Skip to main content
Fig. 7 | Journal of the Brazilian Computer Society

Fig. 7

From: Microalgae classification using semi-supervised and active learning based on Gaussian mixture models

Fig. 7

Comparison of active learning metrics against a random selection using the second dataset, with results showing the average and standard deviation for the datasets with ten different instances. The vertical axis represents the accuracy and the horizontal axis represents the number of active samples informed to the system. a Accuracy for 1 % of initial semi-supervision, b MaxF1 for 1 % of initial semi-supervision, c accuracy for 3 % of initial semi-supervision, d MaxF1 for 3 % of initial semi-supervision, e accuracy for 5 % of initial semi-supervision, f MaxF1 for 5 % of initial semi-supervision (color figure online)

Back to article page