We investigate the advantage of a two-step approach in the recovery of Compressed Sensing (CS) encoded signals in a realistic environment. First, the support of the signal is computed from the compressed measurements exploiting a Deep Neural Network (DNN). Once the support is known, the input signal can be easily recovered by a pseudoinverse operation. We consider a case study involving realistic biomedical signals and a processing architecture based on a limited precision fixed-point arithmetic unit for the implementation of the DNN and the pseudoinverse operation. In this setting, we show that the proposed approach results in a performance improvement of more than 5 dB in terms of average reconstructed signal to noise ratio (ARSNR) compared to CS state-of-the-art approach. This has been possible thanks to two main contributions reported in this paper. The first one is a theoretical investigation of the relationship between the definition of support and both the properties of the input signal and the adopted compression technique. The second one relies on replacing the pseudoinverse operation with a least mean square filter, whose small sensitivity to numerical errors grants advantages in architectures relying on limited precision fixed-point arithmetic units.
Deep Neural Oracle with Support Identification in the Compressed Domain / Prono, L.; Mangia, M.; Marchioni, A.; Pareschi, F.; Rovatti, R.; Setti, G.. - In: IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS. - ISSN 2156-3357. - STAMPA. - 10:4(2020), pp. 458-468. [10.1109/JETCAS.2020.3039731]
Deep Neural Oracle with Support Identification in the Compressed Domain
Prono L.;Pareschi F.;Setti G.
2020
Abstract
We investigate the advantage of a two-step approach in the recovery of Compressed Sensing (CS) encoded signals in a realistic environment. First, the support of the signal is computed from the compressed measurements exploiting a Deep Neural Network (DNN). Once the support is known, the input signal can be easily recovered by a pseudoinverse operation. We consider a case study involving realistic biomedical signals and a processing architecture based on a limited precision fixed-point arithmetic unit for the implementation of the DNN and the pseudoinverse operation. In this setting, we show that the proposed approach results in a performance improvement of more than 5 dB in terms of average reconstructed signal to noise ratio (ARSNR) compared to CS state-of-the-art approach. This has been possible thanks to two main contributions reported in this paper. The first one is a theoretical investigation of the relationship between the definition of support and both the properties of the input signal and the adopted compression technique. The second one relies on replacing the pseudoinverse operation with a least mean square filter, whose small sensitivity to numerical errors grants advantages in architectures relying on limited precision fixed-point arithmetic units.File | Dimensione | Formato | |
---|---|---|---|
JETCAS3039731.pdf
accesso aperto
Descrizione: Author version of the Paper
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
928.21 kB
Formato
Adobe PDF
|
928.21 kB | Adobe PDF | Visualizza/Apri |
Deep_Neural_Oracle_With_Support_Identification_in_the_Compressed_Domain.pdf
accesso riservato
Descrizione: Editorial Version
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
2.25 MB
Formato
Adobe PDF
|
2.25 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2917957