An Adaptive Real-Time Malicious Node Detection Framework Using Machine Learning in Vehicular Ad-Hoc Networks (VANETs)

Keyphrases

• Machine Learning 100%
• Vehicular Ad Hoc Networks 100%
• Detection Framework 100%
• Malicious Node Detection 100%
• Modern Vehicles 25%
• Security System 25%
• Realistic Scenario 25%
• Continuous Process 25%
• Multiple Vehicles 25%
• Training Time 25%
• Detection System 25%
• Network Performance 25%
• Network Environment 25%
• Machine Learning Classification 25%
• Testing Time 25%
• Accuracy Value 25%
• DDoS Attack 25%
• Malicious Node 25%
• OMNeT++ 25%
• Communication Development 25%
• Amazon Web Services 25%
• Vehicle Communication 25%
• DDoS Detection 25%
• Vehicle Dataset 25%
• Attack Classification 25%
• Edge Security 25%
• SVM Model 25%
• RF Model 25%
• Multi-layer Classifier 25%

Computer Science

• Learning System 100%
• Machine Learning 100%
• Vehicular Ad-Hoc Network 100%
• Support Vector Machine 66%
• Security Systems 33%
• Continuous Process 33%
• Network Performance 33%
• Network Environment 33%
• Classification (Machine Learning) 33%
• Amazon Web Services 33%