基于睡眠传感器的HRV异常状态预测数据

基于睡眠传感器采集的HRV数据，建立HRV异常状态监测模型。此数据主要用于用户的日常健康管理服务。1）健身达人可根据此数据评估运动强度和运动量。2）普通健康人群可根据此数据监测日常的身体状态，当发生连续HRV异常时，需要关注自我的情绪、疾病、作息习惯、疲劳程度等方面的变化，从而达到自我健康管理的目的。3）患有相关心血管疾病的用户，可参考该数据，用于评估当前疾病所处时期。1、 将用户历史的HRV的四个指标SDNN、RMSSD、pNN50、LF/HF数据分别进行加权移动平均处理和标准差计算，得到每天更新的HRV的均值和标准差。
2、 根据3sigma原则，设定四个HRV指标每日的正常上、下限范围，作为正常范围。
3、 当今日的HRV指标处于正常范围内，标记为0；当HRV指标高于范围上限，标记为1；当HRV指标低于范围下限，标记为-1。
4、 如果当日四个HRV指标状态都为0，则整体的HRV异常状态为0，否则为1。状态0表示当日整体的HRV不存在异常，状态1表示当日HRV存在异常。

Based on HRV data collected by sleep sensors, a HRV abnormal status monitoring model is established. This dataset is primarily used for users' daily health management services.
1) Fitness enthusiasts can use this data to assess exercise intensity and training volume.
2) General healthy individuals can monitor their daily physical status with this data. When consecutive HRV abnormalities occur, they need to pay attention to changes in their emotions, diseases, sleep habits, fatigue levels and other relevant aspects, so as to achieve the goal of self-health management.
3) Users with relevant cardiovascular diseases can refer to this data to evaluate the current stage of their disease.

1. Perform weighted moving average processing and standard deviation calculation on the four historical HRV indicators (SDNN, RMSSD, pNN50, LF/HF) respectively, to obtain the daily updated mean and standard deviation of HRV.
2. Set the daily normal upper and lower limits for the four HRV indicators according to the 3-sigma rule, which serve as the normal reference ranges.
3. Mark the daily HRV indicator as 0 if it falls within the normal range; mark it as 1 if it exceeds the upper limit of the range; mark it as -1 if it is below the lower limit of the range.
4. If the statuses of all four HRV indicators on the same day are 0, the overall HRV abnormal status is 0; otherwise, it is 1. Status 0 indicates that there is no overall HRV abnormality on that day, while status 1 indicates that there is an HRV abnormality on that day.