# XBioSiP: A Methodology for Approximate Bio-Signal Processing at the Edge

## TL;DR

XBioSiP introduces an approximate computing methodology for bio-signal processing at the edge, significantly reducing energy consumption while maintaining user-defined accuracy levels in wearable devices.

## Contribution

It proposes a novel two-stage quality evaluation approach for approximate bio-signal processing, enabling substantial energy savings with controlled accuracy loss.

## Key findings

- Up to 19x energy reduction at 0% accuracy loss
- Up to 22x energy reduction at less than 1% accuracy loss
- Effective energy-accuracy trade-offs demonstrated in QRS peak detection

## Abstract

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.