CASAS ArWISE smartwatch raw motion dataset - free living, activity labels: Volume 1

The Activity recognition from in-the-WIld SmartwatchEs (ArWISE) dataset is based on sensor data and activity labels collected from smart watches. Sensor data consist of timestamped 10Hz accelerometer and gyroscope readings. Portions of the data are annotated with user-provided labels of their current activity.

Note: Other CASAS smart home and smartwatch datasets are also available, look for more at https://zenodo.org/communities/casas. Additional information about this dataset is available at https://zenodo.org/records/15794726 (doi: 10.5821/zenodo.15794726), datasets s1 and s2.

Csv files for each person’s data are organized into zip files by study collection dates. In cases where the same number is used for files ending in "b" and "w", "b" represents a watch worn while sleeping and "w" is the daytime watch. Volume 1 contains data collected for 31 participants, representing 2 distinct data collections. Each file includes a header with feature names. 

Features

stamp: date and time of the sensor reading (string)

yaw, pitch, roll, rotation_rate_x, rotation_rate_y, rotation_rate_z, user_acceleration_x, user_acceleration_y, user_acceleration_z: 3d movement (float)

user_activity_label: string