I'm working on a machine learning project for classifying activity level (walking, running, sitting etc) based on smartphone accelerometer, gyroscope, and gps data

Of course I can just collect this data myself but this is very time consuming. I'm wondering if anybody knows of a database that contains this type of data, and importantly including labels for what type of activity they were doing?


There is a dataset on the UCI Machine Learning repository. Check this link for the data and data description. There is no GPS information available.

The names for the relevant papers are there as well. So you can look those up if you want to.


You can review this paper: A Public Domain Dataset for Human Activity Recognition Using Smartphones

In particular, tracking down the references leads to this page containing the "Opportunity" activity data and this specific link to the data.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.