We quantify the impact of input sanitation strategies—nan_to_num, zero-padding, and linear interpolation—onclassification error and latency under controlled NaN corruptionof IQ streams. We integrate sanitation hooks in temporal andspectral feature builders and systematically evaluate robustnessacross corruption ratios. Our analysis reveals that linear interpolation typically dominates at low-to-moderate corruption levels,while nan_to_num offers the fastest processing but introducesthe … Continue reading Robustness to Missing Samples in RF Classification Ensembles: NaN Sanitation Strategies Compared