Publikation

Building Adaptive Data Mining Models on Streaming Data in Real-Time

Frederic Theodor Stahl, Atta Badii

In: Miltos Petridis (Hrsg.). Expert Update 20 - Special edition for the UK Symposium on Knowledge Discovery and Data Mining 2019 2 Seiten 1-8 SGAI 2020.

Abstrakt

This article highlights some key concepts and emergent techniques in DSM as presented in the authors’ recent publications and also outlined in a talk given at the UK Symposium on Knowledge Discovery from Data in London on May 24th, 2019. This talk discussed the challenges, opportunities and innovative solutions in Data Stream Mining. The Idea for the talk stemmed from advances in hard and software over two decades enabling capturing of data near real-time. Because of this the research field of Data Stream Mining has been growing in order to tackle real-time analytics of Bit Data as it is being generated. There is a need to build and update models in real-time as new data becomes available in order to maintain model accuracy over time. Applications are for example telecommunications data, telemetric data from industry plants, cyber security, micro-blogging data, etc.

ExpertUpdate_UKKDD2019_FredericStahl.pdf (pdf, 164 KB)

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence