Infometrics¶
How complex/irregular is my signal?
Features in the cobrabox.infometrics domain. Access them as cb.<Feature> (canonical), or as cb.infometrics.<Feature> / cb.feature.<Feature>.
Each feature has two forms: a class for building pipelines, and a one-shot function for a single call.
AmplitudeEntropy¶
Compute amplitude entropy from time-series data using histogram-based probability estimation.
cb.amplitude_entropy(data, ...) # one-shot
cb.AmplitudeEntropy(...).apply(data) # composable, for pipelines
Tags: shannon-entropy, histogram, probability-distribution, eeg, io:scalar-per-channel
FractalDimension¶
Compute fractal dimension over the time dimension.
cb.fractal_dimension(data, ...) # one-shot
cb.FractalDimension(...).apply(data) # composable, for pipelines
Tags: fractal, self-similarity, higuchi, katz, box-counting, aging, anesthesia, dementia, eeg, io:scalar-per-channel
LempelZiv¶
Compute Lempel-Ziv Complexity (LZC) over the time dimension.
Tags: compression, algorithmic-complexity, binary, epilepsy, anesthesia, consciousness, eeg, io:scalar-per-channel
Nonreversibility¶
Compute dc_norm: normalised deviation from causal normality (time-irreversibility).
cb.nonreversibility(data, ...) # one-shot
cb.Nonreversibility(...).apply(data) # composable, for pipelines
Tags: time-irreversibility, causality, kl-divergence, entropy-production, mvar, epilepsy, nonlinear-dynamics, eeg, io:scalar-per-channel
RecurrenceMatrix¶
Compute a pairwise recurrence (self-similarity) matrix from a time-series.
cb.recurrence_matrix(data, ...) # one-shot
cb.RecurrenceMatrix(...).apply(data) # composable, for pipelines
Tags: dynamical-systems, self-similarity, state-space, functional-connectivity, epilepsy, nonlinear-dynamics, eeg, io:matrix
SampleEntropy¶
Sample Entropy feature.
cb.sample_entropy(data, ...) # one-shot
cb.SampleEntropy(...).apply(data) # composable, for pipelines
Tags: entropy, regularity, predictability, dynamical-systems, heart-rate-variability, epilepsy, anesthesia, eeg, ecg, io:scalar-per-channel