Bio-signals exhibit high redundancy, and the algorithms for their processing are inherently error resilient. This property can be leveraged to improve the energy-efficiency of IoT-Edge (wearables) through the emerging trend of approximate computing. This paper presents XBioSiP, a novel methodology for approximate bio-signal processing that employs two quality evaluation stages, during the pre-processing and bio-signal processing stages, to determine the approximation parameters. It thereby achieves high energy savings while satisfying the user-determined quality constraint. Our methodology achieves, up to 19x and 22x reduction in the energy consumption of a QRS peak detection algorithm for 0% and <1% loss in peak detection accuracy, respectively.
@article{arxiv.1902.02649,
title = {XBioSiP: A Methodology for Approximate Bio-Signal Processing at the Edge},
author = {Bharath Srinivas Prabakaran and Semeen Rehman and Muhammad Shafique},
journal= {arXiv preprint arXiv:1902.02649},
year = {2019}
}
Comments
Accepted for publication at the Design Automation Conference 2019 (DAC'19), Las Vegas, Nevada, USA