Ensemble modulation classifiers promise robustnessagainst domain shift and label noise, but each added modelincreases inference latency and energy consumption. For realtime RF spectrum surveillance and signal intelligence workloads,those costs directly bound how many emitters can be tracked pernode and how quickly rare events can be surfaced.This paper quantifies the latency and energy trade-offs ofscaling the … Continue reading Ensemble Size vs Latency and Energy on CPU/GPU for RF Modulation Ensembles