A data-driven modeling approach to stochastic computation for low-energy biomedical devices

Kyong Ho Lee, Kuk Jin Jang, Ali Shoeb, Naveen Verma

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations

Abstract

Low-power devices that can detect clinically relevant correlations in physiologically-complex patient signals can enable systems capable of closed-loop response (e.g., controlled actuation of therapeutic stimulators, continuous recording of disease states, etc.). In ultra-low-power platforms, however, hardware error sources are becoming increasingly limiting. In this paper, we present how data-driven methods, which allow us to accurately model physiological signals, also allow us to effectively model and overcome prominent hardware error sources with nearly no additional overhead. Two applications, EEG-based seizure detection and ECG-based arrhythmia-beat classification, are synthesized to a logic-gate implementation, and two prominent error sources are introduced: (1) SRAM bit-cell errors and (2) logic-gate switching errors (stuck-at faults). Using patient data from the CHB-MIT and MIT-BIH databases, performance similar to error-free hardware is achieved even for very high fault rates (up to 0.5 for SRAMs and 710 2 for logic) that cause computational bit error rates as high as 50%.

Original languageEnglish (US)
Title of host publication33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
Pages826-829
Number of pages4
DOIs
StatePublished - Dec 26 2011
Event33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011 - Boston, MA, United States
Duration: Aug 30 2011Sep 3 2011

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Print)1557-170X

Other

Other33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
CountryUnited States
CityBoston, MA
Period8/30/119/3/11

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Fingerprint Dive into the research topics of 'A data-driven modeling approach to stochastic computation for low-energy biomedical devices'. Together they form a unique fingerprint.

  • Cite this

    Lee, K. H., Jang, K. J., Shoeb, A., & Verma, N. (2011). A data-driven modeling approach to stochastic computation for low-energy biomedical devices. In 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011 (pp. 826-829). [6090189] (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). https://doi.org/10.1109/IEMBS.2011.6090189