name: CorrelationEntropy : public AlgorithmBase

synopsis:

g++ [flags ...] file ... -l /isip/tools/lib/$ISIP_BINARY/lib_algo.a

#include <CorrelationEntropy.h>

CorrelationEntropy(ALGORITHM algorithm = DEF_ALGORITHM, IMPLEMENTATION implementation = DEF_IMPLEMENTATION, EMBEDDING embedding = DEF_EMBEDDING, float epsilon = DEF_EPSILON, long embed_dim_min = DEF_EMBED_DIM_MIN, long embed_dim_max = DEF_EMBED_DIM_MAX, long theiler_correction = DEF_THEILER_CORRECTION, long svd_window_size = DEF_SVD_WINDOW_SIZE, float delay = DEF_DELAY);
boolean eq(const CorrelationEntropy& arg) const;
boolean compute(VectorFloat& output, const VectorFloat& input, AlgorithmData::COEF_TYPE coef_type = DEF_COEF_TYPE, long channel_index = DEF_CHANNEL_INDEX);
quick start:

VectorFloat input;
input.assign(L"1.0, 2.0, 3.0, 6.0, 5.0, 4.0, 7.0, 8.0, 9.0");
VectorFloat output;
CorrelationEntropy correntpy;
correntpy.compute(output, input);
description:

The CorrelationEntropy class is designed to estimate the second order Kolmogorov-Sinai entropy of an attractor's trajectory. It takes as input the time series and outputs a vector of correlation entropies, corresponding to a range of embedding dimensions. A good overview of methods to estimate the correlation entropy can be found in: The mathematical descriptions of the algorithm is provided below for reference purposes:


Two types of attractor reconstruction (embedding) are currently supported: TIME_DELAY, and, SVD.

dependencies:

public constants:

error codes:

protected data:

required public methods:

class-specific public methods:

private methods:

examples:

notes: