- Example 1: Sample Entropy
- Example 2: (Fine-grained) Permutation Entropy
- Example 3: Phase Entropy w/ Second Order Difference Plot
- Example 4: Cross-Distribution Entropy w/ Different Binning Methods
- Example 5: Multiscale Entropy Object - MSobject()
- Example 6: Multiscale Increment Entropy
- Example 7: Refined Multiscale Sample Entropy
- Example 8: Composite Multiscale Cross-Approximate Entropy
- Example 9: Hierarchical Multiscale corrected Cross-Conditional Entropy
- Example 10: Bidimensional Fuzzy Entropy
- Example 11: Multivariate Dispersion Entropy
- Example 12: [Generalized] Refined-composite Multivariate Multiscale Fuzzy Entropy
- Example 13: Window Data Tool
Examples:
The following sections provide some basic examples of EntropyHub functions. These examples are merely a snippet of the full range of EntropyHub functionality.
In the following examples, signals / data are imported into Julia using the ExampleData() function. To use this function as shown in the examples below, an internet connection is required.
Parameters of the base or cross- entropy methods are passed to multiscale and multiscale cross- functions using the multiscale entropy object using MSobject. Base and cross- entropy methods are declared with MSobject() using any Base or Cross- entropy function. See the MSobject example in the following sections for more info.
In hierarchical multiscale entropy (hMSEn) and hierarchical multiscale cross-entropy (hXMSEn) functions, the length of the time series signal(s) is halved at each scale. Thus, hMSEn and hXMSEn only use the first 2^N data points where 2^N <= the length of the original time series signal. i.e. For a signal of 5000 points, only the first 4096 are used. For a signal of 1500 points, only the first 1024 are used.
Each bidimensional entropy function (SampEn2D, FuzzEn2D, DistEn2D, EspEn2D) has an important keyword argument - Lock. Bidimensional entropy functions are "locked" by default (Lock == true) to only permit matrices with a maximum size of 128 x 128.