| Autor: |
Hazarika, Irani, Mahanta, Anjana Kakoti |
| Zdroj: |
Advances in Data Analysis & Classification; Sep2022, Vol. 16 Issue 3, p593-616, 24p |
| Abstrakt: |
Interval data, a special case of symbolic data, are becoming more frequent in different fields of applications due to the uncertainty in the observations or to reduce large data volume. Objects in an interval dataset with two interval variables can be defined as a set of rectangles in two dimensional spaces, where each variable contains an interval describing an attribute of an object. Such a dataset can be named as rectangle dataset. In this paper, we introduce a new notion called maximal frequent rectangle, which is an extension of the notion of maximal frequent intervals and provide solutions to mine maximal frequent rectangles from a rectangle dataset. Moreover, some important properties of rectangles as well as maximal frequent rectangles with related mathematical proofs and probable applications are discussed here. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
Full text from SpringerLink