Show simple item record

dc.contributor.authorArandjelovic, O.
dc.contributor.authorPham, DucSon
dc.contributor.authorVenkatesh, S.
dc.contributor.editorLoo, C.K., Keem Siah, Y., Wong, K.K.W., Beng Jin, A.T. & Huang, K.
dc.identifier.citationArandjelovic, O. and Pham, D. and Venkatesh, S. 2014. Stream Quantiles via Maximal Entropy Histograms, in Loo, C.K., Keem Siah, Y., Wong, K.K.W., Beng Jin, A.T. & Huang, K. (ed), The 21st International Conference on Neural Information Processing (ICONIP 2014), Nov 3 2014, pp. 327-334. Kuching, Malaysia: Springer.

We address the problem of estimating the running quantile of a data stream when the memory for storing observations is limited. We (i) highlight the limitations of approaches previously described in the literature which make them unsuitable for non-stationary streams, (ii) describe a novel principle for the utilization of the available storage space, and (iii) introduce two novel algorithms which exploit the proposed principle. Experiments on three large real-world data sets demonstrate that the proposed methods vastly outperform theexisting alternatives.

dc.subjectvideo surveillance
dc.subjectstream data
dc.subjectquantile estimation
dc.titleStream Quantiles via Maximal Entropy Histograms
dc.typeConference Paper
dcterms.source.titleNeural Information Processing. ICONIP 2014. Lecture Notes in Computer Science, vol 8835.
dcterms.source.seriesNeural Information Processing, 21st International Conference, ICONIP 2014, Kuching, Malaysia, November 3-6, 2014. Proceedings, Part II: Lecture Notes in Computer Science Volume 8835 2014
dcterms.source.conferenceThe 21st International Conference on Neural Information Processing (ICONIP 2014)
dcterms.source.conference-start-dateNov 3 2014
dcterms.source.conferencelocationKuching, Malaysia
curtin.departmentDepartment of Computing
curtin.accessStatusFulltext not available

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record