ApproximateEntropySelector<T>
Models & Types · AiDotNet.Preprocessing.FeatureSelection.Entropy
Approximate Entropy (ApEn) based Feature Selection.
Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> → ApproximateEntropySelector<T>
Implements: IFixedCountFeatureSelector<T>
For Beginners
Approximate entropy measures how likely it is that similar patterns in a sequence remain similar when extended by one point. Low ApEn means the sequence is predictable (patterns repeat); high ApEn means it’s complex and hard to predict. Often used for physiological signals.
How It Works
Selects features based on their approximate entropy, which quantifies the unpredictability and complexity of time series data.
Constructors
| Constructor | Summary |
|---|---|
ApproximateEntropySelector(int nFeaturesToSelect, int embeddingDimension, double tolerance, int[] columnIndices) |
Properties
| Property | Summary |
|---|---|
Vector<T> ApEnValues { get; } |
|
bool SupportsInverseTransform { get; } |
|
double Tolerance { get; } |
|
int EmbeddingDimension { get; } |
|
int NFeaturesToSelect { get; } |
|
int[] SelectedIndices { get; } |
Methods
| Method | Summary |
|---|---|
Matrix<T> FitTransform(Matrix<T> data) |
|
bool[] GetSupportMask() |
|
string[] GetFeatureNamesOut(string[] inputFeatureNames) |