SVM classification of microaneurysms with imbalanced dataset based on borderline-SMOTE and data cleaning techniques.
Qingjie WangJingmin XinJiayi WuNanning ZhengPublished in: ICMV (2016)
Keyphrases
- data cleaning
- imbalanced datasets
- support vector machine
- fraud detection
- imbalanced data
- data integration
- cost sensitive learning
- class distribution
- sampling methods
- svm classifier
- text classification
- outlier detection
- support vector machine svm
- data quality
- missing values
- record linkage
- class imbalance
- minority class
- cost sensitive
- training dataset
- support vectors
- database
- kernel function
- support vector
- ensemble methods
- decision trees
- data mining techniques
- feature selection
- data warehouse
- multi class
- classification accuracy
- training set
- data mining
- classification algorithm
- unlabeled data
- nearest neighbor