Publication detail

Data Cleaning Functionality in DMSL

KOTÁSEK, P., ZENDULKA, J.

Original Title

Data Cleaning Functionality in DMSL

English Title

Data Cleaning Functionality in DMSL

Type

conference paper

Language

en

Original Abstract

Probably the most crucial step in the knowledge discovery in databases (KDD) process is data preparation because valuable knowledge can be obtained only from data that exposes its semantic content in the right way. Data cleaning is one of activities done during this step. But it does not receive much attention among the data mining community, including support in data mining languages. The Data Mining Specification Language (DMSL) presented in the paper aims to contribute to this topic. Some features of the language concerning data cleaning and a simple example are shown in the paper.

English abstract

Probably the most crucial step in the knowledge discovery in databases (KDD) process is data preparation because valuable knowledge can be obtained only from data that exposes its semantic content in the right way. Data cleaning is one of activities done during this step. But it does not receive much attention among the data mining community, including support in data mining languages. The Data Mining Specification Language (DMSL) presented in the paper aims to contribute to this topic. Some features of the language concerning data cleaning and a simple example are shown in the paper.

Keywords

Knowledge discovery, data mining, data cleaning, data mining language, DMSL

RIV year

2003

Released

28.04.2003

Location

Ostrava

ISBN

80-85988-84-4

Book

Proceedings of 6th International Conference ISIM'03 Information Systems Implementation and Modelling

Pages from

99

Pages to

108

Pages count

10

Documents

BibTex


@inproceedings{BUT14190,
  author="Petr {Kotásek} and Jaroslav {Zendulka}",
  title="Data Cleaning Functionality in DMSL",
  annote="Probably the most crucial step in the knowledge
discovery in databases (KDD) process is data preparation because
valuable knowledge can be obtained only from data that exposes its
semantic content in the right way. Data cleaning is one of activities
done during this step. But it does not receive much attention among the
data mining community, including support in data mining languages. The
Data Mining Specification Language (DMSL) presented in the paper aims
to contribute to this topic. Some features of the language concerning
data cleaning and a simple example are shown in the paper.",
  booktitle="Proceedings of 6th International Conference ISIM'03 Information Systems Implementation and Modelling",
  chapter="14190",
  year="2003",
  month="april",
  pages="99--108",
  type="conference paper"
}