Inproceedings,

Anomaly Detection in Distributed Streams

, , , , , and .
Information and Communication Technology for Intelligent Systems: Proceedings of ICTIS 2020, Volume 2, volume 196 of Smart Innovation, Systems and Technologies book series (SIST), page 139--147. Singapore, Springer Singapore, Springer, (2021)
DOI: https://doi.org/10.1007/978-981-15-7062-9_14

Abstract

Anomalies refer to any non-conforming patterns to the expected behavior in the system. The detection of anomaly in real time from logs arriving at very high velocity and are in huge volume requires a distributed framework with high throughput and low latency. In this research, statistical method has been implemented for finding the suspicious associations in Spark Streaming, a highly scalable distributed and streaming framework. The models were deployed in both local mode as well as in cluster mode to perform anomaly detection on server logs.

Tags

Users

  • @amanshakya

Comments and Reviews