Evolving fuzzy rules for anomaly detection in data streams

Masud Moshtaghi, James C Bezdek, Christopher Leckie, Shanika Karunasekera, Marimuthu Palaniswami

    Research output: Contribution to journalArticleResearchpeer-review

    20 Citations (Scopus)

    Abstract

    Evolvable Takagi-Sugeno (T-S) models are fuzzy-rule-based models with the ability to continuously learn and adapt to incoming samples from data streams. The model adjusts both premise and consequent parameters to enhance the performance of the model. This paper introduces a new methodology for the estimation of the premise parameters in the evolvable T-S (eTS) model. Incremental updates for the weighted sample mean and inverse of the covariance matrix enable us to construct an evolvable fuzzy rule base that is used to detect outliers and regime changes in the input stream. We compare our model with Angelov s eTS+ model with artificial and real data.
    Original languageEnglish
    Pages (from-to)688 - 700
    Number of pages13
    JournalIEEE Transactions on Fuzzy Systems
    Volume23
    Issue number3
    DOIs
    Publication statusPublished - 2015

    Cite this

    Moshtaghi, M., Bezdek, J. C., Leckie, C., Karunasekera, S., & Palaniswami, M. (2015). Evolving fuzzy rules for anomaly detection in data streams. IEEE Transactions on Fuzzy Systems, 23(3), 688 - 700. https://doi.org/10.1109/TFUZZ.2014.2322385