EntropyHub

EntropyHub implements entropic time-series and image analysis methods to quantify regularity, variability, and randomness in biomedical engineering, finance, and related research fields.

Key Features:

• Collection of entropy measures: Provides over forty implemented entropy functions covering cross-entropy, multiscale cross-entropy, and bidimensional (image) entropy.
• Theoretical foundations: Integrates methods originating from information theory and dynamical-systems theory.
• Data modality support: Applies to both time-series and bidimensional image data for analysis of variability and complexity.
• Function parameterization: Each function accepts multiple parameters via keyword arguments to control calculation settings.

Scientific Applications:

• Biomedical engineering: Quantifies regularity, variability, and randomness in physiological time series and image data for biomedical research.
• Finance: Assesses complexity and variability in financial time series to study market dynamics.
• Comparative entropic analysis: Enables side-by-side comparison of established entropy measures within a unified computational framework.

Methodology:

Implements entropy measures from information theory and dynamical-systems theory—specifically cross-entropy, multiscale cross-entropy, and bidimensional entropy—with functions parameterized through keyword arguments.