English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Autonomous or self-driving networks are expected to provide a solution to themyriad of extremely demanding new applications in the Future Internet. The keyto handle complexity is to perform tasks like network optimization and failurerecovery with minimal human supervision. For this purpose, the community relieson the development of new Machine Learning (ML) models and techniques. However,ML can only be as good as the data it is fitted with. Datasets provided to thecommunity as benchmarks for research purposes, which have a relevant impact inresearch findings and directions, are often assumed to be of good quality bydefault. In this paper, we show that relatively minor modifications on the samebenchmark dataset (UGR'16, a flow-based real-traffic dataset for anomalydetection) cause significantly more impact on model performance than thespecific ML technique considered. To understand this finding, we contribute amethodology to investigate the root causes for those differences, and to assessthe quality of the data labelling. Our findings illustrate the need to devotemore attention into (automatic) data quality assessment and optimizationtechniques in the context of autonomous networks.

Quality In / Quality Out: Assessing Data quality in an Anomaly Detection Benchmark