File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Towards the application of classification techniques to test and identify faults in multimedia systems

TitleTowards the application of classification techniques to test and identify faults in multimedia systems
Authors
KeywordsBayesian networks
Classification
K-nearest neighbor
Multimedia
Neural networks
Software testing
Issue Date2004
PublisherIEEE, Computer Society.
Citation
Proceedings - Fourth International Conference On Quality Software, Qsic 2004, 2004, p. 32-40 How to Cite?
AbstractThe advances in computer and graphic technologies have led to the popular use of multimedia for information exchange. However, multimedia systems are difficult to test. A major reason is that these systems generally exhibit fuzziness in their temporal behaviors. The fuzziness is caused by the existence of non-deterministic factors in their runtime environments, such as system load and network traffic. It complicates the analysis of test results. The problem is aggravated when a test involves the synchronization of different multimedia streams as well as variations in system loading. In this paper, we conduct an empirical study on the testing and fault-identification of multimedia systems by treating the issue as a classification problem. Typical classification techniques, including Bayesian networks, k-nearest neighbor, and neural networks, are experimented with the use of X-Smiles, an open source multimedia authoring tool supporting the Synchronized Multimedia Integration Language (SMIL). The encouraging result of our study, which is based only on five attributes, shows that our proposal can achieve an accuracy of 57.6 to 79.2% in identifying the types of fault in environments where common cause variations are present. A further improvement of 7.6% is obtained via normalization.
Persistent Identifierhttp://hdl.handle.net/10722/48446
References

 

DC FieldValueLanguage
dc.contributor.authorCheng, MYen_HK
dc.contributor.authorCheung, SCen_HK
dc.contributor.authorTse, THen_HK
dc.date.accessioned2008-05-22T04:13:13Z-
dc.date.available2008-05-22T04:13:13Z-
dc.date.issued2004en_HK
dc.identifier.citationProceedings - Fourth International Conference On Quality Software, Qsic 2004, 2004, p. 32-40en_HK
dc.identifier.urihttp://hdl.handle.net/10722/48446-
dc.description.abstractThe advances in computer and graphic technologies have led to the popular use of multimedia for information exchange. However, multimedia systems are difficult to test. A major reason is that these systems generally exhibit fuzziness in their temporal behaviors. The fuzziness is caused by the existence of non-deterministic factors in their runtime environments, such as system load and network traffic. It complicates the analysis of test results. The problem is aggravated when a test involves the synchronization of different multimedia streams as well as variations in system loading. In this paper, we conduct an empirical study on the testing and fault-identification of multimedia systems by treating the issue as a classification problem. Typical classification techniques, including Bayesian networks, k-nearest neighbor, and neural networks, are experimented with the use of X-Smiles, an open source multimedia authoring tool supporting the Synchronized Multimedia Integration Language (SMIL). The encouraging result of our study, which is based only on five attributes, shows that our proposal can achieve an accuracy of 57.6 to 79.2% in identifying the types of fault in environments where common cause variations are present. A further improvement of 7.6% is obtained via normalization.en_HK
dc.format.extent212492 bytes-
dc.format.extent783 bytes-
dc.format.extent783 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
dc.format.mimetypetext/plain-
dc.languageengen_HK
dc.publisherIEEE, Computer Society.en_HK
dc.relation.ispartofProceedings - Fourth International Conference on Quality Software, QSIC 2004en_HK
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rights©2004 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.en_HK
dc.subjectBayesian networksen_HK
dc.subjectClassificationen_HK
dc.subjectK-nearest neighboren_HK
dc.subjectMultimediaen_HK
dc.subjectNeural networksen_HK
dc.subjectSoftware testingen_HK
dc.titleTowards the application of classification techniques to test and identify faults in multimedia systemsen_HK
dc.typeConference_Paperen_HK
dc.identifier.emailTse, TH: thtse@cs.hku.hken_HK
dc.identifier.authorityTse, TH=rp00546en_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/QSIC.2004.1357942en_HK
dc.identifier.scopuseid_2-s2.0-14044258687en_HK
dc.identifier.hkuros91271-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-14044258687&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.spage32en_HK
dc.identifier.epage40en_HK
dc.identifier.scopusauthoridCheng, MY=7402260451en_HK
dc.identifier.scopusauthoridCheung, SC=7202472792en_HK
dc.identifier.scopusauthoridTse, TH=7005496974en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats