Near-Field Sensing: A Low-Complexity Wavenumber-Domain Method

TL;DR

This paper introduces a low-complexity, gridless near-field sensing method using a wavenumber-domain approach combined with a BiCNN, enabling fast and accurate target localization with limited bandwidth and a single antenna array.

Contribution

It proposes a novel BiCNN-based approach for near-field sensing that significantly reduces computational complexity and training parameters while maintaining high localization accuracy.

Findings

BiCNN learns to localize with fewer parameters.

Method achieves 100x faster online localization.

Performance comparable to MUSIC algorithms.

Abstract

A novel low-complexity wavenumber-domain method is proposed for near-field sensing (NISE). Specifically, the power-concentrated region of the wavenumber-domain channels is related to the target position in a non-linear manner. Based on this observation, a bi-directional convolutional neural network (BiCNN)-based approach is proposed to capture such a relationship, thereby facilitating low-complexity target localization. This method enables direct and gridless target localization using only a limited bandwidth and a single antenna array. Simulation results demonstrate that: 1) during the offline training phase, the proposed BiCNN method can learn to localize the target with fewer trainable parameters compared to the naive neural network architectures; and 2) during the online implementation phase, the BiCNN method can spend 100x less time while maintaining comparable performance to the conventional two-dimensional multiple signal classification (MUSIC) algorithms.