Learning-Based Near-Optimal Area-Power Trade-offs in Hardware Design for Neural Signal Acquisition
Abstract
Wireless implantable devices capable of monitoring the electrical activity of the brain are becoming an important tool for understanding and potentially treating mental diseases such as epilepsy and depression. While such devices exist, it is still necessary to address several challenges to make them more practical in terms of area and power dissipation. In this work, we apply Learning Based Compressive Subsampling (LBCS) to tackle the power and area trade-offs in neural wireless devices. To this end, we propose a low-power and area-efficient system for neural signal acquisition which yields state-of-art compression rates up to 64x with high reconstruction quality, as demonstrated on two human iEEG datasets. This new fully digital architecture handles one neural acquisition channel, with an area of 210 x 210 μm in 90nm CMOS technology, and a power dissipation of only 1μW.
Additional Information
© 2016 ACM. This work was supported in part by the European Commission under grant ERC Future Proof and by the Swiss Science Foundation under grants SNF 200021-146750 and SNF CRSII2-147633. The authors would like to thank Jonathan Narinx for useful discussions on the system design.Additional details
- Eprint ID
- 69903
- DOI
- 10.1145/2902961.2903028
- Resolver ID
- CaltechAUTHORS:20160824-123308419
- European Research Council (ERC)
- Swiss Science Foundation (SNF)
- SNF 200021-146750
- Swiss Science Foundation (SNF)
- CRSII2-147633
- Created
-
2016-08-24Created from EPrint's datestamp field
- Updated
-
2022-09-15Created from EPrint's last_modified field