Smartphone and smartwatch inertial measurements from heterogeneous subjects for human activity recognition

This repository contains the dataset and contents described in the "Dataset of inertial measurements of smartphones and smartwatches for human activity recognition" data article.

Matey-Sanz, M., Casteleyn, S., & Granell, C. (2023). Dataset of inertial measurements of smartphones and smartwatches for human activity recognition. Data in Brief, 109809.

Repository structure

Dataset: the DATA directory contains the dataset collected and described in the article. It contains:

• sXX: directory containing the data collected by the subject sXX. A total of 23 subjects participated in the data collection.
  • sXX_YY_{sp|sw}.csv: file containing the accelerometer and gyroscope samples collected by the subject sXX in the execution YY with the smartphone (sp) or the smartwatch (sw). Each file row (sample) has the following fields:
    • x_acc: X-axis value of the accelerometer.
    • y_acc: Y-axis value of the accelerometer.
    • z_acc: Z-axis value of the accelerometer.
    • x_acc: X-axis value of the gyroscope.
    • y_acc: Y-axis value of the gyroscope.
    • z_acc: Z-axis value of the gyroscope.
    • timestamp: when the sample was collected, UNIX timestamp.
    • label: activity associated to the sample.
• executions_info.csv: file with information about the activity sequences executions (phone orientation, first turn and second turn direction).
• subjects_info.csv: file with information about the subjects (age, gender, height (cm), weight (kg), dominand hand and number of activity sequences executed).

Code:

• utils: Python package containing modules with some util functions.
  • data_loading: module with functions to load the dataset and associated files.
  • exploration: module with functions to obtain insights about the subjects and executions.
  • visualization: module with the plot_execution() function, which plots the accelerometer and gyroscope samples of a certain execution and device.
• example-usage.ipynb: Jupyter Notebook that shows the usage of the provided utility functions.

Common files:

• requirements.txt: Python dependencies required to use the provided functions. Install Python if it is not installed in your system and execute the following command to install the dependecies:

  pip install -r requirements.txt

License

Dataset

The dataset in this repository is licensed under Creative Commons Attribution 4.0 International License.

Code

All contained code in the utils package is licensed under the Apache License 2.0.

Acknowledgements

This work has been funded by the Spanish Ministry of Universities [grant FPU19/05352], by MCIN/AEI/10.13039/501100011033 [grants PID2020-120250RB-I00, PID2022-1404475OB-C21, PID2022-1404475OB-C22] and the AICO 2023 project [grant CIAICO/2022/111] of the Department of Innovation, Universities, Science and Digital Society of the Valencian Government, Spain.