A Machine-Learning-Algorithm-Assisted Intelligent System for Real-Time Wireless Respiratory Monitoring

Respiratory signals are basic indicators of human life and health that used as effective biomarkers to detect respiratory diseases in clinics, including cardiopulmonary function, breathing disorders, system infections. Therefore, it is necessary continuously measure signals. However, there still a lack portable electronic devices designed meet the needs daily monitoring. This study presents an intelligent, portable, wireless monitoring for real-time evaluation behaviors. The consists triboelectric sensor; circuit board hardware data acquisition, preprocessing, transmission; machine learning algorithm enhancing recognition accuracy; mobile terminal app. sensor—fabricated by screen-printing method—is lightweight, non-invasive, biocompatible. It provides clear response frequency intensity airflow. reusable cost-effective. decision tree model identify with average accuracy 97.2%. signal statistical results can be uploaded server network displayed on various terminals body warnings advice. work promotes development wearable systems.