Skip to main content

Table 3 F-Score (FS) comparison between dividing the dataset based on characteristic keywords and taking it as a whole

From: Cleaning by clustering: methodology for addressing data quality issues in biomedical metadata

  cutCluster K-medoid DBSCAN APCluster StdHier
Average [Min, Max] 0.63 [0.43, 0.94] 0.61 [0.41, 0.86] 0.62 [0.49, 0.87] 0.57 [0.35, 0.68] 0.6 [0.4, 0.81]
As a whole dataset 0.43 0.4 0.37 0.34 0.4