Research Article
New Fuzzy Support Vector Machine for the Class Imbalance Problem in Medical Datasets Classification
Algorithm 1
FSVM-CIP in the linear case.
Input: | Training samples | Testing samples | Output: | The predicted labels of data | Procedure: | (1) Compute fuzzy membership using (22) or (23) for the data | (2) Construct data adjacency graph using nearest neighbors and compute the edge weights matrix with examples | (3) Construct local within-class preserving scatter matrix using (8) | (4) Choose parameters (6); and (8) | (5) Compute using (15) and using (17) with a QP Solver | (6) Using decision function (19) with samples , and output the final class labels |
|