Querying and Mining Uncertain Data Streams

Data uncertainty widely exists in many applications, and an uncertain data stream is a series of uncertain tuples that arrive rapidly. However, traditional techniques for deterministic data streams cannot be applied to deal with data uncertainty directly due to the exponential growth of possible solution space.

This book provides a comprehensive overview of the authors' work on querying and mining uncertain data streams. Its contents include some important discoveries dealing with typical topics such as top-k query, ER-Topk query, rarity estimation, set similarity, and clustering.

Querying and Mining Uncertain Data Streams is written for professionals, researchers, and graduate students in data mining and its various related fields.

Contents:

• Introduction
• Top-k Queries Over the Sliding-window Model
• ER-Topk Query Over the Landmark Model
• Rarity Estimation
• Set Similarity
• Clustering
• Conclusion

Readership: Students and Professionals involved in data mining, big data, and data gathering.
Key Features:

• The first book on uncertain data stream management
• There exist significant contributions on typical topics