Hybrid Feature Selection Based Weighted Least Squares Twin Support Vector Machine Approach for Diagnosing Breast Cancer, Hepatitis, and Diabetes

Table 6

Comparison of predictive accuracies of proposed and other classifiers for Hepatitis.

Reference	Approach	Predictive accuracy
This study	HFS + WLSTSVM	87.50%
Ster and Dobnikar [27]	CART decision tree	82.7%
Ster and Dobnikar [27]	LVQ	83.2%
Ster and Dobnikar [27]	MLP with BP	82.1%
Ster and Dobnikar [27]	ASR	85%
Ster and Dobnikar [27]	QDA	85.8%
Rafal Adamczak [47]	RBF (Tooldiag)	79.0%
Rafal Adamczak [47]	MLP + BP (Tooldiag)	77.4%