Hearables: Multimodal physiological in-ear sensing

TL;DR

This paper introduces a comfortable, multimodal in-ear device capable of robustly monitoring neural, cardiac, and respiratory functions, demonstrating improved accuracy and artifact handling in health tracking applications.

Contribution

It presents a novel inconspicuous earpiece with integrated sensors for cross-modal physiological monitoring, enhancing measurement robustness and accuracy over existing methods.

Findings

Validated each sensor modality through comprehensive experiments.

Demonstrated improved measurement accuracy with multimodal data fusion.

Showcased potential in real-world health monitoring scenarios.

Abstract

Future health systems require the means to assess and track the neural and physiological function of a user over long periods of time and in the community. Human body responses are manifested through multiple modalities, such as the mechanical, electrical and chemical; yet current physiological monitors (actigraphy, heart rate) largely lack in both the desired cross-modal and non-stigmatizing aspects. We address these challenges through an inconspicuous and comfortable earpiece, equipped with miniature multimodal sensors, which benefits from the relatively stable position of the ear canal with respect to vital organs to robustly measure the brain, cardiac and respiratory functions. Comprehensive experiments validate each modality within the proposed earpiece, while its potential in health monitoring is illustrated through case studies. We further demonstrate how combining data from multiple sensors within such an integrated wearable device improves both the accuracy of measurements and the ability to deal with artifacts in real-life scenarios.