HKBU at mediaeval 2017 medico: Medical multimedia task

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

2 Citations (Scopus)
26 Downloads (Pure)

Abstract

In this paper, we describe our model designed for automatic detection of diseases based on multimedia data collected in hospitals. Specifically, a two-stage learning strategy is designed to predict the diseases. In the first stage, a dimensionality reduction method called bidirectional marginal Fisher analysis (BMFA) is proposed to project the original data to the low-dimensional space, with the key discriminant information being well preserved. In the second stage, the multi-class support vector machine (SVM) is utilized on the low-dimensional space for detection. Experimental results demonstrate the efficiency of designed model.

Original languageEnglish
Title of host publicationWorking Notes Proceedings of the MediaEval 2017 Workshop, co-located with the Conference and Labs of the Evaluation Forum (CLEF 2017)
EditorsGuillaume Gravier, Benjamin Bischke, Claire-Hélène Demarty, Maia Zaharieva, Michael Riegler , Emmanuel Dellandrea, Dmitry Bogdanov, Richard Sutcliffe, Gareth J. F. Jones, Martha Larson
PublisherCEUR-WS
Number of pages3
Publication statusPublished - Sept 2017
Event2017 Multimedia Benchmark Workshop, MediaEval 2017 - Dublin, Ireland
Duration: 13 Sept 201715 Sept 2017
https://ceur-ws.org/Vol-1984/

Publication series

NameCEUR Workshop Proceedings
PublisherCEUR-WS
Volume1984
ISSN (Print)1613-0073

Conference

Conference2017 Multimedia Benchmark Workshop, MediaEval 2017
Country/TerritoryIreland
CityDublin
Period13/09/1715/09/17
Internet address

Scopus Subject Areas

  • Computer Science(all)

Fingerprint

Dive into the research topics of 'HKBU at mediaeval 2017 medico: Medical multimedia task'. Together they form a unique fingerprint.

Cite this