A Novel Semi-Supervised Learning Method Based on Fast Search and Density Peaks

Figure 16

The sequence diagram of the LCI algorithm for identifying DP clustering results in Figure 15(b). (a) Visualization of DP clustering results after removing the interference samples; (b) LCI’s final recognition visualization of DP clustering. represents the clustering core; represents the initial labeled sample; represents the sample of the next step of the algorithm to be identified; represents the sample for labeling errors.

(a)

(b)