Empirical Evaluation of Noise Influence on Supervised Machine Learning Algorithms Using Intrusion Detection Datasets

<table class="algorithm-group"><tr><td><table class="algorithm" id="alg2"><tr><td>(1)</td><td>Load the training portion of the intrusion dataset</td></tr><tr><td>(2)</td><td>Convert the label values from numeric to nominal (only for the UNSW-NB15)</td></tr><tr><td>(3)</td><td>Conduct noise filtering by removing the outliers and the extreme values</td></tr><tr><td>(4)</td><td>Train the ML algorithm on the training dataset</td></tr><tr><td>(5)</td><td>Run the ML algorithm on the testing dataset</td></tr><tr><td>(6)</td><td>Document the results</td></tr><tr><td>(7)</td><td>Revert to step 4 using the other ML algorithms</td></tr></table></td></tr></table>

<div>The second set of experiments (noise filtering).</div>

Security and Communication Networks

alg2

Pseudocode 2

Pseudocode 2: Empirical Evaluation of Noise Influence on Supervised Machine Learning Algorithms Using Intrusion Detection Datasets 