The HeightBL Algorithm for Bulk-loading F-Onion-trees

Uloženo v:
Podrobná bibliografie
Název: The HeightBL Algorithm for Bulk-loading F-Onion-trees
Autoři: Carosia, Arthur Emanuel de Oliveira, Ciferri, Ricardo Rodrigues, Ciferri, Cristina Dutra de Aguiar
Přispěvatelé: FAPESP, CNPq, CAPES and FINEP
Zdroj: Journal of Information and Data Management; v. 5, n. 3 (2014): SBBD 2014; 321
Journal of Information and Data Management; Vol 5 No 3 (2014): SBBD 2014; 321
Journal of Information and Data Management; v. 5 n. 3 (2014): SBBD 2014; 321
Informace o vydavateli: SBC - Brazilian Computer Society, 2014.
Rok vydání: 2014
Témata: metric access method, similarity search, bulk-loading, Onion-tree, F-Onion-tree
Popis: The F-Onion-tree is a robust access method that slices the metric space into disjoint subspaces to provide quick indexing of complex data in the main memory. However, the F-Onion-tree only performs element-by-element insertions into its structure, i.e. it does not introduce a technique to build the index considering all elements of the dataset at once. In this article, we fill this gap. We propose the HeightBL algorithm for bulk-loading F-Onion-trees. Performance tests with real-world data with different volumes and dimensionalities showed that the index produced by the HeightBL algorithm is very compact. Compared with the element-by-element insertion, the size of the index reduced from 53.42% to 71.25%. The experiments also showed that the HeightBL algorithm significantly improved range and k-NN query processing performance. It required from 13.38% up to 99.94% less distance calculations and was from 8.57% up to 99.04% faster than the element-by-element insertion.
Druh dokumentu: Article
Popis souboru: application/pdf; application/zip
Jazyk: English
ISSN: 2178-7107
Přístupová URL adresa: https://seer.ufmg.br/index.php/jidm/article/view/729
https://seer.ufmg.br/index.php/jidm/article/view/288
Přístupové číslo: edsair.dedup.wf.002..6d68f19a689a1da03a2bc6e8606b6a86
Databáze: OpenAIRE
Buďte první, kdo okomentuje tento záznam!
Nejprve se musíte přihlásit.