Abstract
This chapter provides frameworks for association and classification rules discovery from relational data. The frameworks are specialized versions of the general granular computing framework for mining relational data. The chapter also shows that the time complexity of generating rules from a granular representation of relational data can be decreased.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
If a set of values consists of one element, then the set is replaced with the element.
- 2.
An argument preceded by symbol “+” (“-”) has to be replaced with an input (output) variable. The first argument of function mode (i.e. value 1) means that the relation purchase can be used in the construction of a pattern at most once.
- 3.
Allowed specializations or generalizations of a given rule are understood as those rules that can be formed according to given constraints.
- 4.
The granule \((customer(A,\_,\_,\_,\_,yes),\emptyset )\) can be transformed into the rule \(customer(A,\_,\_,\_,\_,1)\leftarrow 1\), where the rule premise is satisfied by any object.
- 5.
attr(o) is the collection of all components of an object o.
- 6.
P(X) is the power set of X.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this chapter
Cite this chapter
Hońko, P. (2017). Association Discovery and Classification Rule Mining. In: Granular-Relational Data Mining. Studies in Computational Intelligence, vol 702. Springer, Cham. https://doi.org/10.1007/978-3-319-52751-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-52751-2_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-52750-5
Online ISBN: 978-3-319-52751-2
eBook Packages: EngineeringEngineering (R0)