An Attractive Leader Approach Based Clustering for Non-Symmetric Proximity
Bapu B. Kiranagi, D. S. Guru · 2007
In this paper, the importance of non-symmetric proximity between symbolic data is discussed and a new algorithm for clustering is proposed. The proposed algorithm works directly on the non-symmetric proximity matrices and is based on the leader oriented incremental approach. Experiments on the standard symbolic data sets have been conducted in order to study the efficacy of the proposed methodology