CarSite-II: an integrated classification algorithm for identifying carbonylated sites based on K-means similarity-based undersampling and synthetic minority oversampling techniques.
Yun ZuoJianyuan LinXiangxiang ZengQuan ZouXiangrong LiuPublished in: BMC Bioinform. (2021)
Keyphrases
- classification algorithm
- majority class
- class imbalance
- k means
- minority class
- concept drift
- class distribution
- training set
- clustering algorithm
- naive bayes
- support vector machine
- misclassification costs
- knn
- training phase
- k nearest neighbor
- base learners
- cost sensitive
- class labels
- classification method
- website
- attribute selection
- classification rules
- training data
- cost sensitive learning
- real world
- active learning
- reinforcement learning
- learning algorithm
- multi class
- classifier ensemble
- input features
- text categorization
- document classification
- data sets
- nearest neighbor
- pairwise
- decision trees
- e learning
- neural network
- databases