Intelligent anti-jamming communication technology with electromagnetic spectrum feature cognition DOI Creative Commons

Hui Zhao,

Gang Zhao, Xichun Wang

et al.

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(4), P. e0319953 - e0319953

Published: April 24, 2025

Against the backdrop of rapid development wireless communication technology, complex signal interference issues in electromagnetic spectrum environment have become a key factor affecting quality and reliability transmission. Existing solutions, such as traditional suppression techniques that rely on static allocation fixed patterns, are no longer able to adapt rapidly changing face computational complexity challenges when processing large amounts real-time data. This study proposes an intelligent anti-interference algorithm combines deep neural networks game theory, constructs model based near-end strategy optimization. By extracting features through networks, dynamically adjusting strategies with optimization, effectively addresses recognition prediction transmission feature parameters target systems, generates signals same parameters, achieves effective suppression. Experiments show proposed accuracy rate 95.23% identifying 85.47%, significantly outperforming random forest Q-network models. The not only clarifies limitations existing solutions but also precisely defines goals new model, which reduce error rates improve adaptability dynamic environments. results further explain significance used metrics test conditions, providing means for especially dealing interference.

Language: Английский

Intelligent anti-jamming communication technology with electromagnetic spectrum feature cognition DOI Creative Commons

Hui Zhao,

Gang Zhao, Xichun Wang

et al.

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(4), P. e0319953 - e0319953

Published: April 24, 2025

Against the backdrop of rapid development wireless communication technology, complex signal interference issues in electromagnetic spectrum environment have become a key factor affecting quality and reliability transmission. Existing solutions, such as traditional suppression techniques that rely on static allocation fixed patterns, are no longer able to adapt rapidly changing face computational complexity challenges when processing large amounts real-time data. This study proposes an intelligent anti-interference algorithm combines deep neural networks game theory, constructs model based near-end strategy optimization. By extracting features through networks, dynamically adjusting strategies with optimization, effectively addresses recognition prediction transmission feature parameters target systems, generates signals same parameters, achieves effective suppression. Experiments show proposed accuracy rate 95.23% identifying 85.47%, significantly outperforming random forest Q-network models. The not only clarifies limitations existing solutions but also precisely defines goals new model, which reduce error rates improve adaptability dynamic environments. results further explain significance used metrics test conditions, providing means for especially dealing interference.

Language: Английский

Citations

0