Signal Features (skdh.features)

Combined Feature Processing

Bank([bank_file])

A feature bank object for ease in creating a table or pipeline of features to be computed.

Signal Features

Mean()	The signal mean.
MeanCrossRate()	Number of signal mean value crossings.
StdDev()	The signal standard deviation
Skewness()	The skewness of a signal.
Kurtosis()	The kurtosis of a signal.
Range()	The difference between the maximum and minimum value.
IQR()	The difference between the 75th percentile and 25th percentile of the values.
RMS()	The root mean square value of the signal
Autocorrelation([lag, normalize])	The similarity in profile between the signal and a time shifted version of the signal.
LinearSlope()	The slope from linear regression of the signal
SignalEntropy()	A Measure of the information contained in a signal.
SampleEntropy([m, r])	A measure of the complexity of a time-series signal.
PermutationEntropy([order, delay, normalize])	A meausure of the signal complexity.
DominantFrequency([padlevel, low_cutoff, ...])	The primary frequency in the signal.
DominantFrequencyValue([padlevel, ...])	The power spectral density maximum value.
PowerSpectralSum([padlevel, low_cutoff, ...])	Sum of power spectral density values.
SpectralFlatness([padlevel, low_cutoff, ...])	A measure of the "tonality" or resonant structure of a signal.
SpectralEntropy([padlevel, low_cutoff, ...])	A measure of the information contained in the power spectral density estimate.
ComplexityInvariantDistance([normalize])	A distance metric that accounts for signal complexity.
RangeCountPercentage([range_min, range_max])	The percent of the signal that falls between specified values
RatioBeyondRSigma([r])	The percent of the signal outside \(r\) standard deviations from the mean.
JerkMetric()	The normalized sum of jerk.
DimensionlessJerk([log, signal_type])	The dimensionless normalized sum of jerk, or its log value.
SPARC([padlevel, fc, amplitude_threshold])	A quantitative measure of the smoothness of a signal.
DetailPower([wavelet, freq_band])	The summed power in the detail levels that span the chosen frequency band.
DetailPowerRatio([wavelet, freq_band])	The ratio of the power in the detail signals that span the specified frequency band.