Method for real-time auto-detection of outliers

作者: Han C. Wen , Tomas J. Pavel

DOI:

关键词:

摘要: A moving window of data is used to determine a local baseline as average the weighted by number measurements in each time interval. next measurement associated with interval compared value an outlier. In some cases, for example where series shows small variability around mean, multiple other significant sum and root mean square deviation damping factor.

参考文章(22)
Raymond T. Ng, Edwin M. Knorr, Algorithms for Mining Distance-Based Outliers in Large Datasets very large data bases. pp. 392- 403 ,(1998)
M. Allman, M. Mathis, A Framework for Defining Empirical Bulk Transfer Capacity Metrics A Framework for Defining Empirical Bulk Transfer Capacity Metrics. ,vol. 3148, pp. 1- 16 ,(2001)
S. Kalidindi, M. Zekauskas, G. Almes, A Round-trip Delay Metric for IPPM IETF RFC2681. ,vol. 2681, pp. 1- 20 ,(1999)
S. Kalidindi, M. Zekauskas, G. Almes, A One-way Delay Metric for IPPM IETF RFC2679. ,vol. 2679, pp. 1- 20 ,(1999)
Levent Ertoz, Aleksandar Lazarevic, Paul Dokas, Pang-Ning Tan, Vipin Kumar, Jaideep Srivastava, Data Mining for Network Intrusion Detection ,(2002)
S. Kalidindi, M. Zekauskas, G. Almes, A One-way Packet Loss Metric for IPPM RFC2680. ,vol. 2680, pp. 1- 15 ,(1999)
V. Paxson, J. Mahdavi, IPPM Metrics for Measuring Connectivity RFC. ,vol. 2498, pp. 1- 10 ,(1999)
Igor V. Cadez, P. S. Bradley, Model Based Population Tracking and Automatic Detection of Distribution Changes neural information processing systems. ,vol. 14, pp. 1345- 1352 ,(2001)