Conformal Prediction-Aware DOA Tracking
arXiv:2610.39566
Abstract
We introduce an uncertainty-aware DOA-tracking framework combining deep posterior estimation, conformal-prediction calibration, and temporal smoothing. The approach enhances stability against reverberation and burst-like directional noise, yielding more reliable trajectories and greater robustness than conventional DOA-tracking methods.
arXiv commentPresented at the 2026 Israeli Conference on Systems and Electrical Engineering (ICSEE 2026)