Citizen Privacy Framework by Aigul Kaskina

Citizen Privacy Framework by Aigul Kaskina

Author:Aigul Kaskina
Language: eng
Format: epub
ISBN: 9783031060212
Publisher: Springer International Publishing


Step

Step 1: Initialise the parameters of the algorithm, except for the number of clusters, c

Step 2: Run the algorithms for different values of c’s over the range , where

Step 3: Compute the validity index for each partition (U, V ) obtained from step 2

Step 4: Choose the optimal partition and the optimal c according to the criteria

The validation indexes were calculated using the R package “fclust”.7 The results of the FCM validation procedure are displayed in Table 3.11 and PAM in Table 3.12. There are no explicit guidelines on choosing optimal number of clusters based on indexes values. As it can be seen from Tables 3.11 and 3.12, not all indexes agree on the same number of clusters, and therefore, the value of optimal number of clusters was selected on the agreed majority of indexes. Highlighted in bold is the optimal value of c selected by each index according to its criteria mentioned in Table 3.9. Table 3.11Cluster validation of FCM clustering algorithms



Download



Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.