On Segment-Based Stream Modeling and Its Applications.

14 years 1 months ago

Download www.siam.org

The primary constraint in the eﬀective mining of data streams is the large volume of data which must be processed in real time. In many cases, it is desirable to store a summary of the data stream segments in order to perform data mining tasks. Since density estimation provides a comprehensive overview of the probabilistic data distribution of a stream segment, it is a natural choice for this purpose. A direct use of density distributions can however turn out to be an ineﬃcient storage and processing mechanism in practice. In this paper, we introduce the concept of cluster histograms, which provides an eﬃcient way to estimate and summarize the most important data distribution proﬁles over diﬀerent stream segments. These proﬁles can be constructed in a supervised or unsupervised way depending upon the nature of the underlying application. The proﬁles can also be used for change detection, anomaly detection, segmental nearest neighbor search, or supervised stream segment c...

Charu C. Aggarwal

Real-time Traffic