CASAS Smart Home Dataset (Aruba, Cairo, Milan, Tulum)
Catalog Summary
"Longitudinal ambient sensor data collected from 4 community homes featuring motion sensors, door sensors, and temperature readings with activity labels. This dataset captures naturalistic behavior patterns for activity recognition model development in real-world smart home environments. Data includes continuous recordings from PIR motion sensors, magnetic door sensors, and ambient temperature sensors with annotated activities by external annotators. The dataset provides a valuable resource for building activity recognition models that operate in uncontrolled, naturalistic settings."
Catalog Notes
Overview
The CASAS (Center for Advanced Studies in Adaptive Systems) Smart Home dataset is a longitudinal collection of ambient sensor data from 4 community homes. This resource enables analysis of naturalistic behavior and development of activity recognition models that operate in real-world environments.
Technical Details
Dataset includes 4 distinct home environments with continuous sensor readings. Data fields comprise date, time, sensor identifier, and message content. Sensors include PIR motion sensors with constrained 1-meter diameter coverage, magnetic door sensors for open/close detection, and ambient temperature sensors. Motion sensors are ceiling-mounted with constrained lenses for precise area coverage.
Collection Setup
Data collected continuously while residents performed normal routines. Homes include Aruba (1 resident), Milan (2 residents), Cairo (>2 residents), and Tulum (2 residents). Sensors are placed in locations such as Bathroom, Bedroom, DiningRoom, and specific furniture items (Bed, Bath, OfficeChair). Homes with multiple rooms of same type use trailing letters for differentiation (e.g., BedroomA, BedroomB).
Recommended Research Tasks
- Activity recognition and behavior pattern analysis
- Smart home automation algorithm development
- Anomaly detection in daily living patterns
- Longitudinal behavior analysis for eldercare
Access & License
Available on Zenodo with open access. Please cite the original CASAS paper when using this dataset. Related floorplans and additional sensor locations available in companion dataset.
View Data Structure
To explore column names, data types, and sample rows, visit the official dataset page on Kaggle.
Preview on KaggleCite This Dataset
The dataset creators ask users of this dataset to cite the accompanying paper. Use one of the verified formats below.
Cook, D. J., Crandall, A. S., Thomas, B. L., & Krishnan, N. C. (2013). CASAS: A Smart Home in a Box. Computer, 46(7), 62-69. https://doi.org/10.1109/MC.2012.328
Source metadata: Kaggle (2013) · DOI: 10.1109/MC.2012.328
Indexed by IoTDataset.com on Feb 06, 2026
Review the Source Record
Confirm the licence, version, access conditions, file format, and provenance at the source before use.