Classification accuracy of RF, SVM, and WKNN on 100–500 features selected by different methods for imbalanced simulated datasets.

Classification accuracy of RF, SVM, and WKNN on 100–500 features selected by different methods for imbalanced simulated datasets.

<p>Classification accuracy of RF, SVM, and WKNN on 100–500 features selected by different methods for imbalanced simulated datasets.</p>

Saved in:

Bibliographic Details
Main Author:	Sheema Gul (21519289) (author)
Other Authors:	Dost Muhammad Khan (3368810) (author), Saeed Aldahmani (15353913) (author), Zardad Khan (3368813) (author)
Published:	2025
Subjects:	Cell Biology Genetics Immunology Infectious Diseases Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified xlink "> high nearest neighbors classifiers margin weights extracted e ., accuracy amplification factor along feature ranking process using random forest support vector machines paper also gives minority amplification factor proportional overlap score proposed method outperforms features thereby highlighting ensemble minimum redundancy discard redundant genes minority class observation feature selection methods robust weighted score feature selection proposed method support vectors robust solution constrained using also generated existing methods conventional methods class separation class imbalance fisher score wilcoxon rank weighted signal unbalanced data sum test study proposes rds integrates ranked genes noise ratio maximum relevance key challenges k </ futher assess discriminative power deeper understanding binary classification
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!

Cannot write session to /tmp/vufind_sessions/sess_5lvdgdmv1q27mboq8m5m7qu42b