arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.16876eess.SP
收藏

近场移动跟踪:一种使用 XL-RIS 信息的框架

Near-Field Mobile Tracking: A Framework of Using XL-RIS Information

Tuo Wu, Cunhua Pan, Kangda Zhi, Junteng Yao, Hong Ren, Maged Elkashlan, Chau Yuen

AI总结:

提出利用 XL-RIS 高维信息的近场移动跟踪框架,通过 XL-RIS-IR 重建信号并融合多域特征,结合 Bi-LSTM 自动编码器显著提升定位精度与 SNR 鲁棒性。

摘要:

本文介绍了一种新颖的移动跟踪框架,该框架利用从超大规模(XL)可重构智能表面(RIS)接收的高维信号。这种接收信号被命名为 XL-RIS 信息,与传统基站(BS)接收信号(即 BS 信息)相比,具有大得多的数据维度,因此提供了更丰富的特征集,从而能够更准确地跟踪移动用户(MU)。作为第一步,我们提出了一种 XL-RIS 信息重建(XL-RIS-IR)算法,用于从低维 BS 信息重建高维 XL-RIS 信息。在此基础上,本文提出了一个完整的移动跟踪框架,由特征提取模块和移动跟踪模块组成。特征提取模块包含用于空间特征的卷积神经网络(CNN)提取器、用于域特征的时间与频率(T&F)提取器,以及用于捕获 XL-RIS 内到达角(AoA)特征的近场 AoA 提取器。这些特征被组合成一个综合特征向量,形成一个时变序列,并输入移动跟踪模块;该模块采用自动编码器(AE),其具有堆叠的双向长短期记忆(Bi-LSTM)编码器和标准 LSTM 解码器,用于预测 MU 在未来时隙的位置。仿真结果证实,通过使用重建的 XL-RIS 信息,我们所提出框架的跟踪精度得到显著提升,并且对信噪比(SNR)变化表现出很强的鲁棒性。

英文摘要:

This paper introduces a novel mobile tracking framework leveraging the high-dimensional signal received from extremely large-scale (XL) reconfigurable intelligent surfaces (RIS). This received signal, named XL-RIS information, has a much larger data dimension and therefore offers a richer feature set compared to the traditional base station (BS) received signal, i.e., BS information, enabling more accurate tracking of mobile users (MUs). As the first step, we present an XL-RIS information reconstruction (XL-RIS-IR) algorithm to reconstruct the high-dimensional XL-RIS information from the low-dimensional BS information. Building on this, this paper proposes a comprehensive framework for mobile tracking, consisting of a Feature Extraction Module and a Mobile Tracking Module. The Feature Extraction Module incorporates a convolutional neural network (CNN) extractor for spatial features, a time and frequency (T$\&$F) extractor for domain features, and a near-field angles of arrival (AoAs) extractor for capturing AoA features within the XL-RIS. These features are combined into a comprehensive feature vector, forming a time-varying sequence fed into the Mobile Tracking Module, which employs an Auto-encoder (AE) with a stacked bidirectional long short-term memory (Bi-LSTM) encoder and a standard LSTM decoder to predict MUs' positions in the upcoming time slot. Simulation results confirm that the tracking accuracy of our proposed framework is significantly enhanced by using reconstructed XL-RIS information and exhibits substantial robustness to signal-to-noise ratio (SNR) variations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑