Machine-Learning Approach to Optimize SMOTE Ratio in Class Imbalance Dataset for Intrusion Detection.
Jae-Hyun SeoYong-Hyuk KimPublished in: Comput. Intell. Neurosci. (2018)
Keyphrases
- intrusion detection
- class imbalance
- machine learning
- active learning
- class distribution
- cost sensitive learning
- intrusion detection system
- anomaly detection
- feature selection
- cost sensitive
- data mining
- imbalanced datasets
- minority class
- concept drift
- network security
- imbalanced data
- imbalanced data sets
- class imbalanced
- high dimensionality
- majority class
- outlier mining
- learning algorithm
- training data
- sampling methods
- pattern recognition
- benchmark datasets
- computer vision
- training dataset
- misclassification costs
- machine learning methods
- test set
- supervised learning
- model selection
- text classification
- text mining
- information retrieval
- knowledge discovery
- support vector machine
- data analysis
- database systems
- data sets
- decision trees
- training examples
- text categorization
- labeled data
- object recognition
- learning process
- training set