Standard

Similarity Multidimensional Indexing. / Mikhaylova, E.; Novikov, B.; Volokhov, A.

CEUR Workshop Proceedings. Proc. of the XIII-th All-Russian Research Conference RCDL'2011, Voronezh, Russia, October 2011. 2011.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research

Harvard

Mikhaylova, E, Novikov, B & Volokhov, A 2011, Similarity Multidimensional Indexing. in CEUR Workshop Proceedings. Proc. of the XIII-th All-Russian Research Conference RCDL'2011, Voronezh, Russia, October 2011. <http://ceur-ws.org/Vol-803/paper11.pdf>

APA

Mikhaylova, E., Novikov, B., & Volokhov, A. (2011). Similarity Multidimensional Indexing. In CEUR Workshop Proceedings. Proc. of the XIII-th All-Russian Research Conference RCDL'2011, Voronezh, Russia, October 2011 http://ceur-ws.org/Vol-803/paper11.pdf

Vancouver

Mikhaylova E, Novikov B, Volokhov A. Similarity Multidimensional Indexing. In CEUR Workshop Proceedings. Proc. of the XIII-th All-Russian Research Conference RCDL'2011, Voronezh, Russia, October 2011. 2011

Author

Mikhaylova, E. ; Novikov, B. ; Volokhov, A. / Similarity Multidimensional Indexing. CEUR Workshop Proceedings. Proc. of the XIII-th All-Russian Research Conference RCDL'2011, Voronezh, Russia, October 2011. 2011.

BibTeX

@inproceedings{d3d226295ccf42878b858d2821f9c3d8,
title = "Similarity Multidimensional Indexing",
abstract = "The multidimensional k-NN (k nearest neighbors) query problem arises in a large variety of database applications, including information retrieval, natural language processing, and data mining. To solve it efficiently, database needs an indexing structure supporting this kind of search. However, exact solution is hardly feasible in multidimensional space. In this paper we describe and analyze an indexing technique for approximate solution of k-NN problem. Construction of the indexing tree is based on clustering. Construction of hash indexing is based on s-stable distributions. Indices are implemented on top of high-performance industrial DBMS.",
keywords = "k-NN search, multidimensional indexing, LSH",
author = "E. Mikhaylova and B. Novikov and A. Volokhov",
year = "2011",
language = "English",
booktitle = "CEUR Workshop Proceedings. Proc. of the XIII-th All-Russian Research Conference RCDL'2011, Voronezh, Russia, October 2011",

}

RIS

TY - GEN

T1 - Similarity Multidimensional Indexing

AU - Mikhaylova, E.

AU - Novikov, B.

AU - Volokhov, A.

PY - 2011

Y1 - 2011

N2 - The multidimensional k-NN (k nearest neighbors) query problem arises in a large variety of database applications, including information retrieval, natural language processing, and data mining. To solve it efficiently, database needs an indexing structure supporting this kind of search. However, exact solution is hardly feasible in multidimensional space. In this paper we describe and analyze an indexing technique for approximate solution of k-NN problem. Construction of the indexing tree is based on clustering. Construction of hash indexing is based on s-stable distributions. Indices are implemented on top of high-performance industrial DBMS.

AB - The multidimensional k-NN (k nearest neighbors) query problem arises in a large variety of database applications, including information retrieval, natural language processing, and data mining. To solve it efficiently, database needs an indexing structure supporting this kind of search. However, exact solution is hardly feasible in multidimensional space. In this paper we describe and analyze an indexing technique for approximate solution of k-NN problem. Construction of the indexing tree is based on clustering. Construction of hash indexing is based on s-stable distributions. Indices are implemented on top of high-performance industrial DBMS.

KW - k-NN search

KW - multidimensional indexing

KW - LSH

M3 - Conference contribution

BT - CEUR Workshop Proceedings. Proc. of the XIII-th All-Russian Research Conference RCDL'2011, Voronezh, Russia, October 2011

ER -

ID: 4443625