Lightweight Statistical Methods for Real-Time Anomaly Detection in Streaming Data
International Journal of Advanced Research in Science Communication and Technology · 19.06.2026 · 23
DOI: 10.48175/ijarsct-37104 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Advanced Research in Science Communication and Technology, online erschienen am 19.06.2026. Verfasst von Sweta Dave. Die Arbeit nennt 15 Literaturangaben.
Abstract (Originalsprache)
In fields including IoT systems, cloud infrastructures, web services, industrial monitoring, and high-frequency financial markets, real-time anomaly detection is becoming more and more important. Because of their computing efficiency, interpretability, and applicability for scenarios with low latency or resources, lightweight statistical and rule-based techniques are still widely used. Moving averages, exponential smoothing, STL decomposition, seasonal hybrid ESD, and rule-based thresholding are just a few of the lightweight approaches that we carefully consider and evaluate in this paper. Their performance is evaluated using common real-world issues such as idea drift, noise, non-stationarity, multivariate dependencies, and variability in streaming environments. The study describes the benefits, drawbacks, and shortcomings of current statistical models as well as future prospects, such as hybrid statistical–machine learning frameworks meant for adaptive and scalable anomaly detection
Zitieren
APA
Dave, S. (2026). Lightweight Statistical Methods for Real-Time Anomaly Detection in Streaming Data. International Journal of Advanced Research in Science Communication and Technology, 23. https://doi.org/10.48175/ijarsct-37104
Vancouver
Dave S. Lightweight Statistical Methods for Real-Time Anomaly Detection in Streaming Data. International Journal of Advanced Research in Science Communication and Technology. 2026:23. doi:10.48175/ijarsct-37104
BibTeX
@article{Dave2026,
author = {Dave, Sweta},
title = {Lightweight Statistical Methods for Real-Time Anomaly Detection in Streaming Data},
journal = {International Journal of Advanced Research in Science Communication and Technology},
year = {2026},
pages = {23},
doi = {10.48175/ijarsct-37104}
}
EUVIMED