Learning Spectral Structures: Efficient Segmentation via Hierarchical Kernel Attention

doi:10.1109/lwc.2026.3706092

Learning Spectral Structures: Efficient Segmentation via Hierarchical Kernel Attention

2026-01-01

0

PRE

AI

Daniel Benevides da Costa

DOI：10.1109/lwc.2026.3706092

Original

Original request for help

Save

Abstract

En 中文

The increasing demand for efficient spectrum utilization in next-generation wireless networks necessitates advanced sensing methods to accurately characterize complex spectral environments. To address this need, this paper introduces HKANet, a novel encoder-decoder architecture designed for spectrogram segmentation. Its core innovation is centered on a dual-component design: a morphology-aware feature extractor that discerns diverse signal shapes, and a statistical attention block that utilizes higher-order statistics for robust feature recalibration. Extensive simulations on a diverse synthetic dataset comprising fifth-generation new radio, long-term evolution, and radar signals with varying bandwidths and modulation types demonstrate that HKANet achieves state-of-the-art performance, outperforming prominent models with a mean pixel accuracy of 98.49%, a mean intersection-over-union of 97.10%, and a mean F1-score of 98.45%. With a lightweight design of only 4.76M parameters and a competitive inference latency of 22.1 ms, HKANet presents an effective solution for intelligent spectrum sensing in future wireless communication systems.

Keywords:

Modeling

Noise

Kernel

Radar

Spectrogram

Timing

5G mobile communication

Frequency

Long Term Evolution

Architecture

5G NR

attention mechanism

deep learning

parameter efficiency spectrogram segmentation

spectrum sensing

Learning Spectral Structures: Efficient Segmentation via Hierarchical Kernel Attention

Abstract

Journal

Organization

Cited Papers