Temporal CNN over I/Q (T=128). Classical
path: StandardScaler + RF/SVM/GBM/KNN on handcrafted
features. Features (16): RMS, PAPR, µI , µQ, σ
2
I
, σ2
Q, zerocrossings (I/Q), lag-1 autocorr (Re/Im), spectral centroid,
spectral bandwidth, spectral flatness, peak ratio, low/high band
energy. Co-training: Iterative agreement with confidence ≥ τ
pseudo-labels, up to M per round for R rounds. Metrics:
macro-AUROC with 95% CIs over seeds.