Improving energy detection in cognitive radio systems using machine learning

Keyphrases

• Detection Accuracy 100%
• Machine Learning 100%
• Energy Detection 100%
• Cognitive Radio System 100%
• Low Computational Complexity 50%
• Machine Learning Techniques 50%
• Machine Learning Models 50%
• Overall Accuracy 50%
• Communication Overhead 50%
• Secondary User 50%
• Management Techniques 50%
• Underutilization 50%
• Low Signal-to-noise Ratio 50%
• Channel Condition 50%
• Electromagnetic Spectrum 50%
• Complex Tree 50%
• Tree Algorithm 50%
• Energy Detector 50%
• Cognitive Radio 50%
• Spectrum Sensing Algorithm 50%
• Energy Characteristics 50%
• Weighted KNN 50%
• Multipath Fading 50%
• Dynamic Spectrum Management 50%

Engineering

• Primary User 100%
• Energy Detection 100%
• Cognitive Radio System 100%
• Energy Engineering 33%
• Computational Cost 33%
• Signal-to-Noise Ratio 33%
• Sensing Mechanisms 33%
• Secondary User 33%
• Machine Learning Technique 33%
• Channel Condition 33%
• Energy Detector 33%
• Cognitive Radio 33%
• Dynamic Spectrum Management 33%