Dualformer: Efficient Feature Extractor for Complex-valued Blind Communication Signal Analysis
arXiv:2606.31352v1 Announce Type: new Abstract: Designing effective feature extractors is critical for blind signal analysis tasks such as automatic modulation recognition (AMR), signal scheme recognition (SSR), and \color{black} signal structure parsing (SSP). In this work, we propose dual-channel neural network (DualNN) that efficiently exploits complex-valued signals through parameter sharing across IQ channels. Unlike traditional real-valued or complex-valued models, DualNN is a groundbreaking framework which shares the network parameters for processing the real and imaginary parts of the
The proliferation of complex communication systems necessitates more robust and efficient signal analysis, driving innovation in AI-driven feature extraction.
Improved blind signal analysis can significantly enhance applications ranging from secure communications to autonomous systems, impacting national security and industrial efficiency.
The introduction of architectures like DualNN could lead to more accurate and efficient processing of complex-valued signals, fostering advancements in secure and robust communication technologies.
- · Defense contractors
- · Telecommunications companies
- · AI/ML research labs
- · Cybersecurity firms
- · Legacy signal processing firms relying on traditional methods
- · Adversarial entities relying on covert communications
Further development and integration of DualNN into real-world communication systems for enhanced signal intelligence.
Increased efficiency and accuracy in electronic warfare and spectrum management through advanced signal analysis capabilities.
The potential for new communication protocols that are inherently more resilient to sophisticated jamming and eavesdropping.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG