Material Detail

This video was recorded at 15th International Multiconference on Information Society, Ljubljana 2012. In the data stream computational model examples are processed once, using restricted computational resources and storage capabilities. The goal of data stream mining consists of learning a decision model, under these constraints, from sequences of observations generated from environments with unknown dynamics. Most of the stream mining works focus on centralized approaches. The phenomenal growth of mobile and embedded devices coupled with their ever-increasing computational and communications capacity presents exciting new opportunities for real-time, distributed intelligent data analysis in ubiquitous environments. In domains like sensor networks, smart grids, social cars, ambient intelligence, etc. centralized approaches have limitations due to communication constraints, power consumption, and privacy concerns. Distributed online algorithms are highly needed to address the above concerns. The focus of this presentation is on distributed stream clustering algorithms that are highly scalable, computationally efficient and resource-aware. These features enable the continued operation of data stream mining algorithms in highly dynamic mobile and ubiquitous environments.

Disciplines:

• Science and Technology  / Computer Science  / Programming & Programming Languages