Deep Learning for Joint Narrowband Interference Cancellation and Soft Demodulation in OFDM Systems
arXiv:2607.08717v1 Announce Type: new Abstract: Narrowband interference (NBI) severely degrades orthogonal frequency-division multiplexing (OFDM) systems by corrupting subcarriers and rendering classical soft demodulation ineffective. Conventional compressed-sensing (CS) mitigation exhibits high sequential latency and leaves structured, non-Gaussian residuals that cause log-likelihood ratio (LLR) unreliability, decoder saturation, and severe error floors when employing classical Gaussian demappers. We resolve this pipeline mismatch using a unified deep learning framework for joint NBI cancella
The increasing complexity and demands on wireless communication systems, coupled with advances in deep learning, are driving the need for more robust interference mitigation techniques.
This research addresses fundamental limitations in wireless communication reliability, which is critical for future high-bandwidth, low-latency applications across various sectors.
A unified deep learning framework promises to significantly improve the performance and efficiency of OFDM systems by jointly handling interference cancellation and soft demodulation, which were previously separate, inefficient processes.
- · Telecommunication companies
- · AI/ML research institutions
- · 5G and future wireless technology developers
- · IoT device manufacturers
- · Providers of conventional signal processing hardware
- · Legacy OFDM system developers
Improved reliability and spectral efficiency in wireless communication networks, potentially reducing error rates and increasing data throughput.
Accelerated development and adoption of advanced wireless technologies like 6G, tactile internet, and pervasive IoT, enabled by more robust underlying physical layers.
Enhanced overall digital infrastructure underpinning AI applications and autonomous systems, where reliable, low-latency communication is paramount.
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