Efficient NP Tests for Anomaly Detection Over Birth-Death Type DTMCs
Name
11265_2016_1147_ReferencePDF.pdf
Size
392.01 KB
Format
Adobe PDF
Checksum (MD5)
9b224e67bc2950c5ae4426774bd7c4ef
Author(s)
Ozkan, Huseyin
Ozkan, Fatih
Delibalta, Ibrahim
Kozat, Suleyman S.
Date Issued
June 2016
Journal
Journal of Signal Processing Systems
Publisher
Springer US
Citation
Ozkan, Huseyin, et al. “Efficient NP Tests for Anomaly Detection Over Birth-Death Type DTMCs.” Journal of Signal Processing Systems, vol. 90, no. 2, Feb. 2018, pp. 175–84.
Version
Author's final manuscript
Abstract
We propose computationally highly efficient Neyman-Pearson (NP) tests for anomaly detection over birth-death type discrete time Markov chains. Instead of relying on extensive Monte Carlo simulations (as in the case of the baseline NP), we directly approximate the log-likelihood density to match the desired false alarm rate; and therefore obtain our efficient implementations. The proposed algorithms are appropriate for processing large scale data in online applications with real time false alarm rate controllability. Since we do not require parameter tuning, our algorithms are also adaptive to non-stationarity in the data source. In our experiments, the proposed tests demonstrate superior detection power compared to the baseline NP while nearly achieving the desired rates with negligible computational resources. Keywords: Anomaly detection, Neyman pearson, NP, False alarm, Efficient Online, Markov DTMC
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s11265-016-1147-0
