# Heart Rate Estimation — Data

来源：https://www.kaggle.com/competitions/24-exercise1/data

采集时间：2026-10-19T14:04:35Z

The data set is stored in the file *mhealth24_data_public.npy*. You can either download it from here and work locally on your computer or directly work with it in a notebook in this competition on Kaggle.

In the *groupXX_PPGHR.ipynb* example notebook, which you can download here, we show in detail how you can load and plot the data, and create a submission file for this Kaggle competition. You have to download the notebook from here and you can then upload it in the *Code* section to use it.

The total recording length is 14 hours and 9 minutes. It is split into 6 phases. The ground truth HR data is only provided for phases 0, 2, and 4 (training data), phases 1, 3, and 5 will be used for testing and grading (test data). In phases 0 and 3, you are provided with PPG and accelerometer data from the wrist, in phases 1, 2, 4, and 5 with PPG and accelerometer data from the forehead.

The data set contains the following sensor data:
- Raw PPG recordings from the forehead and the wrist
   - sampling rate: 128 Hz
   - 19-bit unsigned integer (possible values in the interval [0, 524288])
   - These measurements do not have a unit but correspond to the light intensity measured by a photodiode in the PPG sensor while a green LED was on.
- Accelerometer data from the forehead and the wrist
   - sampling rate: 128 Hz
   - 3-axes (X, Y, Z) 12-bit signed integer (possible values in the interval [-2040, 2040])
   - 2040 corresponds to a measurement of +2g, -2040 is -2g
   - orientation of the axes is not given.
- Ground Truth HR data (only provided for half the data)
   - as a list of values, each element of which corresponds to the average heart rate in a 30-second window.