i-Mask: An Intelligent Mask for Breath-Driven Activity Recognition

2025-09-04

AI Summary

This work introduces a novel human activity recognition (HAR) paradigm leveraging respiratory patterns as the primary sensing modality for unobtrusive, continuous health monitoring. Methodologically, we design a custom smart mask equipped with airflow sensors to capture high signal-to-noise ratio respiratory time-series data; preprocessing involves noise filtering, empirical mode decomposition, and label alignment to extract lightweight temporal features, followed by classification using an optimized LSTM-Attention architecture. Experimental evaluation on six daily activities—including walking, stair climbing, coughing, and resting—achieves 95.3% accuracy, substantially outperforming conventional accelerometer- or heart-rate-based approaches. To our knowledge, this is the first systematic study demonstrating the discriminative power and robustness of respiratory dynamics for HAR. The results establish respiration as a low-intrusion, information-rich physiological signal, opening a new pathway for wearable health monitoring systems.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

The patterns of inhalation and exhalation contain important physiological signals that can be used to anticipate human behavior, health trends, and vital parameters. Human activity recognition (HAR) is fundamentally connected to these vital signs, providing deeper insights into well-being and enabling real-time health monitoring. This work presents i-Mask, a novel HAR approach that leverages exhaled breath patterns captured using a custom-developed mask equipped with integrated sensors. Data collected from volunteers wearing the mask undergoes noise filtering, time-series decomposition, and labeling to train predictive models. Our experimental results validate the effectiveness of the approach, achieving over 95% accuracy and highlighting its potential in healthcare and fitness applications.

Problem

• Recognizing human activity through breath patterns
• Monitoring health and fitness using exhaled breath
• Developing a sensor-equipped mask for activity recognition

Innovation

• Intelligent mask with integrated sensors captures breath
• Noise filtering and time-series decomposition process data
• Predictive models achieve over 95% accuracy recognition