SoDA

Donated on 6/19/2022

Dataset of "Social Distancing Alert with Smartwatches"

Dataset Characteristics

Time-Series

Subject Area

Health and Medicine

Associated Tasks

Classification

Feature Type

-

# Instances

1800

# Features

-

Dataset Information

For what purpose was the dataset created?

People would violate the social distancing practice unconsciously when they conduct some social activities such as handshaking, hugging, kissing on the face or forehead, etc. For preventing COVID-19 virus transmission, we collected recordings of accelerometers and gyroscopes to recognize activities that may violate social distancing practices.

Who funded the creation of the dataset?

Fei Wang

What do the instances in this dataset represent?

every instance is a time series of different social distancing actions

Are there recommended data splits?

based on different needs, can split data into training-set/validation-set/testing-set

Was there any data preprocessing performed?

please reference https://github.com/aiotgroup/SoDA

Additional Information

The file name with the format of "I_J_K.mat". I(1 - 10): the I-th subject. J(1 - 18): the J-th action. K(0 - 9): the K-th repetition. Every mat file contains three keys: accData(1, 3, sequence length): A sequence of the accelerometer readings. gyrData (1, 3, sequence length): A sequence of the gyroscope readings. label(1, sequence length): Action labels for each sample point.

Has Missing Values?

No

Introductory Paper

Social Distancing Alert with Smartwatches

By Xin Wang, Xilei Wu, Huina Meng, Yu Fan, Jing Shi, Han Ding, Fei Wang. 2022

Published in ArXiv

Dataset Files

FileSize
SoDA.zip6.7 MB
18actions.png224.8 KB

Reviews

There are no reviews for this dataset yet.

Login to Write a Review
Download (6.9 MB)
1 citations
4450 views

Creators

Xin Wang

xwang6@stu.xjtu.edu.cn

XJTU

Huina Meng

menghuina@stu.xjtu.edu.cn

XJTU

Fei Wang

feynmanw@xjtu.edu.cn

XJTU

Xilei Wu

xlwuuu@stu.xjtu.edu.cn

License

By using the UCI Machine Learning Repository, you acknowledge and accept the cookies and privacy practices used by the UCI Machine Learning Repository.

Read Policy