Low-power ECG acquisition by Compressed Sensing with Deep Neural Oracles

Mauro Mangi; Alex Marchioni; Luciano Prono; Fabio Pareschi; Riccardo Rovatti; Gianluca Setti

doi:10.1109/AICAS48895.2020.9073945

Low-power ECG acquisition by Compressed Sensing with Deep Neural Oracles

Mauro Mangi, Alex Marchioni, Luciano Prono, Fabio Pareschi, Riccardo Rovatti, Gianluca Setti

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Scopus citations

Abstract

The recovery of sparse signals from their linear mapping on a lower-dimensional space is traditionally performed by finding the sparsest solution compatible with such solutions. This task can be partitioned in two phases: support estimation and coefficient estimation. We propose to perform the former with a deep neural network jointly trained with the encoder that divines a support that is used in the latter phase to estimate the coefficients by pseudo-inversion. Numerical evidence demonstrates that the proposed encoder-decoder architecture outperforms state-of-the-art Compressed Sensing (CS) approaches in the recovery of synthetic ECG signals for a compression ratio higher than 2.5. Further tests on real ECG prove the applicability in real-world scenarios.

Original language	English (US)
Title of host publication	Proceedings - 2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	158-162
Number of pages	5
ISBN (Print)	9781728149226
DOIs	https://doi.org/10.1109/AICAS48895.2020.9073945
State	Published - Aug 1 2020
Externally published	Yes

Access to Document

10.1109/AICAS48895.2020.9073945

Cite this

Mangi, M., Marchioni, A., Prono, L., Pareschi, F., Rovatti, R., & Setti, G. (2020). Low-power ECG acquisition by Compressed Sensing with Deep Neural Oracles. In Proceedings - 2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2020 (pp. 158-162). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AICAS48895.2020.9073945

@inproceedings{6993886c84a04464a2762a6cbeab2066,

title = "Low-power ECG acquisition by Compressed Sensing with Deep Neural Oracles",

abstract = "The recovery of sparse signals from their linear mapping on a lower-dimensional space is traditionally performed by finding the sparsest solution compatible with such solutions. This task can be partitioned in two phases: support estimation and coefficient estimation. We propose to perform the former with a deep neural network jointly trained with the encoder that divines a support that is used in the latter phase to estimate the coefficients by pseudo-inversion. Numerical evidence demonstrates that the proposed encoder-decoder architecture outperforms state-of-the-art Compressed Sensing (CS) approaches in the recovery of synthetic ECG signals for a compression ratio higher than 2.5. Further tests on real ECG prove the applicability in real-world scenarios.",

author = "Mauro Mangi and Alex Marchioni and Luciano Prono and Fabio Pareschi and Riccardo Rovatti and Gianluca Setti",

note = "Generated from Scopus record by KAUST IRTS on 2023-02-15",

year = "2020",

month = aug,

day = "1",

doi = "10.1109/AICAS48895.2020.9073945",

language = "English (US)",

isbn = "9781728149226",

pages = "158--162",

booktitle = "Proceedings - 2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

}

Mangi, M, Marchioni, A, Prono, L, Pareschi, F, Rovatti, R & Setti, G 2020, Low-power ECG acquisition by Compressed Sensing with Deep Neural Oracles. in Proceedings - 2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2020. Institute of Electrical and Electronics Engineers Inc., pp. 158-162. https://doi.org/10.1109/AICAS48895.2020.9073945

Low-power ECG acquisition by Compressed Sensing with Deep Neural Oracles. / Mangi, Mauro; Marchioni, Alex; Prono, Luciano et al.
Proceedings - 2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 158-162.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Low-power ECG acquisition by Compressed Sensing with Deep Neural Oracles

AU - Mangi, Mauro

AU - Marchioni, Alex

AU - Prono, Luciano

AU - Pareschi, Fabio

AU - Rovatti, Riccardo

AU - Setti, Gianluca

N1 - Generated from Scopus record by KAUST IRTS on 2023-02-15

PY - 2020/8/1

Y1 - 2020/8/1

N2 - The recovery of sparse signals from their linear mapping on a lower-dimensional space is traditionally performed by finding the sparsest solution compatible with such solutions. This task can be partitioned in two phases: support estimation and coefficient estimation. We propose to perform the former with a deep neural network jointly trained with the encoder that divines a support that is used in the latter phase to estimate the coefficients by pseudo-inversion. Numerical evidence demonstrates that the proposed encoder-decoder architecture outperforms state-of-the-art Compressed Sensing (CS) approaches in the recovery of synthetic ECG signals for a compression ratio higher than 2.5. Further tests on real ECG prove the applicability in real-world scenarios.

AB - The recovery of sparse signals from their linear mapping on a lower-dimensional space is traditionally performed by finding the sparsest solution compatible with such solutions. This task can be partitioned in two phases: support estimation and coefficient estimation. We propose to perform the former with a deep neural network jointly trained with the encoder that divines a support that is used in the latter phase to estimate the coefficients by pseudo-inversion. Numerical evidence demonstrates that the proposed encoder-decoder architecture outperforms state-of-the-art Compressed Sensing (CS) approaches in the recovery of synthetic ECG signals for a compression ratio higher than 2.5. Further tests on real ECG prove the applicability in real-world scenarios.

UR - https://ieeexplore.ieee.org/document/9073945/

UR - http://www.scopus.com/inward/record.url?scp=85085052057&partnerID=8YFLogxK

U2 - 10.1109/AICAS48895.2020.9073945

DO - 10.1109/AICAS48895.2020.9073945

M3 - Conference contribution

SN - 9781728149226

SP - 158

EP - 162

BT - Proceedings - 2020 IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2020

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Low-power ECG acquisition by Compressed Sensing with Deep Neural Oracles

Abstract

Access to Document

Other files and links

Fingerprint

Cite this