direction after PCA Alignment

Notes

The PCA is sign invariant this means only an alignment to the medio-lateral plane will be performend! An additional 180deg flip of the coordinate system might be still necessary after the PCA alignment!

[1]

W. Kong, S. Sessa, M. Zecca, and A. Takanishi, “Anatomical Calibration through Post-Processing of Standard Motion Tests Data,” Sensors, vol. 16, no. 12, p. 2011, Dec. 2016. [Online]. Available: https://www.mdpi.com/1424-8220/16/12/2011

Examples

Align dataset to medio-lateral plane, by aligning the y-axis with the dominant component in the gyro x-y-plane

>>> pca_alignment = PcaAlignment(target_axis="y", pca_plane_axis=("gyr_x", "gyr_y"))
>>> pca_alignment = pca_alignment.align(data, 204.8)
>>> pca_alignment.aligned_data_["left_sensor"]
<copy of dataset with axis aligned to the medio-lateral plane>
...

Methods

align(data, **_)	Align sensor data.
clone()	Create a new instance of the class with all parameters copied over.
from_json(json_str)	Import an gaitmap object from its json representation.
get_params([deep])	Get parameters for this algorithm.
set_params(**params)	Set the parameters of this Algorithm.
to_json()	Export the current object parameters as json.

__init__(target_axis: str = 'y', pca_plane_axis: Sequence[str] = ('gyr_x', 'gyr_y')) → None

align(data: DataFrame | dict[Union[collections.abc.Hashable, str], pandas.core.frame.DataFrame], **_) → Self

Align sensor data.

clone() → Self

Create a new instance of the class with all parameters copied over.

This will create a new instance of the class itself and all nested objects

classmethod from_json(json_str: str) → Self

Import an gaitmap object from its json representation.

For details have a look at the this example.

You can use the to_json method of a class to export it as a compatible json string.

Parameters:

json_str

json formatted string

get_params(deep: bool = True) → dict[str, Any]

Get parameters for this algorithm.

Parameters:

deep

Only relevant if object contains nested algorithm objects. If this is the case and deep is True, the params of these nested objects are included in the output using a prefix like nested_object_name__ (Note the two “_” at the end)

Returns:

params

Parameter names mapped to their values.

set_params(**params: Any) → Self

Set the parameters of this Algorithm.

To set parameters of nested objects use nested_object_name__para_name=.

to_json() → str

Export the current object parameters as json.

For details have a look at the this example.

You can use the from_json method of any gaitmap algorithm to load the object again.

Warning

This will only export the Parameters of the instance, but not any results!

Examples using gaitmap.preprocessing.sensor_alignment.PcaAlignment

Automatic sensor alignment

Automatic sensor alignment

Automatic sensor alignment (detailed)

Automatic sensor alignment (detailed)