SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data.
Chi Ian TangIgnacio Perez-PozueloDimitris SpathisSøren BrageNicholas J. WarehamCecilia MascoloPublished in: CoRR (2021)
Keyphrases
- human activity recognition
- unlabeled data
- semi supervised learning
- co training
- semi supervised
- labeled data
- activity recognition
- semi supervised classification
- training set
- human activities
- active learning
- text classification
- supervised learning
- abundant unlabeled data
- labeled examples
- labeled training data
- labeled and unlabeled data
- training data
- multi view
- learning algorithm
- single view
- text categorization
- transfer learning
- class labels
- unsupervised learning
- label propagation
- data points
- training examples
- data sets
- pairwise
- information retrieval
- semi supervised learning algorithms
- multi class
- domain adaptation
- visual surveillance
- decision boundary
- similarity measure
- decision trees
- sensor data