OQIMLI MA‘LUMOTLARNI QAYTA ISHLASHDA ANOMALIYALARNI ANIQLASH UCHUN ADAPTIVE THRESHOLD MEXANIZMINI ISHLATISH
;
adaptive threshold, sliding window, real-time anomaly detection.Abstrak
Zamonaviy dunyoda moliya, IoT va kiberxavfsizlik sohalarida real vaqt rejimida hosil bo‘layotgan ma’lumot oqimlarining hajmi keskin ortib bormoqda. Bu esa oqimdagi anomal (noan’anaviy) hodisalarni tezkor aniqlash zaruratini kuchaytirmoqda. Mazkur tadqiqotda real-time anomaly detection tizimlari uchun adaptiv threshold mexanizmi taklif etiladi. Tizim oqimdagi ma’lumotlarning statistik xususiyatlarini doimiy ravishda tahlil qilib, o‘z chegaraviy qiymatlarini avtomatik tarzda yangilab boradi. Model sliding window, Z-score, va EWMA (Exponentially Weighted Moving Average) yondashuvlariga asoslangan.
Iqtiboslar
Ahmed, M., Mahmood, A. N., & Hu, J. (2016). A Survey of Network Anomaly Detection Techniques. Journal of Network and Computer Applications, 60, 19–31.
Akidau, T., et al. (2018). Streaming Systems: The What, Where, When, and How of Large-Scale Data Processing. O’Reilly Media.
Buda, T., & Spirkovska, L. (2022). Adaptive Thresholding in Real-Time Data Streams. IEEE BigData Conference Proceedings.
