Mining Emerging Patterns and Classification in Data Streams
Hamad Alhammady, Kotagiri Ramamohanarao · 2005
A data stream model has been proposed recently for those data intensive applications such as financial applications, manufacturing, and others (Babcock et al., 2002). In this model, data arrives in multiple, continuous, rapid, time-varying data streams. These characteristics make it infeasible for traditional classification and mining techniques to deal with data streams. In this paper, we propose a novel method for mining emerging patterns (EPs) in data streams. Moreover, we show how these EPs can be used to classify data streams. EPs (Dong and Li, 1999) are those itemsets whose supports in one class are significantly higher than their supports in the other classes. The experimental evaluation shows that our proposed method can achieve up to 10% increase in accuracy compared to the other methods.