2D Angularly Dependent Array Error Calibration for 1D Array via Neural Network with Local Manifold Interpolation

Simple item page
dc.contributor.authorPan, Yujian
dc.contributor.authorRajendran, Sreeraj
dc.contributor.authorPollin, Sofle
dc.coverage.issue3cs
dc.coverage.volume30cs
dc.date.accessioned2021-11-08T10:24:40Z
dc.date.available2021-11-08T10:24:40Z
dc.date.issued2021-09cs
dc.description.abstractThe calibration of the angularly dependent array error is a challenging task for signal processing. In this paper, we propose a neural network (NN)-based two-dimensional (2D) calibration method for a linear array. Firstly, the array steering vectors are measured on an azimuth grid at different elevations in an anechoic chamber, and the off-grid steering vectors are derived by the proposed local manifold interpolation (LMI) technique to reduce the risk of model overfitting. Then, the phase differences are extracted to form the features of the training data. At last, noise is added to the training data to enable the NN model to generalize well to the noisy data. The proposed method is evaluated by the indoor and outdoor measured data from a 77 GHz automotive radar and is compared with the conventional signal processing-based methods. The evaluation results show that a single NN model trained at the lowest signal-to-noise ratio (SNR) outperforms conventional methods by at least 55% on average over the entire SNR range and gives close performance to the perfect array without array error at low to medium SNR.en
dc.formattextcs
dc.format.extent547-555cs
dc.format.mimetypeapplication/pdfen
dc.identifier.citationRadioengineering. 2021 vol. 30, č. 3, s. 547-555. ISSN 1210-2512cs
dc.identifier.doi10.13164/re.2021.0547en
dc.identifier.issn1210-2512
dc.identifier.urihttp://hdl.handle.net/11012/201827
dc.language.isoencs
dc.publisherSpolečnost pro radioelektronické inženýrstvícs
dc.relation.ispartofRadioengineeringcs
dc.relation.urihttps://www.radioeng.cz/fulltexts/2021/21_03_0547_0555.pdfcs
dc.rightsCreative Commons Attribution 4.0 International licenseen
dc.rights.accessopenAccessen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectAngularly dependent array erroren
dc.subjectautomotive radaren
dc.subjectdirection-of-arrival (DOA) estimationen
dc.subjectlocal manifold interpolationen
dc.subjectneural networken
dc.title2D Angularly Dependent Array Error Calibration for 1D Array via Neural Network with Local Manifold Interpolationen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
eprints.affiliatedInstitution.facultyFakulta eletrotechniky a komunikačních technologiícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
21_03_0547_0555.pdf
Size:
626.75 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
2021/3