An implementation of the Cohen's class time-frequency distributions on a massively parallel processor

A time-frequency signal analysis (TFSA) refers to processing of signals with a time-varying frequency content. These non-stationary signals are best represented by the time-frequency distributions, which show how the energy of the signal is distributed over a two-dimensional time-frequency space. Real time processing of these non-stationary signals demands the computational performance of a few giga operations per second, which cannot be obtained using the single or multi core processors. The required computing power can be provided by the massively parallel processors. The paper presents an implementation of the Cohen's class time-frequency representations on a massively parallel processor.