An efficient method for anomaly detection in non-stationary data streams

Milad Chenaghlou, Masud Moshtaghi, Christopher Leckie, Mahsa Salehi

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

    6 Citations (Scopus)


    Anomaly detection in data streams has become a major research problem in the era of ubiquitous sensing. We are collecting large amounts of data from non-stationary environments, which makes traditional anomaly detection techniques ineffective. In this paper we propose an unsupervised cluster-based algorithm for modelling normal behaviour in nonstationary data streams and detecting anomalous data points. We show that our method scales linearly with the number of observed data points, while the complexity of our model is independent of the size of the data stream. We have employed a selective clustering approach to optimize the computation time needed to model the normal data. Our experiments on largescale synthetic and real life datasets show that the accuracy of the proposed algorithm is comparable to the state-of-the-art techniques reported in the literature while providing substantial improvements in terms of computation time.

    Original languageEnglish
    Title of host publication2017 IEEE Global Communications Conference (GLOBECOM) - Proceedings
    EditorsYing-Chang Liang, Teng Joon Lim, Chengshan Xiao
    Place of PublicationPiscataway NJ USA
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Number of pages6
    ISBN (Electronic)9781509050192, 9781509050185
    ISBN (Print)9781509050208
    Publication statusPublished - 2017
    EventIEEE Global Telecommunications Conference 2017 - Singapore, Singapore
    Duration: 4 Dec 20178 Dec 2017 (Proceedings)


    ConferenceIEEE Global Telecommunications Conference 2017
    Abbreviated titleIEEE GLOBECOM 2017
    Internet address

    Cite this