🤖 AI Summary
Source number estimation in array signal processing suffers from poor robustness under limited snapshots, multiple sources, and non-ideal noise—including white Gaussian noise, spatially colored Gaussian noise, and heavy-tailed noise.
Method: This paper proposes a parameter-free source number estimation method based on the angular distribution of the signal subspace. It models the angular statistical characteristics of the received signal subspace as discriminative features, derives their asymptotic distributions under various noise models using random matrix theory, and constructs a nonparametric hypothesis testing framework for unified robust modeling across diverse noise environments.
Contribution/Results: The method requires no prior noise knowledge or manually tuned thresholds. It significantly outperforms classical approaches—including AIC, MDL, and eigenvalue-splitting methods—under low snapshot and multiple-source conditions. Simulation results demonstrate an average detection accuracy improvement exceeding 30%.
📝 Abstract
Source enumeration, the task of estimating the number of sources from the signal received by the array of antennas, is a critical problem in array signal processing. Numerous methods have been proposed to estimate the number of sources under white or colored Gaussian noise. However, their performance degrades significantly in the presence of a limited number of observations and/or a large number of sources. In this work, we propose a method based on the distribution of angles that performs well in (a) independent Gaussian, (b) spatially colored Gaussian, and (c) heavy-tailed noise, even when the number of sources is large. We support the supremacy of our algorithm over state-of-the-art methods with extensive simulation results.