From: Review and classification of variability analysis techniques with clinical applications
Domain Assumptions | Features | Feature Assumptions | Transformation used | References |
---|---|---|---|---|
The information is held in the degree of complexity, therefore: distance from periodicity and stochasticity, distance from a reference model, distance from a precedent pattern within the data | Approximate entropy | Â | Â | |
 | Conditional entropy |  | Bins | [25] |
 | Compression entropy |  |  | |
 | Fuzzy entropy |  |  | |
 | Kullback-Leibler permutation entropy |  | Symbolic dynamics and phase space representation | [82] |
 | Multiscale entropy | The complexity changes depending on the window length used in the analysis |  | |
 | Predictive-based features | The data follows a model, and the deviation (prediction error) from that model describes changes in the system. | Multiple | |
 | Sample entropy |  |  | |
 | Shannon entropy |  | Bins | |
 | Similarity indexes | The comparison of the properties of two successive windows allows the detection of changes in a time series | Multiple | |
 | Rényi entropy | Bins | [25] |  |