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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Machine Learning-based supervised approaches require highly customized andfine-tuned methodologies to deliver outstanding performance. This paperpresents a dataset-driven design and performance evaluation of a machinelearning classifier for the network intrusion dataset UNSW-NB15. Analysis ofthe dataset suggests that it suffers from class representation imbalance andclass overlap in the feature space. We employed ensemble methods using BalancedBagging (BB), eXtreme Gradient Boosting (XGBoost), and Random Forest empoweredby Hellinger Distance Decision Tree (RF-HDDT). BB and XGBoost are tuned tohandle the imbalanced data, and Random Forest (RF) classifier is supplementedby the Hellinger metric to address the imbalance issue. Two new algorithms areproposed to address the class overlap issue in the dataset. These twoalgorithms are leveraged to help improve the performance of the testing datasetby modifying the final classification decision made by three base classifiersas part of the ensemble classifier which employs a majority vote combiner. Theproposed design is evaluated for both binary and multi-category classification.Comparing the proposed model to those reported on the same dataset in theliterature demonstrate that the proposed model outperforms others by asignificant margin for both binary and multi-category classification cases.

Ensemble Classifier Design Tuned to Dataset Characteristics for Network Intrusion Detection