SBCS-Net: Sparse Bayesian and Deep Learning Framework for Compressed Sensing in Sensor Networks
Compressed sensing is widely used in modern resource-constrained sensor networks. However, achieving high-quality and robust signal reconstruction under low sampling rates and noise interference remains challenging. Traditional CS methods have limited performance, so many deep learning-based CS mode...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/15/4559 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849239535906455552 |
|---|---|
| author | Xianwei Gao Xiang Yao Bi Chen Honghao Zhang |
| author_facet | Xianwei Gao Xiang Yao Bi Chen Honghao Zhang |
| author_sort | Xianwei Gao |
| collection | DOAJ |
| description | Compressed sensing is widely used in modern resource-constrained sensor networks. However, achieving high-quality and robust signal reconstruction under low sampling rates and noise interference remains challenging. Traditional CS methods have limited performance, so many deep learning-based CS models have been proposed. Although these models show strong fitting capabilities, they often lack the ability to handle complex noise in sensor networks, which affects their performance stability. To address these challenges, this paper proposes SBCS-Net. This framework innovatively expands the iterative process of sparse Bayesian compressed sensing using convolutional neural networks and Transformer. The core of SBCS-Net is to optimize key SBL parameters through end-to-end learning. This can adaptively improve signal sparsity and probabilistically process measurement noise, while fully leveraging the powerful feature extraction and global context modeling capabilities of deep learning modules. To comprehensively evaluate its performance, we conduct systematic experiments on multiple public benchmark datasets. These studies include comparisons with various advanced and traditional compressed sensing methods, comprehensive noise robustness tests, ablation studies of key components, computational complexity analysis, and rigorous statistical significance tests. Extensive experimental results consistently show that SBCS-Net outperforms many mainstream methods in both reconstruction accuracy and visual quality. In particular, it exhibits excellent robustness under challenging conditions such as extremely low sampling rates and strong noise. Therefore, SBCS-Net provides an effective solution for high-fidelity, robust signal recovery in sensor networks and related fields. |
| format | Article |
| id | doaj-art-b2f41f01ce2b4a68b03558d347efe24a |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-b2f41f01ce2b4a68b03558d347efe24a2025-08-20T04:00:55ZengMDPI AGSensors1424-82202025-07-012515455910.3390/s25154559SBCS-Net: Sparse Bayesian and Deep Learning Framework for Compressed Sensing in Sensor NetworksXianwei Gao0Xiang Yao1Bi Chen2Honghao Zhang3Beijing Electronic Science and Technology Institute, Beijing 100070, ChinaBeijing Electronic Science and Technology Institute, Beijing 100070, ChinaBeijing Electronic Science and Technology Institute, Beijing 100070, ChinaBeijing Electronic Science and Technology Institute, Beijing 100070, ChinaCompressed sensing is widely used in modern resource-constrained sensor networks. However, achieving high-quality and robust signal reconstruction under low sampling rates and noise interference remains challenging. Traditional CS methods have limited performance, so many deep learning-based CS models have been proposed. Although these models show strong fitting capabilities, they often lack the ability to handle complex noise in sensor networks, which affects their performance stability. To address these challenges, this paper proposes SBCS-Net. This framework innovatively expands the iterative process of sparse Bayesian compressed sensing using convolutional neural networks and Transformer. The core of SBCS-Net is to optimize key SBL parameters through end-to-end learning. This can adaptively improve signal sparsity and probabilistically process measurement noise, while fully leveraging the powerful feature extraction and global context modeling capabilities of deep learning modules. To comprehensively evaluate its performance, we conduct systematic experiments on multiple public benchmark datasets. These studies include comparisons with various advanced and traditional compressed sensing methods, comprehensive noise robustness tests, ablation studies of key components, computational complexity analysis, and rigorous statistical significance tests. Extensive experimental results consistently show that SBCS-Net outperforms many mainstream methods in both reconstruction accuracy and visual quality. In particular, it exhibits excellent robustness under challenging conditions such as extremely low sampling rates and strong noise. Therefore, SBCS-Net provides an effective solution for high-fidelity, robust signal recovery in sensor networks and related fields.https://www.mdpi.com/1424-8220/25/15/4559compressed sensingsensor networkssparse Bayesian learningdeep learning |
| spellingShingle | Xianwei Gao Xiang Yao Bi Chen Honghao Zhang SBCS-Net: Sparse Bayesian and Deep Learning Framework for Compressed Sensing in Sensor Networks Sensors compressed sensing sensor networks sparse Bayesian learning deep learning |
| title | SBCS-Net: Sparse Bayesian and Deep Learning Framework for Compressed Sensing in Sensor Networks |
| title_full | SBCS-Net: Sparse Bayesian and Deep Learning Framework for Compressed Sensing in Sensor Networks |
| title_fullStr | SBCS-Net: Sparse Bayesian and Deep Learning Framework for Compressed Sensing in Sensor Networks |
| title_full_unstemmed | SBCS-Net: Sparse Bayesian and Deep Learning Framework for Compressed Sensing in Sensor Networks |
| title_short | SBCS-Net: Sparse Bayesian and Deep Learning Framework for Compressed Sensing in Sensor Networks |
| title_sort | sbcs net sparse bayesian and deep learning framework for compressed sensing in sensor networks |
| topic | compressed sensing sensor networks sparse Bayesian learning deep learning |
| url | https://www.mdpi.com/1424-8220/25/15/4559 |
| work_keys_str_mv | AT xianweigao sbcsnetsparsebayesiananddeeplearningframeworkforcompressedsensinginsensornetworks AT xiangyao sbcsnetsparsebayesiananddeeplearningframeworkforcompressedsensinginsensornetworks AT bichen sbcsnetsparsebayesiananddeeplearningframeworkforcompressedsensinginsensornetworks AT honghaozhang sbcsnetsparsebayesiananddeeplearningframeworkforcompressedsensinginsensornetworks |