In-situ wearable-based dataset of continuous heart rate variability monitoring accompanied by sleep diaries

In-situ wearable-based dataset of continuous heart rate variability monitoring accompanied by sleep diaries integrates continuous physiological states and motion signals collected via smartwatches from 49 healthy individuals (mean age: 28.35±5.87, including 51% females) over four weeks. The recordings were sampled every 100 ms (10 Hz), allowing for short-term HRV computation for each 5-minute segment of raw data. We validated the collected signals by examining collection frequency, analyzing the correlation between smartwatch sensor data and computed HRV, and comparing HRV and sleep-related feature distributions with existing literature. Alongside wearable recordings, we obtained daily sleep diaries and biweekly clinical questionnaire results to assess participants' mental disorders, such as anxiety, depression, and insomnia. The dataset aims to benchmark in-the-wild HRV recordings and support researchers in developing algorithms to predict mental health and sleep patterns using health indicators.

本数据集为基于原位可穿戴设备的连续心率变异性（heart rate variability, HRV）监测数据集，搭配睡眠日记，整合了49名健康受试者（平均年龄28.35±5.87岁，女性占比51%）在四周内通过智能手表采集的连续生理状态与运动信号。所有采集数据的采样间隔为100毫秒（即10赫兹），可针对原始数据的每5分钟片段计算短时HRV。本研究通过检验采集频率、分析智能手表传感器数据与计算所得HRV的相关性，以及将HRV与睡眠相关特征的分布与现有文献进行对比，对采集到的信号进行了有效性验证。除可穿戴设备采集的数据外，本研究还收集了受试者的每日睡眠日记与每两周一次的临床问卷结果，用于评估受试者的焦虑、抑郁、失眠等精神障碍状况。本数据集旨在为真实野外场景下的HRV采集提供基准测试标准，并助力研究人员开发基于健康指标预测精神健康与睡眠模式的算法。