Semi-supervised detection of structural damage using Variational Autoencoder and a One-Class Support Vector Machine.
Andrea PollastroGiusiana TestaAntonio BilottaRoberto PrevetePublished in: CoRR (2022)
Keyphrases
- semi supervised
- one class support vector machines
- anomaly detection
- semi supervised learning
- damage detection
- false positives
- detection method
- detection algorithm
- false alarms
- pairwise
- structural information
- detection rate
- image segmentation
- automatic detection
- detection accuracy
- unsupervised learning
- multi view
- supervised learning
- object detection
- semi supervised classification
- optical flow
- unlabeled data
- data sets
- labeled data
- pattern recognition
- active learning
- data mining