Reproduce “EarGate: Gait-based User Identification with In-ear Microphones” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Andrea Ferlini, Dong Ma, Robert Harle, Cecilia Mascolo
Ferlini et al. from the University of Cambridge introduce EarGate, a system for gait-based user identification using in-ear microphones in earable devices. The system leverages bone conduction and the occlusion effect to achieve up to 97.26% Balanced Accuracy, offering a continuous and private authentication method.
Key insights
- The occlusion effect and bone conduction within an occluded ear canal provide a distinct and robust low-frequency acoustic signature of an individual's gait.
- Repurposing existing in-ear microphones, commonly used for noise cancellation, offers a cost-effective and hardware-efficient approach to gait biometrics without additional dedicated sensors.
- Fusing biometric data from both the left and right earbud microphones significantly enhances identification accuracy, demonstrating the advantage of multi-sensor input.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.