Analysis-driven data collection, integration and preparation for visualisation

Bernhard Thalheim, Yasushi Kiyoki

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

Data analysis based on spatial and temporal relationships leads to new knowledge discovery in multi-database environments. As various and almost infinite relationships are potentially existing among heterogeneous databases, it is important to realize an objective-based dynamic data analysis environment with appropriate data collection from selected databases. These databases are integrated within a meso database which combines the data from different databases into one redundant data store. Typically the data store consists of a number of data cubes. These cubes are recharged whenever micro data changes depending on a recharge policy. The meso database is then use for population of the analysis databases which contains data according to the analysis demands. After application of analysis or data mining functions the result presentation database is populated. We develop a novel approach to data analysis by turning topsy-turvy the analysis task. The analysis task drives the features of the data collectors. These collectors are small databases which collect data within their interest profile. Data from the collector databases are then used for the presentation database. The feature of this approach is to realize dynamic data integration and analysis among heterogeneous databases by computing spatial and temporal interrelationships objective-dependently, and such integration realizes to retrieve, analyse and extract new information generated with a viewpoint of spatial and temporal occurrences among legacy databases.

Original languageEnglish
Title of host publicationFrontiers in Artificial Intelligence and Applications
Pages142-160
Number of pages19
Volume251
DOIs
Publication statusPublished - 2013

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume251
ISSN (Print)09226389

Fingerprint

Visualization
Data mining
Data integration

Keywords

  • active data mining
  • dataspace exploration
  • event-oriented data analysis

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Thalheim, B., & Kiyoki, Y. (2013). Analysis-driven data collection, integration and preparation for visualisation. In Frontiers in Artificial Intelligence and Applications (Vol. 251, pp. 142-160). (Frontiers in Artificial Intelligence and Applications; Vol. 251). https://doi.org/10.3233/978-1-61499-177-9-142

Analysis-driven data collection, integration and preparation for visualisation. / Thalheim, Bernhard; Kiyoki, Yasushi.

Frontiers in Artificial Intelligence and Applications. Vol. 251 2013. p. 142-160 (Frontiers in Artificial Intelligence and Applications; Vol. 251).

Research output: Chapter in Book/Report/Conference proceedingChapter

Thalheim, B & Kiyoki, Y 2013, Analysis-driven data collection, integration and preparation for visualisation. in Frontiers in Artificial Intelligence and Applications. vol. 251, Frontiers in Artificial Intelligence and Applications, vol. 251, pp. 142-160. https://doi.org/10.3233/978-1-61499-177-9-142
Thalheim B, Kiyoki Y. Analysis-driven data collection, integration and preparation for visualisation. In Frontiers in Artificial Intelligence and Applications. Vol. 251. 2013. p. 142-160. (Frontiers in Artificial Intelligence and Applications). https://doi.org/10.3233/978-1-61499-177-9-142
Thalheim, Bernhard ; Kiyoki, Yasushi. / Analysis-driven data collection, integration and preparation for visualisation. Frontiers in Artificial Intelligence and Applications. Vol. 251 2013. pp. 142-160 (Frontiers in Artificial Intelligence and Applications).
@inbook{0394c394ad8543b1b2ef9330b9c6aa32,
title = "Analysis-driven data collection, integration and preparation for visualisation",
abstract = "Data analysis based on spatial and temporal relationships leads to new knowledge discovery in multi-database environments. As various and almost infinite relationships are potentially existing among heterogeneous databases, it is important to realize an objective-based dynamic data analysis environment with appropriate data collection from selected databases. These databases are integrated within a meso database which combines the data from different databases into one redundant data store. Typically the data store consists of a number of data cubes. These cubes are recharged whenever micro data changes depending on a recharge policy. The meso database is then use for population of the analysis databases which contains data according to the analysis demands. After application of analysis or data mining functions the result presentation database is populated. We develop a novel approach to data analysis by turning topsy-turvy the analysis task. The analysis task drives the features of the data collectors. These collectors are small databases which collect data within their interest profile. Data from the collector databases are then used for the presentation database. The feature of this approach is to realize dynamic data integration and analysis among heterogeneous databases by computing spatial and temporal interrelationships objective-dependently, and such integration realizes to retrieve, analyse and extract new information generated with a viewpoint of spatial and temporal occurrences among legacy databases.",
keywords = "active data mining, dataspace exploration, event-oriented data analysis",
author = "Bernhard Thalheim and Yasushi Kiyoki",
year = "2013",
doi = "10.3233/978-1-61499-177-9-142",
language = "English",
isbn = "9781614991762",
volume = "251",
series = "Frontiers in Artificial Intelligence and Applications",
pages = "142--160",
booktitle = "Frontiers in Artificial Intelligence and Applications",

}

TY - CHAP

T1 - Analysis-driven data collection, integration and preparation for visualisation

AU - Thalheim, Bernhard

AU - Kiyoki, Yasushi

PY - 2013

Y1 - 2013

N2 - Data analysis based on spatial and temporal relationships leads to new knowledge discovery in multi-database environments. As various and almost infinite relationships are potentially existing among heterogeneous databases, it is important to realize an objective-based dynamic data analysis environment with appropriate data collection from selected databases. These databases are integrated within a meso database which combines the data from different databases into one redundant data store. Typically the data store consists of a number of data cubes. These cubes are recharged whenever micro data changes depending on a recharge policy. The meso database is then use for population of the analysis databases which contains data according to the analysis demands. After application of analysis or data mining functions the result presentation database is populated. We develop a novel approach to data analysis by turning topsy-turvy the analysis task. The analysis task drives the features of the data collectors. These collectors are small databases which collect data within their interest profile. Data from the collector databases are then used for the presentation database. The feature of this approach is to realize dynamic data integration and analysis among heterogeneous databases by computing spatial and temporal interrelationships objective-dependently, and such integration realizes to retrieve, analyse and extract new information generated with a viewpoint of spatial and temporal occurrences among legacy databases.

AB - Data analysis based on spatial and temporal relationships leads to new knowledge discovery in multi-database environments. As various and almost infinite relationships are potentially existing among heterogeneous databases, it is important to realize an objective-based dynamic data analysis environment with appropriate data collection from selected databases. These databases are integrated within a meso database which combines the data from different databases into one redundant data store. Typically the data store consists of a number of data cubes. These cubes are recharged whenever micro data changes depending on a recharge policy. The meso database is then use for population of the analysis databases which contains data according to the analysis demands. After application of analysis or data mining functions the result presentation database is populated. We develop a novel approach to data analysis by turning topsy-turvy the analysis task. The analysis task drives the features of the data collectors. These collectors are small databases which collect data within their interest profile. Data from the collector databases are then used for the presentation database. The feature of this approach is to realize dynamic data integration and analysis among heterogeneous databases by computing spatial and temporal interrelationships objective-dependently, and such integration realizes to retrieve, analyse and extract new information generated with a viewpoint of spatial and temporal occurrences among legacy databases.

KW - active data mining

KW - dataspace exploration

KW - event-oriented data analysis

UR - http://www.scopus.com/inward/record.url?scp=84873191560&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873191560&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-177-9-142

DO - 10.3233/978-1-61499-177-9-142

M3 - Chapter

AN - SCOPUS:84873191560

SN - 9781614991762

VL - 251

T3 - Frontiers in Artificial Intelligence and Applications

SP - 142

EP - 160

BT - Frontiers in Artificial Intelligence and Applications

ER -