Assessing the impact of bag-of-words versus word-to-vector embedding methods and dimension reduction on anomaly detection from log files.
Ziyu QiuZhilei ZhouBrad NiblettAndrew JohnstonJeffrey SchwartzentruberNur Zincir-HeywoodMalcolm I. HeywoodPublished in: Int. J. Netw. Manag. (2024)
Keyphrases
- anomaly detection
- bag of words
- dimension reduction
- log files
- n gram
- unsupervised learning
- image classification
- text classification
- feature extraction
- action recognition
- principal component analysis
- website
- image representation
- high dimensional
- feature selection
- singular value decomposition
- dimensionality reduction
- high dimensional data
- cluster analysis
- low dimensional
- language model
- feature vectors
- feature space
- co occurrence
- neural network
- preprocessing
- clustering method
- image features
- supervised learning
- semi supervised
- image retrieval
- natural language
- image processing
- computer vision
- search engine