发表机构
University of Thessaly; University of Western Macedonia; InnoCube P.C.; Democritus University of Thrace（色萨利大学; 西马其顿大学; InnoCube有限公司; 色雷斯德谟克利特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出基于卷积脉冲神经网络的无线架构，实现CSI到用户位置的转换与波束成形，在能效与定位精度间取得权衡。
AI 中文摘要
无线定位是高频、高方向性无线系统的一项关键使能功能。支持波束跟踪依赖于将信道状态信息（CSI）估计准确转换为位置预测。然而，由于城市传播环境本质上高度复杂，确定连接CSI与移动用户位置的过程是一项困难的任务。受此观察启发，大量研究致力于设计采用传统机器学习方法（如k近邻（k-NN）和卷积神经网络（CNN））的用户定位方案。然而，传统模型实现了较低的能效（EE）。为弥补这一劣势，脑启发的神经处理单元（NPU）最近被引入。为达到最佳运行，NPU需要执行一种新型神经模型，即脉冲神经网络（SNN）。受此启发，本文提出了一种无线网络架构，该架构通过新型卷积SNN（CSNN）模型实现CSI采集、转换为移动用户位置信息以及波束成形自适应。为训练和评估模型性能，我们基于逼真的射线追踪仿真创建了数据集。我们应用了CSNN架构，并将其性能与指纹k-NN和CNN在计算和通信定制性能指标方面进行了比较。结果凸显了能效与用户定位精度之间的权衡。
英文摘要
Wireless positioning is a key enabling functionality of high-frequency, highly directional wireless systems. Supporting beam tracking depends on accurately translating channel state in- formation (CSI) estimations into position predictions. However, as urban propagation environments are inherently highly complex, determining the process that connects the CSI with the mobile user position is a difficult task. Motivated by this observation, a great amount of effort was put on designing user positioning schemes that employ conventional machine learning approaches, such as k-nearest neighbors (k-NN), and convolutional neural networks (CNNs). However, conventional models achieve low energy efficiency (EE). To counterbalance this disadvantage, brain-inspired neural processing units (NPUs) has recently been introduced. For their optimum operation, NPUs require the execution of a new type of neural models, namely spiking neural networks (SNNs). Inspired by this, in this paper, we present a wireless network architecture that enables CSI acquisition, translation into mobile user position information, and beamforming adaptation through novel convolutional SNN (CSNN) models. To train and assess the models' performance, we created datasets based on realistic ray-tracing-based simulations. We applied the CSNN architecture and compared its performance against fingerprinting k-NNs, and CNNs in terms of both computing- and communication-tailored performance metrics. The results highlight a trade-off between EE and user positioning accuracy.
Comments13 pages, 9 figures
