Performance evaluation of SVM and iterative FSVM classifiers with bootstrapping-based over-sampling and under-sampling.
A. ZughratMahdi MahfoufS. ThorntonPublished in: FUZZ-IEEE (2015)
Keyphrases
- fuzzy support vector machine
- support vector
- svm classifier
- imbalanced data
- support vector machine classifiers
- training data
- support vector machine svm
- support vector machine
- feature selection
- training set
- hybrid model
- improves the classification accuracy
- classification algorithm
- linear support vector machines
- decision boundary
- decision trees
- high classification accuracy
- minority class
- linear classifiers
- kernel function
- hyperplane
- svm classification
- feature vectors
- fold cross validation
- ensemble classifier
- bayes classifier
- input features
- random sampling
- fuzzy support vector machines
- svm training
- feature space
- classification accuracy
- logistic regression
- feature set
- classification method
- kernel support vector machines
- rule based classifier
- knn
- bayesian classifiers
- text classification
- small sample
- sampling methods
- training examples
- kernel methods
- machine learning
- machine learning algorithms
- classifier training
- train a support vector machine
- cross validation
- rbf kernel
- support vectors
- class labels
- multiple kernel learning
- k nearest neighbor
- training samples
- text classifiers
- relation extraction
- image classification
- multi class
- information extraction
- highest accuracy
- class imbalance
- unbalanced data
- multiclass classification
- support vector regression
- feature extraction
- naive bayes