A Machine Learning Approach for Specification of Spinal Cord Injuries Using Fractional Anisotropy Values Obtained from Diffusion Tensor Images

Table 5

The best accuracy of the base dataset, extended dataset, and feature selection applied dataset using KNN and SVM.

	Base dataset; (4 features)	Extended dataset; (15 features)	FS applied dataset; (𝑛 feature)
KNN	0.901	0.914	0.938 (𝑛=2)
SVM	0.932	0.927	0.933 (𝑛=8)