CASAS Smart Home dataset (aruba, cairo, milan, tulum) - free living, motion, door, temperature, activity labels
Creators
Contributors
Data collectors:
Description
This dataset represents ambient data collected longitudinally in 4 community homes. This is a resource for analyzing naturalistic behavior in a home and building activity recognition models that operate in the wild.
Data are collected continuously from ambient sensors while residents perform their normal routines. The data fields are date, time, sensor identifier, and message. The sensors consist of PIR (motion) sensors, magnetic door (open/close) sensors, and ambient temperature sensors. Motion sensors are attached to ceilings and the lens of most motion sensors are constrained to cover a 1 meter diameter area. To detect movement in a larger area, an unconstrained sensor is angled to cover an entire room or region.
There is one file per home. Data labeled with activities by an external annotator.
Note: This is a companion dataset to one found at https://zenodo.org/uploads/15708568 (doi: 10.5281/zenodo.15708568). Additional information about the sites, including floorplans with sensor locations, can be found at that location.
Methods
Citation: Please cite the following paper when using this dataset:
Cook, D., Crandall, A., Thomas, B., & Krishnan, N. (2013). CASAS: A smart home in a box. IEEE Computer, 46(7):62-69, 2013. https://doi.org/10.1109/MC.2012.328
Files
new_labeled_data.zip
Files
(33.0 MB)
Name | Size | Download all |
---|---|---|
md5:86954063e1d2099d288f59227b19a749
|
33.0 MB | Preview Download |
Additional details
Funding
- National Institutes of Health
- Smart environment technology for longitudinal behavior analysis and intervention R01EB015853
- National Institutes of Health
- Smart Environment Technologies for Health Assessment and Assistance R01EB009675
Software
- Repository URL
- https://github.com/WSU-CASAS