From Linear Programming Approach to Metaheuristic Approach: Scaling Techniques

The objective of this work is to propose ten efficient scaling techniques for the Wisconsin Diagnosis Breast Cancer (WDBC) dataset using support vector machine (SVM). These are linear programming approach. SVM with proposed was applied on WDBC dataset. are, namely, arithmetic mean, de Buchet three cases p = 1,2 , and ∞ , equilibration, geometric IBM MPSX, and Lp-norm id="M2"> . experimental results show that equilibration technique overcomes benchmark normalization used in many commercial solvers. Finally, also effectiveness grid search which gets optimal parameters (C gamma) classifier.