Zensei

Abstract

As interactions with everyday handheld devices and objects become increasingly common, a more seamless and effortless identification and personalization technique will be essential to an uninterrupted user experience. In this paper, we present Zensei, a user identification and customization system using human body bioimpedance sensing through multiple electrodes embedded into everyday objects. Zensei provides for an uninterrupted user-device personalization experience that is difficult to forge because it uses both the unique physiological and behavioral characteristics of the user. We demonstrate our measurement system in three exemplary device configurations that showcase different levels of constraint via environment-based, whole-body-based, and handheld-based identification scenarios. We evaluated Zensei's classification accuracy among 12 subjects on each configuration over 22 days of collected data and report our promising results.