A low-energy computation platform for data-driven biomedical monitoring algorithms

Mohammed Shoaib, Niraj Jha, Naveen Verma

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

9 Scopus citations

Abstract

A key challenge in closed-loop chronic biomedical systems is the ability to detect complex physiological states from patient signals within a constrained power budget. Data-driven machine-learning techniques are major enablers for the modeling and interpretation of such states. Their computational energy, however, scales with the complexity of the required models. In this paper, we propose a low-energy, biomedical computation platform optimized through the use of an accelerator for data-driven classification. The accelerator retains selective flexibility through hardware reconfiguration and exploits voltage scaling and parallelism to operate at a sub-threshold minimum-energy point. Using cardiac arrhythmia detection algorithms with patient data from the MIT-BIH database, classification is achieved in 2.96 μJ (at Vdd = 0.4 V), over four orders of magnitude smaller than that on a low-power general-purpose processor. The energy of feature extraction is 148 μJ while retaining flexibility for a range of possible biomarkers.

Original languageEnglish (US)
Title of host publication2011 48th ACM/EDAC/IEEE Design Automation Conference, DAC 2011
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages591-596
Number of pages6
ISBN (Print)9781450306362
DOIs
StatePublished - 2011

Publication series

NameProceedings - Design Automation Conference
ISSN (Print)0738-100X

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Modeling and Simulation
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Keywords

  • C.3 Real-time and embedded systems
  • Electrocardiograph (ECG)
  • support vector machine (SVM)

Fingerprint Dive into the research topics of 'A low-energy computation platform for data-driven biomedical monitoring algorithms'. Together they form a unique fingerprint.

  • Cite this

    Shoaib, M., Jha, N., & Verma, N. (2011). A low-energy computation platform for data-driven biomedical monitoring algorithms. In 2011 48th ACM/EDAC/IEEE Design Automation Conference, DAC 2011 (pp. 591-596). [5981857] (Proceedings - Design Automation Conference). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1145/2024724.2024861