A Novel Online Generalized Possibilistic Clustering Algorithm for Big Data Processing
Spyridoula D. Xenaki, Konstantinos Koutroumbas, Athanasios A. Rontogiannis · 2018
In this paper a novel efficient online possibilistic c-means clustering algorithm, called Online Generalized Adaptive Possibilistic C-Means (O-GAPCM), is presented. The algorithm extends the abilities of the Adaptive Possibilistic C-Means (APCM) algorithm, allowing the study of cases where the data form compact and hyper-ellipsoidally shaped clusters in the feature space. In addition, the algorithm performs online processing, that is the data vectors are processed one-by-one and their impact is memorized to suitably defined parameters. It also embodies new procedures for creating new clusters and merging existing ones. Thus, O-GAPCM is able to unravel on its own the number and the actual hyper-ellipsoidal shape of the physical clusters formed by the data. Experimental results verify the effectiveness of O-GAPCM both in terms of accuracy and time efficiency.