Vision Transformer Based User Equipment Positioning
Parshwa Shah, Dhaval K. Patel, Brijesh Soni, Miguel López-Benítez, Siddhartan Govindasamy
最近,深度学习(DL)技术被用于用户设备(UE)定位。 然而,这些模型的主要缺点是:i)它们对整个输入具有相同的关注度;ii)它们不适合非顺序数据,例如,当只有瞬时通道状态信息(CSI)可用。 在此背景下,我们提出了一个基于注意力的视觉变压器(ViT)架构,该架构侧重于CSI矩阵中的角度延迟配置文件(ADP)。 我们的方法在“DeepMIMO”和“ViWi”射线跟踪数据集上进行了验证,在室内实现了0.55m的根均方误差(RMSE),在DeepMIMO的室外实现了13.59m,在ViWi的室外阻塞场景中实现了3.45m的根均方误差(RMSE)。 拟议的计划比最先进的计划高出38%。 它还比我们在误差距离分布方面考虑的其他方法要好得多。
Recently, Deep Learning (DL) techniques have been used for User Equipment (UE) positioning. However, the key shortcomings of such models is that: i) they weigh the same attention to the entire input; ii) they are not well suited for the non-sequential data e.g., when only instantaneous Channel State Information (CSI) is available. In this context, we propose an attention-based Vision Transformer (ViT) architecture that focuses on the Angle Delay Profile (ADP) from CSI matrix. Our approach, valid...
