Introduced anomaly detection method in Big Data environment

An article entitled “Hybridisation of classifiers for anomaly detection in big data” co-authored by the director of Institute, academician Rasim Alguliyev, Corresponding Member of ANAS Ramiz Aliguliyev and Leading Researcher, Ph.D., Associate Professor Fargana Abdullayeva was published in the “International Journal of Big Data Intelligence”.

To ensure the safety of the cloud infrastructure, it is considered important to determine the infrastructure hardware, the system state and the detection of anomalies of quality indicators that may arise in the operation of the software. The article proposes a classification method based on an ensemble of classifiers to identify anomalies in the quality of cloud infrastructure. The proposed model is based on algorithms that are included in classes of classifiers, such as Bayesian classifiers, neural networks, and decision trees. A comparative analysis of the model using different machine learning methods was carried out in large-scale open cloud databases “Google Cloud Cluster Trace” and “Yahoo!”. The experimental results showed that the proposed approach is effective in detecting anomalies.

The article was prepared on the basis of the grant “Development of methods and algorithms for ensuring information security in the Big Data environment (“ Big Data ”) and their some applications” funded by the Science Development Foundation under the President of the Republic of Azerbaijan.

Note that the journal International Journal of Big Data Intelligence is indexed in the international scientific databases - Asian Digital Library, cnpLINKer (CNPIEC), Computer Database (Gale), DBLP Computer Science Bibliography, Google Scholar.

© All rights reserved. Citing to www.ict.az is necessary upon using news