24th Signal Processing and Communication Application Conference (SIU), Zonguldak, Türkiye, 16 - 19 Mayıs 2016, ss.1801-1804
The most important one of main problems for K-based clustering algorithm is randomly selected k parameter when running the algorithm. In this study, an automated clustering algorithm based on agglomerative clustering and clusters without taking k parameter from user have been proposed. The main objective of the study is to select correct k value by using Spearman's Correlation Coefficient. This newly proposed automatic k parameter selection method's performance was examined in the study.