A Hybrid Deep Learning-Based Model for Anomaly Detection in Cloud Datacenter Networks
- Submitting institution
-
University of Newcastle upon Tyne
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 273226-197872-1292
- Type
- D - Journal article
- DOI
-
10.1109/TNSM.2019.2927886
- Title of journal
- IEEE Transactions on Network and Service Management
- Article number
- -
- First page
- 924
- Volume
- 16
- Issue
- 3
- ISSN
- 1932-4537
- Open access status
- Not compliant
- Month of publication
- July
- Year of publication
- 2019
- URL
-
https://doi.org/10.1109/TNSM.2019.2927886
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
5
- Research group(s)
-
F - Networked and Ubiquitous Systems Engineering (NUSE)
- Citation count
- 51
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper, resulting from an international collaboration, introduced a novel anomaly detection technique for enhancing the reliability of typically bug-prone Cloud Datacentre networks. Unlike its antecedents, the technique fused grey wolf optimisation (GWO) and convolutional neural network (CNN). This is more computationally efficient and suffers from fewer false positives than alternatives. It improved the exploration, exploitation and initial population generation capabilities of GWO while revamping the drop-out functionality in CNN. Published in the flagship IEEE Trans. journal, the influence of this research is evidenced by a large number of Google (77), Scopus (59), and Web-of-Science (44) citations since 2019.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -