Intelligent anti-jamming communication technology with electromagnetic spectrum feature cognition

Area of Science:

• Electrical Engineering
• Computer Science
• Signal Processing

Background:

• Complex signal interference in wireless communication degrades transmission quality and reliability.
• Traditional anti-interference methods struggle with dynamic electromagnetic environments and computational demands.
• Rapid advancements in wireless technology necessitate adaptive interference management solutions.

Purpose of the Study:

• To develop an intelligent anti-interference algorithm for enhanced wireless communication reliability.
• To address the limitations of existing static and computationally intensive interference suppression techniques.
• To improve adaptability and reduce error rates in dynamic electromagnetic spectrum environments.

Main Methods:

• Combines deep neural networks (DNNs) for feature extraction and game theory for strategy optimization.
• Employs a near-end strategy optimization model for dynamic communication adjustments.
• Utilizes DNNs to recognize signal features, generate matching interference, and achieve suppression.

Main Results:

• The proposed algorithm achieved 95.23% accuracy in identifying interference signals.
• Demonstrated an 85.47% anti-interference accuracy rate, outperforming existing models.
• Significantly improved performance compared to random forest and deep Q-network models.

Conclusions:

• The intelligent algorithm effectively suppresses complex signal interference in dynamic environments.
• Offers a novel and adaptive solution for anti-interference communication technology development.
• Highlights the potential of combining DNNs and game theory for future wireless systems.