Key points are not available for this paper at this time.
It is known that model uncertainties impose fundamental limits on the sensitivity of purely energy-based detectors. Feature detectors are sometimes proposed as being robust to uncertainties of the type that limit energy detectors because they can exploit more detailed structures of the signals to be detected. We show that natural model uncertainties for wireless environments lead to fundamental limits on the sensitivity of cyclostationary feature detectors as well - leading to "SNR Walls" beyond which robust detection is impossible, no matter how long the observations are.
Tandra et al. (Sun,) studied this question.