Deep Compressed Sensing Generation Model for End-to-End Extreme Observation and Reconstruction
Data transmission and storage are inseparable from compression technology. Compressed sensing directly undersamples and reconstructs data at a much lower sampling frequency than Nyquist, which reduces redundant sampling. However, the requirement of data sparsity in compressed sensing limits its appl...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/23/12176 |
| _version_ | 1797463651807920128 |
|---|---|
| author | Han Diao Xiaozhu Lin Chun Fang |
| author_facet | Han Diao Xiaozhu Lin Chun Fang |
| author_sort | Han Diao |
| collection | DOAJ |
| description | Data transmission and storage are inseparable from compression technology. Compressed sensing directly undersamples and reconstructs data at a much lower sampling frequency than Nyquist, which reduces redundant sampling. However, the requirement of data sparsity in compressed sensing limits its application. The combination of neural network-based generative models and compressed sensing breaks the limitation of data sparsity. Compressed sensing for extreme observations can reduce costs, but the reconstruction effect of the above methods in extreme observations is blurry. We addressed this problem by proposing an end-to-end observation and reconstruction method based on a deep compressed sensing generative model. Under RIP and S-REC, data can be observed and reconstructed from end to end. In MNIST extreme observation and reconstruction, end-to-end feasibility compared to random input is verified. End-to-end reconstruction accuracy improves by 5.20% over random input and SSIM by 0.2200. In the Fashion_MNIST extreme observation and reconstruction, it is verified that the reconstruction effect of the deconvolution generative model is better than that of the multi-layer perceptron. The end-to-end reconstruction accuracy of the deconvolution generative model is 2.49% higher than that of the multi-layer perceptron generative model, and the SSIM is 0.0532 higher. |
| first_indexed | 2024-03-09T17:53:47Z |
| format | Article |
| id | doaj.art-ec318d12f0fe4a61b327dbd58a032c19 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T17:53:47Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-ec318d12f0fe4a61b327dbd58a032c192023-11-24T10:32:13ZengMDPI AGApplied Sciences2076-34172022-11-0112231217610.3390/app122312176Deep Compressed Sensing Generation Model for End-to-End Extreme Observation and ReconstructionHan Diao0Xiaozhu Lin1Chun Fang2College of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, ChinaCollege of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, ChinaCollege of Information Engineering, Beijing Institute of Petrochemical Technology, Beijing 102617, ChinaData transmission and storage are inseparable from compression technology. Compressed sensing directly undersamples and reconstructs data at a much lower sampling frequency than Nyquist, which reduces redundant sampling. However, the requirement of data sparsity in compressed sensing limits its application. The combination of neural network-based generative models and compressed sensing breaks the limitation of data sparsity. Compressed sensing for extreme observations can reduce costs, but the reconstruction effect of the above methods in extreme observations is blurry. We addressed this problem by proposing an end-to-end observation and reconstruction method based on a deep compressed sensing generative model. Under RIP and S-REC, data can be observed and reconstructed from end to end. In MNIST extreme observation and reconstruction, end-to-end feasibility compared to random input is verified. End-to-end reconstruction accuracy improves by 5.20% over random input and SSIM by 0.2200. In the Fashion_MNIST extreme observation and reconstruction, it is verified that the reconstruction effect of the deconvolution generative model is better than that of the multi-layer perceptron. The end-to-end reconstruction accuracy of the deconvolution generative model is 2.49% higher than that of the multi-layer perceptron generative model, and the SSIM is 0.0532 higher.https://www.mdpi.com/2076-3417/12/23/12176compressed sensingdeep learningextreme observationhigh precision reconstructionend-to-end |
| spellingShingle | Han Diao Xiaozhu Lin Chun Fang Deep Compressed Sensing Generation Model for End-to-End Extreme Observation and Reconstruction Applied Sciences compressed sensing deep learning extreme observation high precision reconstruction end-to-end |
| title | Deep Compressed Sensing Generation Model for End-to-End Extreme Observation and Reconstruction |
| title_full | Deep Compressed Sensing Generation Model for End-to-End Extreme Observation and Reconstruction |
| title_fullStr | Deep Compressed Sensing Generation Model for End-to-End Extreme Observation and Reconstruction |
| title_full_unstemmed | Deep Compressed Sensing Generation Model for End-to-End Extreme Observation and Reconstruction |
| title_short | Deep Compressed Sensing Generation Model for End-to-End Extreme Observation and Reconstruction |
| title_sort | deep compressed sensing generation model for end to end extreme observation and reconstruction |
| topic | compressed sensing deep learning extreme observation high precision reconstruction end-to-end |
| url | https://www.mdpi.com/2076-3417/12/23/12176 |
| work_keys_str_mv | AT handiao deepcompressedsensinggenerationmodelforendtoendextremeobservationandreconstruction AT xiaozhulin deepcompressedsensinggenerationmodelforendtoendextremeobservationandreconstruction AT chunfang deepcompressedsensinggenerationmodelforendtoendextremeobservationandreconstruction |