An Efficient Classification Approach for Novel Class Detection by Evolving Feature Datastreams
Data stream classification has been an extensively studied research problem in recent years. Data stream classification requires efficient and effective techniques that are significantly different from static data classification techniques because of its dynamic nature. Existing system faces major challenges in the methods namely feature-evolution, infinite length, concept-drift and concept-evolution. To address and overcome the problems in these techniques an ensemble classification framework is proposed where each classifier is equipped with a novel class detector and addresses concept-drift and concept-evolution.