Optimizing Intrusion Detection Systems Using Ensemble Voting Classifiers: A Multi-Dataset Performance Analysis

Key Points

• This research aims to improve the performance of intrusion detection systems by using ensemble voting classifiers across multiple datasets.
• Analyzed various datasets to assess classifier performance.
• Implemented ensemble voting techniques for optimizing detection accuracy.
• Compared results of different classifier models to identify the most effective ones.
• Ensemble voting classifiers showed significantly improved detection rates compared to individual classifiers.
• Performance varied across different datasets, indicating adaptability of the model.
• The best-performing ensemble model achieved over 90% accuracy in detecting intrusions.