# Artificial Intelligence‐Driven Soft Bioelectronics for Self‐Powered Respiration Monitoring

## TL;DR

This paper explores AI-powered, self-powered bioelectronic sensors for monitoring respiration, aiming to improve healthcare through continuous data collection and disease diagnostics.

## Contribution

The paper introduces a comparative analysis of triboelectric, piezoelectric, and magnetoelastic sensors integrated with AI for respiration monitoring.

## Key findings

- Triboelectric, piezoelectric, and magnetoelastic generators enable self-powered respiration monitoring with high sensitivity.
- AI integration allows for multi-scenario data collection and big data-driven diagnostics for respiratory diseases.
- The study highlights practical considerations like breathability and comfort for wearable bioelectronics.

## Abstract

Respiration is a critical physiological process that reflects the health status of the human body. Self‐powered bioelectronic devices for respiration monitoring have shown great promise, driven by their advantages in miniaturization, cost‐effectiveness, high sensitivity, and excellent reliability. This work examines the recent advances in artificial intelligence‐driven, self‐powered respiration monitoring sensors based on triboelectricity, piezoelectricity, and magnetoelasticity, with a focus on their sensing performance and signal transduction mechanisms. A comparative analysis of their performance characteristics and applicable scenarios is presented, together with a discussion of practical considerations including breathability, wearing comfort, and waterproof performance, and an overview of the relative performance and application suitability of the three technologies. Furthermore, this report envisions future directions including long‐term multi‐scenario data collection and big data‐driven respiratory diseases diagnostics. We believe that the widespread implementation of artificial intelligence‐driven, self‐powered respiration monitoring sensors will play a pivotal role in reshaping healthcare and advancing intelligent interventions for respiratory diseases, ultimately promoting global health and well‐being.

Artificial intelligence‐driven soft bioelectronics for self powered respiration monitoring based on triboelectric nanogenerators (TENGs), piezoelectric nanogenerators (PENGs), and magnetoelastic generators (MEGs) enable continuous and multi‐scenario respiratory biomechanical data collection. Coupled with machine learning and big data driven diagnostics, these systems support disease identification, personalized therapy, and responsive intervention.