Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
4970338 | Pattern Recognition Letters | 2017 | 7 Pages |
â¢An Adjustable Preference Affinity Propagation (APAP) algorithm is proposed.â¢The initial value of each element preference pk is determined according to the data distribution.â¢Element preference pk can be automatically adjusted during the iteration process.â¢Experiments on synthetic and real data verify the effectiveness and the advantages of APAP.
A new Affinity Propagation (AP) algorithm, Adjustable Preference Affinity Propagation (APAP) algorithm, is proposed in this work. The distinguishing features of APAP algorithm are that the initial value of each element preference pk is independently determined according to the data distribution and pk will be automatically adjusted during the iteration process. Experiments on synthetic data and real data are carried out. Experimental results verified the effectiveness of the proposed APAP algorithm. Compared with the standard AP algorithm, APAP algorithm has a better overall performance and can obtain better clustering results.