Computer-Assisted Diagnosis for Diabetic Retinopathy Based on Fundus Images Using Deep Convolutional Neural Network

Table 4

Accuracy comparison when using different classifiers and different parameter optimization methods on each dataset.

Dataset	Method
	SVM			RF [39]
	Without optimization	Default parameter searching	TLBO
Five-fold cross validation (using training data)	88.744%	96.5724%	—	—
Validation data	85.4%	79.6%	—	84.7%
Test data	86.1177%	81.0573%	86.17%	86.02%