Deep Unfolding of Iteratively Reweighted ADMM for Wireless RF Sensing
We address the detection of material defects, which are inside a layered material structure using compressive sensing-based multiple-input and multiple-output (MIMO) wireless radar. Here, strong clutter due to the reflection of the layered structure’s surface often makes the detection of the defects...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/8/3065 |
| _version_ | 1797443716421517312 |
|---|---|
| author | Udaya S. K. P. Miriya Thanthrige Peter Jung Aydin Sezgin |
| author_facet | Udaya S. K. P. Miriya Thanthrige Peter Jung Aydin Sezgin |
| author_sort | Udaya S. K. P. Miriya Thanthrige |
| collection | DOAJ |
| description | We address the detection of material defects, which are inside a layered material structure using compressive sensing-based multiple-input and multiple-output (MIMO) wireless radar. Here, strong clutter due to the reflection of the layered structure’s surface often makes the detection of the defects challenging. Thus, sophisticated signal separation methods are required for improved defect detection. In many scenarios, the number of defects that we are interested in is limited, and the signaling response of the layered structure can be modeled as a low-rank structure. Therefore, we propose joint rank and sparsity minimization for defect detection. In particular, we propose a non-convex approach based on the iteratively reweighted nuclear and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mo>ℓ</mo><mn>1</mn></msub></mrow></semantics></math></inline-formula>-norm (a double-reweighted approach) to obtain a higher accuracy compared to the conventional nuclear norm and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mo>ℓ</mo><mn>1</mn></msub></mrow></semantics></math></inline-formula>-norm minimization. To this end, an iterative algorithm is designed to estimate the low-rank and sparse contributions. Further, we propose deep learning-based parameter tuning of the algorithm (i.e., algorithm unfolding) to improve the accuracy and the speed of convergence of the algorithm. Our numerical results show that the proposed approach outperforms the conventional approaches in terms of mean squared errors of the recovered low-rank and sparse components and the speed of convergence. |
| first_indexed | 2024-03-09T13:02:03Z |
| format | Article |
| id | doaj.art-bf0867e5a0134d1b81a19a8fd9ca465d |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T13:02:03Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-bf0867e5a0134d1b81a19a8fd9ca465d2023-11-30T21:53:42ZengMDPI AGSensors1424-82202022-04-01228306510.3390/s22083065Deep Unfolding of Iteratively Reweighted ADMM for Wireless RF SensingUdaya S. K. P. Miriya Thanthrige0Peter Jung1Aydin Sezgin2Institute of Digital Communication Systems, Ruhr University Bochum, 44801 Bochum, GermanyInstitute of Communications and Information Theory, Technical University Berlin, 10587 Berlin, GermanyInstitute of Digital Communication Systems, Ruhr University Bochum, 44801 Bochum, GermanyWe address the detection of material defects, which are inside a layered material structure using compressive sensing-based multiple-input and multiple-output (MIMO) wireless radar. Here, strong clutter due to the reflection of the layered structure’s surface often makes the detection of the defects challenging. Thus, sophisticated signal separation methods are required for improved defect detection. In many scenarios, the number of defects that we are interested in is limited, and the signaling response of the layered structure can be modeled as a low-rank structure. Therefore, we propose joint rank and sparsity minimization for defect detection. In particular, we propose a non-convex approach based on the iteratively reweighted nuclear and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mo>ℓ</mo><mn>1</mn></msub></mrow></semantics></math></inline-formula>-norm (a double-reweighted approach) to obtain a higher accuracy compared to the conventional nuclear norm and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mo>ℓ</mo><mn>1</mn></msub></mrow></semantics></math></inline-formula>-norm minimization. To this end, an iterative algorithm is designed to estimate the low-rank and sparse contributions. Further, we propose deep learning-based parameter tuning of the algorithm (i.e., algorithm unfolding) to improve the accuracy and the speed of convergence of the algorithm. Our numerical results show that the proposed approach outperforms the conventional approaches in terms of mean squared errors of the recovered low-rank and sparse components and the speed of convergence.https://www.mdpi.com/1424-8220/22/8/3065algorithm unfoldingclutter suppressiondefects detectioncompressive sensingreweighted norm |
| spellingShingle | Udaya S. K. P. Miriya Thanthrige Peter Jung Aydin Sezgin Deep Unfolding of Iteratively Reweighted ADMM for Wireless RF Sensing Sensors algorithm unfolding clutter suppression defects detection compressive sensing reweighted norm |
| title | Deep Unfolding of Iteratively Reweighted ADMM for Wireless RF Sensing |
| title_full | Deep Unfolding of Iteratively Reweighted ADMM for Wireless RF Sensing |
| title_fullStr | Deep Unfolding of Iteratively Reweighted ADMM for Wireless RF Sensing |
| title_full_unstemmed | Deep Unfolding of Iteratively Reweighted ADMM for Wireless RF Sensing |
| title_short | Deep Unfolding of Iteratively Reweighted ADMM for Wireless RF Sensing |
| title_sort | deep unfolding of iteratively reweighted admm for wireless rf sensing |
| topic | algorithm unfolding clutter suppression defects detection compressive sensing reweighted norm |
| url | https://www.mdpi.com/1424-8220/22/8/3065 |
| work_keys_str_mv | AT udayaskpmiriyathanthrige deepunfoldingofiterativelyreweightedadmmforwirelessrfsensing AT peterjung deepunfoldingofiterativelyreweightedadmmforwirelessrfsensing AT aydinsezgin deepunfoldingofiterativelyreweightedadmmforwirelessrfsensing |