Effective Similarity Analysis over Event Streams Based on Sharing Extent

  • Authors:

  • Yanqiu Wang;Ge Yu;Tiancheng Zhang;Dejun Yue;Yu Gu;Xiaolong Hu

  • Affiliations:

  • School of Information Science and Engineering, Northeastern University, China;School of Information Science and Engineering, Northeastern University, China;School of Information Science and Engineering, Northeastern University, China;School of Information Science and Engineering, Northeastern University, China;School of Information Science and Engineering, Northeastern University, China;School of Information Science and Engineering, Northeastern University, China

  • Venue:
  • APWeb/WAIM '09 Proceedings of the Joint International Conferences on Advances in Data and Web Management
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

With the development of event-driven applications, event stream processing has received more and more attentions in database community. However, little work has focused on the problem of data mining and similarity analysis among event streams. As the foundation for the data mining such as frequent or abnormal event pattern detection, efficient similarity search is desired to be first executed. In this paper, we attempt to take the first step into the similarity search in the context of vast event streams. We propose a simple but effective model to improve the efficiency of the similarity search. To avoid redundant pair-wise comparison, we adopt the definition of sharing extent to dramatically filter dissimilar event streams and speed up the calculation of similarity. Extensive simulated experiments have demonstrated that our model and algorithm can lead to higher efficiency when guaranteeing expected accuracy.