HAR-GCNN: Deep Graph CNNs for Human Activity Recognition From Highly Unlabeled Mobile Sensor Data.
Abduallah A. MohamedFernando LejarzaStephanie CahailChristian G. ClaudelEdison ThomazPublished in: PerCom Workshops (2022)
Keyphrases
- sensor data
- human activity recognition
- human activities
- wearable devices
- sensor networks
- activity recognition
- data streams
- visual surveillance
- sensor measurements
- sensor readings
- ubiquitous computing
- health monitoring
- smart environments
- mobile devices
- unsupervised learning
- active learning
- smart home
- training data
- multiple sensors
- daily life
- prior knowledge
- semi supervised learning
- supervised learning
- mobile applications
- expert systems
- user interface
- action recognition
- labeled data
- sensor data streams
- raw sensor data