A 28.2 μC Neuromorphic Sensing System Featuring SNN-based Near-sensor Computation and Event-Driven Body-Channel Communication for Insertable Cardiac Monitoring

Yuming He 1
Federico Corradi 1
Chengyao Shi 1, 2
Ming Ding Ming Ding 1
Martijn Timmermans 2
Jan Stuijt 1
Pieter Harpe 2
Ilja Ocket 3
Yao Hong Liu 1
Publication typeProceedings Article
Publication date2021-11-07
Abstract
This paper presents an event-driven neuromorphic sensing system capable of performing on-chip feature extraction and “send-on-delta” transmission for insertable cardiac monitoring. A background offset calibration improves the SNDR of clockless level-crossing ADCs. A fully synthesized spiking neural network extracts full ECG PQRST features with $\lt 1$ ms time precision. An event-driven body channel communication minimizes transmission energy. The prototype is fabricated in 40nm CMOS and consumes $28.2 \mu \mathrm{W}$ system power.
Found 
Found 

Top-30

Journals

1
Nature Machine Intelligence
1 publication, 9.09%
IEEE Journal of Solid-State Circuits
1 publication, 9.09%
IEEE Transactions on Microwave Theory and Techniques
1 publication, 9.09%
Nature Communications
1 publication, 9.09%
IEEE Micro
1 publication, 9.09%
Biomedical Engineering Letters
1 publication, 9.09%
IEEE Transactions on Circuits and Systems I: Regular Papers
1 publication, 9.09%
1

Publishers

1
2
3
4
5
6
7
Institute of Electrical and Electronics Engineers (IEEE)
7 publications, 63.64%
Springer Nature
3 publications, 27.27%
Association for Computing Machinery (ACM)
1 publication, 9.09%
1
2
3
4
5
6
7
  • We do not take into account publications without a DOI.
  • Statistics recalculated weekly.

Are you a researcher?

Create a profile to get free access to personal recommendations for colleagues and new articles.
Metrics
11
Share