A hybrid prototype selection-based deep learning approach for anomaly detection in industrial machines.
Rodrigo de Paula MonteiroMariela Cerrada-LozadaDiego Roman Cabrera MendietaRené-Vinicio SánchezCarmelo José Albanez Bastos FilhoPublished in: Expert Syst. Appl. (2022)
Keyphrases
- anomaly detection
- deep learning
- prototype selection
- unsupervised learning
- selection algorithm
- intrusion detection
- anomalous behavior
- detecting anomalies
- nearest neighbor classifier
- machine learning
- network intrusion detection
- nearest neighbor classification
- feature selection
- network traffic
- nearest neighbor
- supervised learning
- one class support vector machines
- negative selection algorithm
- detect anomalies
- weakly supervised
- intrusion detection system
- data sets
- multi class
- semi supervised
- expectation maximization
- knn
- pairwise
- similarity measure
- computer vision
- text classification