Parallel high-dimensional index structure for content-based information retrieval

Jaewoo Chang; Ahreum Lee

doi:10.1109/CIT.2008.4594657

Parallel high-dimensional index structure for content-based information retrieval

Jaewoo Chang^*
, Ahreum Lee

^*Corresponding author for this work

Jeonbuk National University

Research output: Contribution to conference › Conference paper › peer-review

2 Scopus citations

Abstract

To solve 'dimensional curse'problem, the cell-based filtering scheme has been proposed, but it shows a linear decrease in performance as the dimensionality is increased. In this paper, we propose a parallel high-dimensional index structure for content-based information retrieval so as to cope with the linear decrease in retrieval performance. In addition, we devise data insertion, range query and k-NN query processing algorithms which are suitable for a clusterbased parallel architecture. Finally, we show that our parallel index structure achieves good retrieval performance in proportion to the number of servers in the cluster-based architecture and it outperforms a parallel version of the VA-File when the dimensionality is over 10.

Original language	English
Title of host publication	Proceedings - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008
Pages	101-106
Number of pages	6
DOIs	https://doi.org/10.1109/CIT.2008.4594657
State	Published - 2008
Event	2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008 - Sydney, NSW, Australia Duration: 2008.07.8 → 2008.07.11

Publication series

Name	Proceedings - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008

Conference

Conference	2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008
Country/Territory	Australia
City	Sydney, NSW
Period	08.07.8 → 08.07.11

Quacquarelli Symonds(QS) Subject Topics

Computer Science & Information Systems
Data Science

Access to Document

10.1109/CIT.2008.4594657

Cite this

Chang, J., & Lee, A. (2008). Parallel high-dimensional index structure for content-based information retrieval. In Proceedings - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008 (pp. 101-106). Article 4594657 (Proceedings - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008). https://doi.org/10.1109/CIT.2008.4594657

@inproceedings{b65cd1327b6a4640bb8d9162f7852dee,

title = "Parallel high-dimensional index structure for content-based information retrieval",

abstract = "To solve 'dimensional curse'problem, the cell-based filtering scheme has been proposed, but it shows a linear decrease in performance as the dimensionality is increased. In this paper, we propose a parallel high-dimensional index structure for content-based information retrieval so as to cope with the linear decrease in retrieval performance. In addition, we devise data insertion, range query and k-NN query processing algorithms which are suitable for a clusterbased parallel architecture. Finally, we show that our parallel index structure achieves good retrieval performance in proportion to the number of servers in the cluster-based architecture and it outperforms a parallel version of the VA-File when the dimensionality is over 10.",

author = "Jaewoo Chang and Ahreum Lee",

year = "2008",

doi = "10.1109/CIT.2008.4594657",

language = "English",

isbn = "9781424423583",

series = "Proceedings - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008",

pages = "101--106",

booktitle = "Proceedings - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008",

note = "2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008 ; Conference date: 08-07-2008 Through 11-07-2008",

}

Chang, J & Lee, A 2008, Parallel high-dimensional index structure for content-based information retrieval. in Proceedings - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008., 4594657, Proceedings - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008, pp. 101-106, 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008, Sydney, NSW, Australia, 08.07.8. https://doi.org/10.1109/CIT.2008.4594657

Parallel high-dimensional index structure for content-based information retrieval. / Chang, Jaewoo; Lee, Ahreum.
Proceedings - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008. 2008. p. 101-106 4594657 (Proceedings - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008).

Research output: Contribution to conference › Conference paper › peer-review

TY - GEN

T1 - Parallel high-dimensional index structure for content-based information retrieval

AU - Chang, Jaewoo

AU - Lee, Ahreum

PY - 2008

Y1 - 2008

N2 - To solve 'dimensional curse'problem, the cell-based filtering scheme has been proposed, but it shows a linear decrease in performance as the dimensionality is increased. In this paper, we propose a parallel high-dimensional index structure for content-based information retrieval so as to cope with the linear decrease in retrieval performance. In addition, we devise data insertion, range query and k-NN query processing algorithms which are suitable for a clusterbased parallel architecture. Finally, we show that our parallel index structure achieves good retrieval performance in proportion to the number of servers in the cluster-based architecture and it outperforms a parallel version of the VA-File when the dimensionality is over 10.

AB - To solve 'dimensional curse'problem, the cell-based filtering scheme has been proposed, but it shows a linear decrease in performance as the dimensionality is increased. In this paper, we propose a parallel high-dimensional index structure for content-based information retrieval so as to cope with the linear decrease in retrieval performance. In addition, we devise data insertion, range query and k-NN query processing algorithms which are suitable for a clusterbased parallel architecture. Finally, we show that our parallel index structure achieves good retrieval performance in proportion to the number of servers in the cluster-based architecture and it outperforms a parallel version of the VA-File when the dimensionality is over 10.

UR - https://www.scopus.com/pages/publications/51849150855

U2 - 10.1109/CIT.2008.4594657

DO - 10.1109/CIT.2008.4594657

M3 - Conference paper

AN - SCOPUS:51849150855

SN - 9781424423583

T3 - Proceedings - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008

SP - 101

EP - 106

BT - Proceedings - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008

T2 - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008

Y2 - 8 July 2008 through 11 July 2008

ER -

Parallel high-dimensional index structure for content-based information retrieval

Abstract

Publication series

Conference

Quacquarelli Symonds(QS) Subject Topics

Access to Document

Other files and links

Fingerprint

Cite this