ADC '99

A Query-Sensitive Cost Model for Similarity Queries with M-tree

Paolo Ciaccia, Alessandro Nanni, and Marco Patella

Click here to start

Contents

A Query-Sensitive Cost Model for Similarity Queries with M-tree

Similarity Search

A Data Mining Example (Ester et al. VLDB '98)

The M-tree (VLDB '97)

Range Query

What about Performance?

Average-Case Model (PODS '98)

Limitations of the A-C Model

The Query-sensitive Model

Witnesses

How Witnesses Are Chosen

How d.d.'s Are Combined

Experimental Evaluation

Choosing the Witnesses

Variants of the Model

Influence of the Query Volume

Conclusions

Contacting the Authors

Author: Marco Patella

E-mail: mpatella@deis.unibo.it

Home Page: http://www-db.deis.unibo.it/~mpatella