| Title: | SABER : symbolic regression-based angle of arrival and beam pattern estimator |
|---|
| Authors: | ID Chou, Shih-Kai, Institut "Jožef Stefan" (Author)
ID Zhao, Mengran (Author)
ID Hu, Cheng-Nan (Author)
ID Chou, Kuang-Chung (Author)
ID Fortuna, Carolina, Institut "Jožef Stefan" (Author)
ID Hribar, Jernej, Institut "Jožef Stefan" (Author) |
|---|
| Files: |  URL - Source URL, visit https://ieeexplore.ieee.org/document/11494930
 PDF - Presentation file, download (2,37 MB)
MD5: EDB3C987686F9981759FBEBF94113985
|
|---|
| Language: | English |
|---|
| Typology: | 1.01 - Original Scientific Article |
|---|
| Organization: |  IJS - Jožef Stefan Institute
|
|---|
| Abstract: | Accurate angle-of-arrival (AoA) estimation is essential for next-generation wireless communication systems to enable reliable beamforming, high-precision localization, and integrated sensing. Unfortunately, classical high-resolution techniques require multielement arrays and extensive snapshot collection, while generic machine-learning (ML) approaches often yield black-box models that lack physical interpretability. To address these limitations, we propose a symbolic regression (SR)-based ML framework. Namely, symbolic regression-based angle of arrival and beam pattern estimator (SABER), a constrained SR framework that automatically discovers closed-form beam pattern and AoA models from path loss measurements with interpretability. SABER achieves high accuracy while bridging the gap between opaque ML methods and interpretable physics-driven estimators. First, we validate our approach in a controlled free-space anechoic chamber, showing that both direct inversion of the known cos[sup]n beam and a low-order polynomial surrogate achieve sub-0.5° mean absolute error (MAE). A purely unconstrained SR method can further reduce the error of the predicted angles, but produces complex formulas that lack physical insight. Then, we implement the same SR-learned inversions in a real-world, reconfigurable intelligent surface (RIS)-aided indoor testbed. SABER and unconstrained SR models accurately recover the true AoA with near-zero error. Finally, we benchmark SABER against the Cramér–Rao lower bounds (CRLBs). Our results demonstrate that SABER is an interpretable and accurate alternative to state-of-the-art and black-box ML-based methods for AoA estimation. |
|---|
| Keywords: | angle of arrival, estimation, reconfigurable intelligent surface, symbolic regression |
|---|
| Publication status: | Published |
|---|
| Publication version: | Version of Record |
|---|
| Submitted for review: | 30.10.2025 |
|---|
| Article acceptance date: | 07.04.2026 |
|---|
| Publication date: | 07.05.2026 |
|---|
| Publisher: | IEEE |
|---|
| Year of publishing: | 2026 |
|---|
| Number of pages: | str. [1-13] |
|---|
| Numbering: | Vol. 75, article no. 5501213 |
|---|
| Source: | ZDA |
|---|
| PID: | 20.500.12556/DiRROS-29348  |
|---|
| UDC: | 004.8 |
|---|
| ISSN on article: | 1557-9662 |
|---|
| DOI: | 10.1109/TIM.2026.3687328 |
|---|
| COBISS.SI-ID: | 277527043 |
|---|
| Copyright: | © 2026 The Authors. |
|---|
| Note: | Nasl. z nasl. zaslona;
Soavtorja iz Slovenije: Carolina Fortuna, Jernej Hribar;
Opis vira z dne 8. 5. 2026;
|
|---|
| Publication date in DiRROS: | 11.05.2026 |
|---|
| Views: | 50 |
|---|
| Downloads: | 22 |
|---|
| Metadata: |    |
|---|
|
:
|
Copy citation |
|---|
| | | | Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
