Mecklenbräuker, C. F., Gerstoft, P., Ollila, E., & Park, Y. (2023). Robust Sparse Bayesian Learning for DOA. In 2023 31st European Signal Processing Conference (EUSIPCO) (pp. 1788–1792). https://doi.org/10.23919/EUSIPCO58844.2023.10289816
2023 31st European Signal Processing Conference (EUSIPCO)
-
ISBN:
978-9-4645-9360-0
-
Date (published):
4-Sep-2023
-
Event name:
31st European Signal Processing Conference (EUSIPCO 2023)
en
Event date:
4-Sep-2023 - 8-Sep-2023
-
Event place:
Helsinki, Finland
-
Number of Pages:
5
-
Keywords:
sparsity; array processing; direction of arrival estimation
en
Abstract:
We formulate statistically robust Sparse Bayesian Learning (SBL) for Direction of Arrival (DOA) estimation from Complex Elliptically Symmetric (CES) data using a general approach based on loss functions. Simulation results for DOA estimation are obtained for several choices of loss functions: Gauss, multivariate t (MVT), Huber, and Tyler. The root mean square DOA error is discussed for Gaussian, MVT, and ε-contaminated data. The robust SBL estimators perform well in the presence of outliers and for heavy-tailed data and almost like classical SBL for Gaussian data.
