Hybrid classifiers and data stream recognition

Michal Wozniak.

Prof. Michal Wozniak, Ph.D., D.Sc.
Department of Systems and Computer Networks, Faculty of Electronics, Wroclaw University of Technology
Wybrzeze Wyspianskiego 27,50-370 Wroclaw, Poland

Tutorial description

The main aims of this talk is to deliver a either definite or compact knowledge on how hybridization can help improving the quality of computer classification systems. In order to make readers clearly realize the knowledge of hybridization, this tutorial primarily focuses on introducing the different levels of hybridization and illuminating what problems we will face with as dealing with such projects. In the first instance the data and knowledge incorporated in hybridization were the action points, and then a still growing up area of classifier systems known as combined classifiers was considered.

Additionally one of the hot topic of pattern classification devoted data stream classification will be discussed. We will present the concept drift phenomena, its taxonomy and the main methods how to deal with it with a special attention to the ensemble methods.

The tutorial will be based on the latest book of Prof. Wozniak: Hybrid classifiers: Method of Data, Knowledge, and Data Hybridization, Springer, 2014, http://www.springer.com/engineering/computational+intelligence+and+complexity/book/978-3-642-40996-7.