An Optimized k-NN Approach for Classification on Imbalanced Datasets with Missing Data.
Ezgi Can OzanEkaterina RiabchenkoSerkan KiranyazMoncef GabboujPublished in: IDA (2016)
Keyphrases
- missing data
- knn
- imbalanced datasets
- k nearest neighbour
- k nearest neighbor
- classification algorithm
- missing values
- cost sensitive learning
- support vector machine svm
- class imbalance
- feature selection
- nearest neighbor
- support vector machine
- text classification
- text categorization
- distance function
- nearest neighbour
- incomplete data
- class distribution
- sampling methods
- feature space
- cost sensitive
- multi layer perceptron
- decision trees
- classification accuracy
- minority class
- imbalanced data
- training dataset
- neural network
- ensemble methods
- high dimensionality
- unsupervised learning
- active learning
- feature extraction
- information gain
- machine learning
- training samples
- support vector