An innovative outlier detection method using localized thresholds
Article
Article Title | An innovative outlier detection method using localized thresholds |
---|---|
ERA Journal ID | 17828 |
Article Category | Article |
Authors | Zhang, Ji (Author), Cao, Jie (Author) and Zhu, Xiaodong (Author) |
Editors | Xiang, Y., Pathan, M., Tao, X. and Wang, H. |
Journal Title | Data and Knowledge Engineering |
Number of Pages | 9 |
Year | 2012 |
Place of Publication | Berlin, Germany |
ISSN | 0169-023X |
1872-6933 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-642-34679-8-7 |
Abstract | In this paper, we investigate the research problem of specifying the thresholds to effectively detect outliers and propose an innovative technique that leverages multiple localized thresholds for detecting outliers. Our technique is able to overcome a major limitation of the existing outlier detection approaches that use a single universal threshold to distinguish outliers from normal data. The experiments conducted demonstrate that our technique is able to achieve a better detection effectiveness than the traditional approaches. |
Keywords | distributed database; experimental evaluation; innovative systems |
ANZSRC Field of Research 2020 | 460699. Distributed computing and systems software not elsewhere classified |
469999. Other information and computing sciences not elsewhere classified | |
Public Notes | Series: Lecture Notes in Computer Science v.7696 |
Byline Affiliations | Centre for Systems Biology |
Nanjing University of Information Science and Technology, China | |
Event | 3rd International Conference on Data and Knowledge Engineering (ICDKE 2012) |
Institution of Origin | University of Southern Queensland |
ISBN | 9783642346781 |
Event Details | 3rd International Conference on Data and Knowledge Engineering (ICDKE 2012) Event Date 21 to end of 23 Nov 2012 Event Location Fujian, China |
https://research.usq.edu.au/item/q1v05/an-innovative-outlier-detection-method-using-localized-thresholds
Download files
1783
total views935
total downloads3
views this month1
downloads this month