Approaches for reconstructing signals encoded with Compressed Sensing (CS) techniques, and based on Deep Neural Networks (DNNs) are receiving increasing interest in the literature. In a recent work, a new DNN-based method named Trained CS with Support Oracle (TCSSO) is introduced, relying the signal reconstruction on the two separate tasks of support identification and measurements decoding. The aim of this paper is to improve the TCSSO framework by considering actual implementations using a finite-precision hardware. Solutions with low memory footprint and low computation requirements by employing fixed-point notation and by reducing the number of bits employed are considered. Results using synthetic electrocardiogram (ECG) signals as a case study show that this approach, even when used in a constrained-resources scenario, still outperform current state-of-art CS approaches.

Low-power fixed-point compressed sensing decoder with support oracle / Prono, L.; Mangia, M.; Marchioni, A.; Pareschi, F.; Rovatti, R.; Setti, G.. - STAMPA. - 2020:(2020). (Intervento presentato al convegno 52nd IEEE International Symposium on Circuits and Systems, ISCAS 2020 tenutosi a Seville, Spain (Virtual) nel 2020) [10.1109/ISCAS45731.2020.9180502].

Low-power fixed-point compressed sensing decoder with support oracle

Prono L.;Pareschi F.;Setti G.
2020

Abstract

Approaches for reconstructing signals encoded with Compressed Sensing (CS) techniques, and based on Deep Neural Networks (DNNs) are receiving increasing interest in the literature. In a recent work, a new DNN-based method named Trained CS with Support Oracle (TCSSO) is introduced, relying the signal reconstruction on the two separate tasks of support identification and measurements decoding. The aim of this paper is to improve the TCSSO framework by considering actual implementations using a finite-precision hardware. Solutions with low memory footprint and low computation requirements by employing fixed-point notation and by reducing the number of bits employed are considered. Results using synthetic electrocardiogram (ECG) signals as a case study show that this approach, even when used in a constrained-resources scenario, still outperform current state-of-art CS approaches.
2020
978-1-7281-3320-1
File in questo prodotto:
File Dimensione Formato  
ISCAS2020-NNOracle.pdf

accesso aperto

Descrizione: Author version of the Paper
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 760.04 kB
Formato Adobe PDF
760.04 kB Adobe PDF Visualizza/Apri
09180502.pdf

non disponibili

Descrizione: Editorial Version
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 811.51 kB
Formato Adobe PDF
811.51 kB 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.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2918018