Exploring the Use of Short-term Memory in Building More Efficient Metric Access Methods
Abstract
Similarity queries are fundamental operations for applications that deal with complex data. This work proposes a new approach to create the metric access method Slim-tree through a short-term memory. The strategy was evaluated in a dynamic context and the preliminary experiments resulted in less distance calculations, disk accesses and execution time to run k-nearest neighbor queries.
Keywords:
Indexing, Slim-tree, Short-term memory
References
Ciaccia, P., Patella, M., and Zezula, P. (1997). M-tree: An efficient access method for similarity search in metric spaces. In VLDB, pages 426–435, Atenas, Grécia.
Gama, J. (2012). A survey on learning from data streams: current and future trends. Progress in Artificial Intelligence, 1(1):45–55.
Guttman, A. (1984). R-trees: A dynamic index structure for spatial searching. In SIGMOD, pages 47–57, Boston, Massachusetts.
Lichman, M. (2013). UCI Machine Learning Repository, University of California, Irvine, http://archive.ics.uci.edu/ml.
Navarro, G. and Reyes, N. (2016). New dynamic metric indices for secondary memory. Information Systems, 59:48–78.
Oliveira, P., Traina, C., and Kaster, D. (2015). Improving the pruning ability of dynamic metric access methods with local additional pivots and anticipation of information. In ADBIS, LNCS 9282, pages 18–31, Poitiers, França. Springer.
Skopal, T. (2006). On fast non-metric similarity search by metric access methods. In EDBT, LNCS 3896, pages 718–736, Munique, Alemanha. Springer.
Souza, J., Razente, H., and Barioni, M. C. (2014). Optimizing metric access methods for querying and mining complex data types. J. Braz. Comput. Soc., 20(1):1.
Traina, C., Traina, A., Faloutsos, C., and Seeger, B. (2002). Fast indexing and visualization of metric data sets using slim-trees. IEEE Trans Knowl Data Eng, 14(2):244–260.
Vieira, M. R., Jr., C. T., Chino, F. J. T., and Traina, A. J. M. (2010). Dbm-tree: A dynamic metric access method sensitive to local density data. JIDM, 1(1):111–128.
Gama, J. (2012). A survey on learning from data streams: current and future trends. Progress in Artificial Intelligence, 1(1):45–55.
Guttman, A. (1984). R-trees: A dynamic index structure for spatial searching. In SIGMOD, pages 47–57, Boston, Massachusetts.
Lichman, M. (2013). UCI Machine Learning Repository, University of California, Irvine, http://archive.ics.uci.edu/ml.
Navarro, G. and Reyes, N. (2016). New dynamic metric indices for secondary memory. Information Systems, 59:48–78.
Oliveira, P., Traina, C., and Kaster, D. (2015). Improving the pruning ability of dynamic metric access methods with local additional pivots and anticipation of information. In ADBIS, LNCS 9282, pages 18–31, Poitiers, França. Springer.
Skopal, T. (2006). On fast non-metric similarity search by metric access methods. In EDBT, LNCS 3896, pages 718–736, Munique, Alemanha. Springer.
Souza, J., Razente, H., and Barioni, M. C. (2014). Optimizing metric access methods for querying and mining complex data types. J. Braz. Comput. Soc., 20(1):1.
Traina, C., Traina, A., Faloutsos, C., and Seeger, B. (2002). Fast indexing and visualization of metric data sets using slim-trees. IEEE Trans Knowl Data Eng, 14(2):244–260.
Vieira, M. R., Jr., C. T., Chino, F. J. T., and Traina, A. J. M. (2010). Dbm-tree: A dynamic metric access method sensitive to local density data. JIDM, 1(1):111–128.
Published
2016-10-04
How to Cite
SOUSA, Régis Michel dos Santos; RAZENTE, Humberto; BARIONI, Maria Camila N..
Exploring the Use of Short-term Memory in Building More Efficient Metric Access Methods. In: BRAZILIAN SYMPOSIUM ON DATABASES (SBBD), 31. , 2016, Salvador/BA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2016
.
p. 163-168.
ISSN 2763-8979.
DOI: https://doi.org/10.5753/sbbd.2016.24322.
