List of available features

The following table provides an overview of the available featurest in the current version of TSFEL.



Computes the absolute energy of the signal.

auc(signal, fs)

Computes the area under the curve of the signal computed with trapezoid rule.


Calculates the first 1/e crossing of the autocorrelation function (ACF).

average_power(signal, fs)

Computes the average power of the signal.

calc_centroid(signal, fs)

Computes the centroid along the time axis.


Computes the maximum value of the signal.


Computes mean value of the signal.


Computes median of the signal.


Computes the minimum value of the signal.


Computes standard deviation (std) of the signal.


Computes variance of the signal.


Computes the Detrended Fluctuation Analysis (DFA) of the signal.


Computes signal traveled distance.

ecdf(signal[, d])

Computes the values of ECDF (empirical cumulative distribution function) along the time axis.

ecdf_percentile(signal[, percentile])

Computes the percentile value of the ECDF.

ecdf_percentile_count(signal[, percentile])

Computes the cumulative sum of samples that are less than the percentile.

ecdf_slope(signal[, p_init, p_end])

Computes the slope of the ECDF between two percentiles.

entropy(signal[, prob])

Computes the entropy of the signal using the Shannon Entropy.

fft_mean_coeff(signal, fs[, nfreq])

Computes the mean value of each spectrogram frequency.

fundamental_frequency(signal, fs)

Computes fundamental frequency of the signal.


Computes the fractal dimension of a signal using Higuchi's method (HFD).

hist(signal[, nbins, r])

Computes histogram of the signal.

human_range_energy(signal, fs)

Computes the human range energy ratio.


Computes the Hurst exponent of the signal through the Rescaled range (R/S) analysis.


Computes interquartile range of the signal.


Computes kurtosis of the signal.

lempel_ziv(signal[, threshold])

Computes the Lempel-Ziv's (LZ) complexity index, normalized by the signal's length.

lpcc(signal[, n_coeff])

Computes the linear prediction cepstral coefficients.

max_frequency(signal, fs)

Computes maximum frequency of the signal.

max_power_spectrum(signal, fs)

Computes maximum power spectrum density of the signal.


Computes the Maximum Fractal Length (MFL) of the signal, which is the average length at the smallest scale, measured from the logarithmic plot determining FD.


Computes mean absolute deviation of the signal.


Computes mean absolute differences of the signal.


Computes mean of differences of the signal.


Computes median absolute deviation of the signal.


Computes median absolute differences of the signal.


Computes median of differences of the signal.

median_frequency(signal, fs)

Computes median frequency of the signal.

mfcc(signal, fs[, pre_emphasis, nfft, ...])

Computes the MEL cepstral coefficients.

mse(signal[, m, maxscale, tolerance])

Computes the Multiscale entropy (MSE) of the signal, that performs the entropy analysis over multiple time scales.


Computes number of negative turning points of the signal.

neighbourhood_peaks(signal[, n])

Computes the number of peaks from a defined neighbourhood of the signal.


Computes the Petrosian Fractal Dimension of a signal.


Computes the peak to peak distance.


Computes number of positive turning points of the signal.

power_bandwidth(signal, fs)

Computes power spectrum density bandwidth of the signal.


Computes root mean square of the signal.


Computes skewness of the signal.


Computes the slope of the signal.

spectral_centroid(signal, fs)

Barycenter of the spectrum.

spectral_decrease(signal, fs)

Represents the amount of decreasing of the spectra amplitude.

spectral_distance(signal, fs)

Computes the signal spectral distance.

spectral_entropy(signal, fs)

Computes the spectral entropy of the signal based on Fourier transform.

spectral_kurtosis(signal, fs)

Measures the flatness of a distribution around its mean value.

spectral_positive_turning(signal, fs)

Computes number of positive turning points of the fft magnitude signal.

spectral_roll_off(signal, fs)

Computes the spectral roll-off of the signal.

spectral_roll_on(signal, fs)

Computes the spectral roll-on of the signal.

spectral_skewness(signal, fs)

Measures the asymmetry of a distribution around its mean value.

spectral_slope(signal, fs)

Computes the spectral slope.

spectral_spread(signal, fs)

Measures the spread of the spectrum around its mean value.

spectral_variation(signal, fs)

Computes the amount of variation of the spectrum along time.


Computes sum of absolute differences of the signal.

wavelet_abs_mean(signal[, function, widths])

Computes CWT absolute mean value of each wavelet scale.

wavelet_energy(signal[, function, widths])

Computes CWT energy of each wavelet scale.

wavelet_entropy(signal[, function, widths])

Computes CWT entropy of the signal.

wavelet_std(signal[, function, widths])

Computes CWT std value of each wavelet scale.

wavelet_var(signal[, function, widths])

Computes CWT variance value of each wavelet scale.


Computes Zero-crossing rate of the signal.