Online one pass clustering of data streams based on growing neural gas and fuzzy inference systems

The clustering of big data streams has become a challenging task due to time and space constraints of the hardware and decreasing accuracy when the dimensionality of input data grows in time. In this paper, fuzzy growing neural gas is introduced, an online fuzzy approach for clustering data streams based on the growing neural gas algorithm, by adopting more restrictive criteria for selecting the winner nodes in the topological graph constructed at each iteration of the algorithm. The algorithm is tested on public datasets, and the results show improvements over existing clustering methods.

Automated summary

This paper introduces an online fuzzy approach for clustering data streams based on the growing neural gas algorithm, with more restrictive criteria for selecting winner nodes in the topological graph, showing improvements over existing clustering methods when tested on public datasets.