Modeling and Language Support for the Pattern Management

Modeling and Language Support for the Pattern Management

Zdenka Telnarova (University of Ostrava, Czech Republic)
Copyright: © 2017 |Pages: 21
DOI: 10.4018/978-1-5225-0565-5.ch004
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Patterns are mentioned usually in the extraction context. Little stress is posed in their representation and management. This chapter is focused on the representation of the patterns, manipulation with patterns and query patterns. Crucial issue can be seen in systematic approach to pattern management and specific pattern query language which takes into consideration semantics of patterns. In the background we discuss two different approaches to the pattern store and manipulation (based on inductive database and PANDA project). General pattern model is illustrated using abstract data type implemented in Oracle. In the following chapters the introduction to querying patterns and simple scheme of the architecture PBMS is shown.
Chapter Preview
Top

Background

In general, a pattern can be defined as a compact and rich in semantics representation of raw data (Catania, Maddalena, & Mazza, 2005). Patterns can be generated from different application context. Usually patterns are extracted by using some data mining tools or other pattern recognition tools. Raw data from which the patterns are extracted change with high frequency. The question is whether existing patterns still represent the data source. It is clear that any tool for providing manipulation with patterns not only in terms of changing pattern information can be useful for users.

Several approaches have been provided for pattern management. In this chapter we can mention Inductive Database approach which is based on integrated architecture, which means that raw data and patterns are stored together, and PANDA framework relying on separated architecture where raw data and patterns are logically stored and managed by two distinct systems.

Inductive database in this context can be defined as a database that contains inductive generalization about the data, in addition to the usual data. The inductive database concept has been suggested in several papers, for example (Mannila 1997).

Complete Chapter List

Search this Book:
Reset