Assessment of the classification capability of prediction and approximation methods for HRV analysis

Automated diagnosis of coronary artery disease using tunable-Q wavelet transform applied on heart rate signals

“…In recent past, many nonlinear methods such as Lyapunov exponents [10,22], correlation dimension (D2) [10,29,30], fractal dimension [31][32][33][34][35], 1/f slope [36], approximate entropy [10], detrended fluctuation analysis (DFA) [37,38], Poincare geometry [39][40][41], recurrence quantification analysis (RQA) [42][43][44][45], higher order spectrum (HOS) [46] are studied for diagnosis of CAD. In [38], it is shown that DFA and fractal dimension features exhibited lower values for CAD compared to normal heart rate signals.…”

Automated diagnosis of Coronary Artery Disease affected patients using LDA, PCA, ICA and Discrete Wavelet Transform

“…They are: Lyapunov exponents [1,3], correlation dimension [40,1], fractal dimension [2], 1/f slope [31], approximate entropy (ApEn) [41,1] and Detrended Fluctuation Analysis [39]. Nonlinear parameters like correlation dimension, entropy features were extracted from HRV signals to detect CAD [32,37,42]. It was found that Detrended Fluctuation Analysis (DFA) features and fractal properties of RR interval dynamics were reduced in CAD patients [28].…”

Extension and detailed overview of the HRVFrame framework for heart rate variability analysis

“…Cardiac rhythm, as a specific type of BTS, shows interesting short-and long-scale complex fluctuations [2]. Aside from describing the very nature of these fluctuations, they can be analyzed in order to: model cardiac disorders [3], classify cardiac rhythms [4], predict the onset of cardiac disorders [5], and establish disorder prognosis [6]. The analysis of the fluctuations of the cardiac inter-beat intervals is known as heart rate variability (HRV) analysis.…”