Table 3 Analysis of performance metrics with and without feature selection.

From: A secure and efficient deep learning-based intrusion detection framework for the internet of vehicles

Metrics

With Feature Selection

Without Feature Selection

Accuracy

0.99125

0.980981

Precision

0.985433

0.973654

Recall

0.98452

0.97218

Sensitivity

0.985453

0.971489

Specificity

0.990158

0.97325

F-measure

0.98455

0.979421

NPV

0.990835

0.981482

FPR

0.001148

0.020045

FNR

0.00368

0.092452

MCC

0.984523

0.972166

Back to article page