A Comparison Study between Non-parameterized and Parameterized Time-Frequency Representation for Non-stationary Signals

Time-frequency representation (TFR), revealing time and frequency features of signals simultaneously, has attracted increasingly attention in non-stationary signal processing. The existing TFRs can be mainly divided into two categories: non-parameterized and parameterized TFRs. The former has been widely applied on various non-stationary signals, while the latter is of particular interesting since it adopts signal-dependent parameters. A TFR cannot be effective in all applications, so it is necessary to evaluate different TFR candidates and select the optimal one for the specified task. To assist the selection in real practice, several typical TFRs belonging to these two categories are evaluated in this paper. All TFRs are evaluated in terms of the four aspects: the computational complexity, the readability of the representation and easiness of the interpretation, the resolution and concentration, as well as the estimation accuracy of instantaneous frequency (IF).