CoughTrigger: Earbuds IMU Based Cough Detection Activator Using An Energy-efficient Sensitivity-prioritized Time Series Classifier

TL;DR

CoughTrigger leverages low-power IMU sensors in earbuds to activate audio-based cough detection, reducing power consumption and improving detection specificity, validated through experiments on 45 subjects and real-world data.

Contribution

This work introduces a novel IMU-based cough detection activator for earbuds that minimizes power use and enhances detection accuracy compared to traditional audio-only methods.

Findings

Achieved 0.77 AUC score in leave-one-subject-out evaluation.

Validated effectiveness on free-living data.

Implemented on-device for real-time detection.

Abstract

Persistent coughs are a major symptom of respiratory-related diseases. Increasing research attention has been paid to detecting coughs using wearables, especially during the COVID-19 pandemic. Among all types of sensors utilized, microphone is most widely used to detect coughs. However, the intense power consumption needed to process audio signals hinders continuous audio-based cough detection on battery-limited commercial wearable products, such as earbuds. We present CoughTrigger, which utilizes a lower-power sensor, an inertial measurement unit (IMU), in earbuds as a cough detection activator to trigger a higher-power sensor for audio processing and classification. It is able to run all-the-time as a standby service with minimal battery consumption and trigger the audio-based cough detection when a candidate cough is detected from IMU. Besides, the use of IMU brings the benefit of improved specificity of cough detection. Experiments are conducted on 45 subjects and our IMU-based model achieved 0.77 AUC score under leave one subject out evaluation. We also validated its effectiveness on free-living data and through on-device implementation.