Filters#

Filters are used to preprocess the data before it is used by the model. Some filters can only work on chunked data, while others can work on both chunked and unchunked data.

Generic Filters#

Generic filters e.g. allow the use of custom methods to preprocess the data.

ApplyFunctionFilter(input_is_chunked[, ...])

Filter that applies a function to the input array.

IndexDataFilter(input_is_chunked[, ...])

Filter that indexes the input array using NumPy-style indexing.

ChunkizeDataFilter(input_is_chunked[, ...])

Filter that chunks the input array into overlapping or non-overlapping segments.

IdentityFilter(input_is_chunked[, ...])

Filter that returns the input unchanged.

Temporal Filters#

Temporal filters can be used to compute most EMG features such as the root mean square or the mean absolute value.

SOSFrequencyFilter(input_is_chunked[, ...])

Filter that applies a second-order-section filter to the input array.

RectifyFilter(input_is_chunked[, is_output, ...])

Filter that rectifies the input array.

WindowedFunctionFilter(input_is_chunked[, ...])

Base class for filters that apply a function to windowed data.

RMSFilter(input_is_chunked[, is_output, ...])

Filter that computes the root mean squared value [1]_ of the input array.

VARFilter(input_is_chunked[, is_output, ...])

Filter that computes the variance [1]_ of the input array.

MAVFilter(input_is_chunked[, is_output, ...])

Filter that computes the mean absolute value [1]_ of the input array.

IAVFilter(input_is_chunked[, is_output, ...])

Filter that computes the integrated absolute value [1]_ of the input array.

WFLFilter(input_is_chunked[, is_output, ...])

Filter that computes the waveform length [1]_ of the input array.

ZCFilter(input_is_chunked[, is_output, ...])

Computes the zero crossings [1]_ of the input array.

SSCFilter(input_is_chunked[, is_output, ...])

Computes the slope sign change [1]_ of the input array.

SpectralInterpolationFilter(input_is_chunked)

Filter that removes certain frequency bands from the signal and interpolates the gaps.

Spatial Filters#

Spatial filters can be used to compute spatial features such as the Laplacian.

DifferentialSpatialFilter(input_is_chunked)

Differential spatial filter for EMG data.

ApplyFunctionSpatialFilter(input_is_chunked)

Apply a function over the EMG grids using a user defined kernel.

Base Filter Classes#

Important

If you wish to add a new filter make sure they inherit from the following base classes.

FilterBaseClass(input_is_chunked, ...[, ...])

Base class for filters.

SpatialFilterGridAware([input_is_chunked, ...])

Base class for spatial filters that need to be grid-aware.