DOA Uncertainty Quantification With Conformal Prediction

Uncertainty quantification (UQ) of deep learning-based estimation methods can establish confidence in the predictions. We use conformal prediction (CP) for uncertainty quantification in DOA estimation. CP is a statistically rigorous method to provide confidence intervals for an estimated quantity without making distributional assumptions. CP confidence intervals are computed via quantiles of user-defined scores. This easy-to-use method can be applied to any trained classification/regression model as long as an appropriate score function is chosen. The approach shows the potential to enhance the real-time applicability of deep learning methods for DOA. Codes are on GitHub (Link: Conformal Prediction).