I am selecting a distribution for MIT-BIH arrhythmia data that is ECG data which follows AAMI standards. Let distribution $A$ : $D(\mathbb{R}) \subset L^{2}(\mathbb{R})$ such that
\begin{equation} A : D(\mathbb{R}) \to L^{2}(\mathbb{R} \times \mathbb{R}) \end{equation} but because the digital signal that is all frequencies above Nyquist frequency are removed, I would choose and make the signal bounded above by redefining \begin{equation} A : D(\mathbb{R}) \to D(\mathbb{R} \times \mathbb{R}). \end{equation} where $D(\mathbb{R} \times \mathbb{R}) \subset L^{2}(\mathbb{R} \times \mathbb{R})$.
The distribution $A$ is like Wigner-Ville Distribution but Quadratic. It is quadratic nonlinear Time-Frequency Representation.
Is there any sense of selecting the range dense here for ECG signal?
