Anomaly Detection in Data streams using MOA
Main Article Content
Abstract
Anomaly means anything which deviates from normal. It can be a credit card fraud or sensor alarm or a signal from a condition monitoring device. A problem like anomaly arises when we try to monitor the unusual behaviour of a machine. More number of outliers means the machine needs to be inspected. Anomaly detection in static data can be entirely different from that of streaming data.
We have some issues in anomaly detection in streaming data when compared to static data. If any off – line algorithms attempt to find anomalies in streams, it has to store the entire stream for analysis. So, there is a high probability that it will run out of memory space.
Also, streams can be infinite and evolving over a period of time because of which maintenance of high detection accuracy becomes almost impossible. In this paper we will discuss about anomaly detection in data streams and using MOA (Massive Online Analysis) tool we will analyse which algorithm derives best results.
Downloads
Metrics
Article Details
Licensing
TURCOMAT publishes articles under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This licensing allows for any use of the work, provided the original author(s) and source are credited, thereby facilitating the free exchange and use of research for the advancement of knowledge.
Detailed Licensing Terms
Attribution (BY): Users must give appropriate credit, provide a link to the license, and indicate if changes were made. Users may do so in any reasonable manner, but not in any way that suggests the licensor endorses them or their use.
No Additional Restrictions: Users may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
