실시간 운동 상황 판별을 이용한 심박 회복률 평가용 웨어러블 시스템

Abstract

Heart rate recovery (HRR) is a convenient index to assess a cardiovascular autonomic function response to physical exercise. HRR monitoring during daily exercise can be an effective way to verify cardiorespiratory performance. Because HRR varies depending on exercise intensity and resting condition, an exercise condition needs to be acquired for a reliable HRR analysis. Recent progress in developing a wireless bio-signal monitoring system has provided an opportunity to analyze individual health status. However, the absence of a real-time monitoring system that analyzed HRR in a valid method made it difficult to utilize performance tracking using HRR. This study presents a real-time wearable monitoring system for HRR evaluation with automatic labeling of exercise conditions using real-time activity classification. The wearable system is composed of a wearable device with an embedded electrocardiogram (ECG) and accelerometer sensors, a wireless communication using Bluetooth Low Energy (BLE) with a character encoding, and a real-time classification of activity. An acceleration peak and an angle tilt peak from the accelerometer sensor were used to classify activities such as running, walking, and postural. Seven healthy subjects participated to a test to evaluate accuracy of the activity classification. The wearable device system accurately detected activities with a sensitivity of 99.2% and posture transitions with a sensitivity of 92% and specificity of 93.3%. The proposed wearable system can help monitor HRR during training by labeling the exercise conditions simultaneously.