Title :
Research and experiment on Affinity Propagation clustering algorithm
Author :
Zhang, Huan ; Song, Kun
Author_Institution :
Coll. of Mech. & Electron. Eng., Qingdao Agric. Univ., Qingdao, China
Abstract :
This paper introduces Affinity Propagation (AP) clustering algorithm, which is intensively researched by some scholars owing to its advantage of fast speed and no need of setting the initial clusters manually. Mainly analyzed the characteristics of Affinity Propagation clustering algorithm at first, and then compared several principle similarity calculating methods based on Euclidean distance and Mahalanobis distance and etc. Experiment on AP clustering algorithm were done with the parts of the UCI data sets, thus the effectiveness of this algorithm was verified. Finally, the experimental results were analyzed in general.
Keywords :
data mining; pattern clustering; AP clustering algorithm; Euclidean distance; Mahalanobis distance; UCI data sets; affinity propagation clustering algorithm; data mining; principle similarity calculation method; Clustering algorithms; Computers; Educational institutions; Electrical engineering; Euclidean distance; Ionosphere; Vehicles; Euclidean distance; Mahalanobis Distance; UCI data set; affinity propagation clustering; similarity;
Conference_Titel :
Mechanic Automation and Control Engineering (MACE), 2011 Second International Conference on
Conference_Location :
Hohhot
Print_ISBN :
978-1-4244-9436-1
DOI :
10.1109/MACE.2011.5988401