In 2019 27th European Signal Processing Conference (EUSIPCO), pages 1-5, Sep., 2019. Paper doi abstract bibtex
Jointly detecting a signal in noise and, in case a signal is present, estimating the Signal-to-Noise Ratio (SNR) is investigated in a sequential setup. The sequential test is designed such that it achieves desired error probabilities and Mean-Squared Errors (MSEs), while the expected number of samples is minimized. This problem is first converted to an unconstrained problem, which is then reduced to an optimal stopping problem. The solution, which is obtained by means of dynamic programming, is characterized by a non-linear Bellman equation. A gradient ascent approach is then presented to select the cost coefficients of the Bellman equation such that the desired error probabilities and MSEs are achieved. A numerical example concludes the work.