SDDSMOTE: Synthetic Minority Oversampling Technique based on Sample Density Distribution for Enhanced Classification on Imbalanced Microarray Data.
Qikang WanXiongshi DengMin LiHaotian YangPublished in: ICCDA (2022)
Keyphrases
- microarray data
- class imbalance
- minority class
- microarray data analysis
- density distribution
- feature selection
- microarray
- gene selection
- dna microarray data
- gene expression
- microarray datasets
- cancer classification
- class distribution
- class imbalanced
- small number of samples
- dna microarray
- gene expression profiles
- support vector machine
- gene expression data
- ovarian cancer
- microarray analysis
- support vector machine svm
- high dimensionality
- data sets
- cluster analysis
- text classification
- training set
- pattern recognition
- machine learning
- arbitrary shape
- training samples
- model selection
- feature space
- support vector
- feature extraction
- cost sensitive learning
- decision boundary
- random forest
- gene sets
- cost sensitive
- cancer diagnosis
- machine learning methods
- supervised learning
- knn