Deep embedding kernel mixture networks for conditional anomaly detection in high-dimensional data.
Hyojoong KimHeeyoung KimPublished in: Int. J. Prod. Res. (2023)
Keyphrases
- anomaly detection
- high dimensional data
- nonlinear dimensionality reduction
- laplacian eigenmaps
- input space
- dimensionality reduction
- nearest neighbor
- low dimensional
- high dimensional
- detecting anomalies
- anomalous behavior
- intrusion detection
- data points
- data sets
- low dimensional structure
- subspace clustering
- data analysis
- network traffic
- intrusion detection system
- manifold learning
- low rank
- similarity search
- dimension reduction
- locally linear embedding
- one class support vector machines
- unsupervised learning
- feature space
- high dimensional spaces
- network intrusion detection
- network anomaly detection
- linear discriminant analysis
- latent space
- lower dimensional
- kernel pca
- kernel methods
- expectation maximization
- support vector
- negative selection algorithm
- subspace learning
- kernel matrix
- input data
- machine learning
- clustering high dimensional data
- clustering method
- decision trees
- data mining