iBreath: Usage Of Breathing Gestures as Means of Interactions

2025-07-05

AI Summary

This study investigates the feasibility of respiration as a hands-free interaction modality. We propose iBreath, a bioimpedance-based sensing system that enables gesture recognition—including single and double “breath clicks.” To our knowledge, this is the first work to establish a systematic respiratory gesture interaction framework and distill eight evidence-based design guidelines. Under both user-dependent and user-independent modeling paradigms, iBreath achieves >90% classification accuracy and an F1-score of 95.2%, with model training requiring only 50 seconds. Empirical evaluation reveals median gesture durations of 3.5–5.3 seconds; single breath clicks are the most frequently used gesture and are rated by users as intuitive, simple, and comfortable. The work introduces a low-intrusiveness, high-availability paradigm for ubiquitous human–computer interaction and provides a reproducible technical pathway grounded in bioimpedance sensing.

Technology Category

• Humans and AI: Interaction Techniques and Devices
• Computer Vision: Biometrics, Face, Gesture & Pose
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

Breathing is a spontaneous but controllable body function that can be used for hands-free interaction. Our work introduces "iBreath", a novel system to detect breathing gestures similar to clicks using bio-impedance. We evaluated iBreath's accuracy and user experience using two lab studies (n=34). Our results show high detection accuracy (F1-scores > 95.2%). Furthermore, the users found the gestures easy to use and comfortable. Thus, we developed eight practical guidelines for the future development of breathing gestures. For example, designers can train users on new gestures within just 50 seconds (five trials), and achieve robust performance with both user-dependent and user-independent models trained on data from 21 participants, each yielding accuracies above 90%. Users preferred single clicks and disliked triple clicks. The median gesture duration is 3.5-5.3 seconds. Our work provides solid ground for researchers to experiment with creating breathing gestures and interactions.

Problem

• Develops a system to detect breathing gestures for hands-free interaction
• Evaluates accuracy and user experience of bio-impedance-based breathing gestures
• Provides guidelines for designing effective breathing gesture interactions

Innovation

• Uses bio-impedance to detect breathing gestures
• Achieves high accuracy with F1-scores over 95.2%
• Provides eight practical guidelines for gesture design