Body-worn, object and ambient sensor recordings of daily activities from four participants: 24 runs, 869,387 samples, 242 sensor channels and seven annotation tracks.
Accelerometer and gyroscope data from nine users carrying eight phones and four watches at once: 33.7 million rows built to study device heterogeneity.
6,461,328 annotated samples from 22 free-living participants wearing two accelerometers; CSVs contain eight core fields, with extra index columns in three files.
Comprehensive smart home dataset with 1,048,575 rows and 31 columns including timestamps, device states (TV, oven, lights, fridge) and activity labels for machine learning classification of daily activities.
Comprehensive smart home dataset with 1,048,575 rows and 31 columns including timestamp, device states (TV, oven, lights, fridge) and activity labels for machine learning applications.
Sensor recordings of activities by a single user in a smart home, using PIR, reed switches, force sensors, light, temperature/humidity and smart plugs; includes three CSV files for analysis.
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.
CeTI-Age-Kinematics is a full-body IMU kinematics dataset of 30 daily tasks recorded with a 19-IMU sensor suit in an age-comparative sample of 32 participants (older adults and younger controls), intended for motion analysis and activity recognition research.
Multimodal dataset from 18 subjects with wearable IMUs (wrists, torso), Bluetooth indoor localization, and first-person video capturing 12 activity categories in realistic home/office scenarios for human activity recognition and fall detection research.