One Pass Concept Change Detection for Data Streams

Simple item page
aut.conference.typePaper Published in Proceedings
aut.researcherPears, Russel Lawrence
dc.contributor.authorSakthithasan, S
dc.contributor.authorPears, RL
dc.contributor.authorKoh, YS
dc.date.accessioned2013-04-25T21:59:43Z
dc.date.accessioned2013-04-25T21:59:58Z
dc.date.available2013-04-25T21:59:43Z
dc.date.available2013-04-25T21:59:58Z
dc.date.copyright2013-04
dc.date.issued2013-04
dc.description.abstractIn this research we present a novel approach to the concept change detection problem. Change detection is a fundamental issue with data stream mining as models generated need to be updated when significant changes in the underlying data distribution occur. A number of change detection approaches have been proposed but they all suffer from limitations such as high computational complexity, poor sensitivity to gradual change, or the opposite problem of high false positive rate. Our approach, termed OnePassSampler, has low computational complexity as it avoids multiple scans on its memory buffer by sequentially processing data. Extensive experimentation on a wide variety of datasets reveals that OnePassSampler has a smaller false detection rate and smaller computational overheads while maintaining a competitive true detection rate to ADWIN2.
dc.identifier.citationAdvances in Knowledge Discovery and Data Mining. Lecture Notes in Computer Science Volume 7819, 2013, pp 461-472.
dc.identifier.doi10.1007/978-3-642-37456-2_39
dc.identifier.urihttps://hdl.handle.net/10292/5298
dc.publisherSpringer Verlag
dc.relation.replaceshttp://hdl.handle.net/10292/5297
dc.relation.replaces10292/5297
dc.rightsThe author may only post his/her version provided acknowledgement is given to the original source of publication and a link is inserted to the published article on Springer's website. The link must be accompanied by the following text: "The final publication is available at www.springerlink.com”. (Please also see Publisher’s Version and Citation)
dc.rights.accessrightsOpenAccess
dc.subjectData stream mining
dc.subjectConcept drift detection
dc.subjectBernstein bound
dc.titleOne Pass Concept Change Detection for Data Streams
dc.typeConference Contribution
pubs.elements-id137075
pubs.organisational-data/AUT
pubs.organisational-data/AUT/Design & Creative Technologies
pubs.organisational-data/AUT/Design & Creative Technologies/School of Computing & Mathematical Science
Files
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
licence.htm
Size:
29.97 KB
Format:
Unknown data format
Description:
Download
Collections
School of Engineering, Computer and Mathematical Sciences - Te Kura Mātai Pūhanga, Rorohiko, Pāngarau