TechRxiv
NN-CSdecoder2019.pdf (1.37 MB)
Download file

Deep Neural Oracles for Short-window Optimized Compressed Sensing of Biosignals

Download (1.37 MB)
preprint
posted on 26.10.2019, 17:43 authored by Mauro MangiaMauro Mangia, Luciano Prono, Fabio PareschiFabio Pareschi, Riccardo Rovatti, Gianluca Setti
The recovery of sparse signals given their linear mapping on lower-dimensional spaces can be partitioned into a support estimation phase and a coefficient estimation phase. We propose to estimate the support with an oracle based on a deep neural network trained jointly with the linear mapping at the encoder. The divination of the oracle is then used to estimate the coefficients by pseudo-inversion. This architecture allows the definition of an encoding-decoding scheme with state-of-the-art recovery capabilities when applied to biological signals such as ECG and EEG, thus allowing extremely low-complex encoders.
As an additional feature, oracle-based recovery is able to self-assess, by indicating with remarkable accuracy chunks of signals that may have been reconstructed with a non-satisfactory quality. This self-assessment capability is unique in the CS literature and paves the way for further improvements depending on the requirements of the specific application.
As an example, our scheme is able to satisfyingly compress by a factor of 2.67 an ECG or EEG signal with a complexity equivalent to only 24 signed sums per processed sample.

History

Email Address of Submitting Author

mauro.mangia2@unibo.it

ORCID of Submitting Author

0000-0002-3818-9115

Submitting Author's Institution

University of Bologna

Submitting Author's Country

Italy

Usage metrics

Read the peer-reviewed publication

in IEEE Transactions on Biomedical Circuits and Systems

Licence

Exports