Earinter: A Closed-Loop System for Eating Pace Regulation with Just-in-Time Intervention Using Commodity Earbuds

2026-02-10

AI Summary

Rapid eating is prevalent yet challenging to monitor and regulate in real time, and long-term self-monitoring imposes a high burden. This work proposes the first closed-loop intervention system leveraging off-the-shelf earbuds, utilizing bone conduction sensors to capture chewing vibrations and a lightweight on-device algorithm to estimate chews per swallow (CPS) in real time. Guided by dual-process theory, the system delivers just-in-time interventions to slow eating pace. It represents the first field-deployed, theory-driven closed-loop intervention using a single-modality commercial ear-worn device. Experimental results show a chewing detection F1-score of 0.97 and a CPS estimation mean absolute error of 0.18 chews/min. A 13-day in-the-wild study demonstrated significant increases in CPS, reduced eating speed, and evidence of retention effects.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

Rapid eating is common yet difficult to regulate in situ, partly because people seldom notice pace changes and sustained self-monitoring is effortful. We present Earinter, a commodity-earbud-based closed-loop system that integrates in-the-wild sensing, real-time reasoning, and theory-grounded just-in-time (JIT) intervention to regulate eating pace during daily meals. Earinter repurposes the earbud's bone-conduction voice sensor to capture chewing-related vibrations and estimate eating pace as chews per swallow (CPS) for on-device inference. With data collected equally across in-lab and in-the-wild sessions, Earinter achieves reliable chewing detection (F1 = 0.97) and accurate eating pace estimation (MAE: 0.18 $\pm$ 0.13 chews/min, 3.65 $\pm$ 3.86 chews/swallow), enabling robust tracking for closed-loop use. Guided by Dual Systems Theory and refined through two Wizard-of-Oz pilots, Earinter adopts a user-friendly design for JIT intervention content and delivery policy in daily meals. In a 13-day within-subject field study (N=14), the closed-loop system significantly increased CPS and reduced food-consumption speed, with statistical signs of carryover on retention-probe days and acceptable user burden. Our findings highlight how single-modality commodity earables can support practical, theory-driven closed-loop JIT interventions for regulating eating pace in the wild.

Problem

• eating pace regulation
• rapid eating
• just-in-time intervention
• in-the-wild monitoring
• closed-loop system

Innovation

• closed-loop intervention
• eating pace regulation
• commodity earbuds
• bone-conduction sensing
• just-in-time adaptive intervention