基于视觉Transformer的用户设备定位
Vision Transformer Based User Equipment Positioning
AI总结:
针对现有深度学习用户设备定位模型注意力分配单一、不适用于非序列数据的问题,提出聚焦CSI矩阵角度延迟谱的ViT架构,在DeepMIMO和ViWi数据集上验证,定位精度优于现有最优方案约38%。
摘要:
近年来,深度学习(DL)技术已被用于用户设备(UE)定位。然而,此类模型的主要缺点在于:i)对整个输入赋予相同的注意力;ii)不适用于非序列数据,例如仅能获取瞬时信道状态信息(CSI)时。在此背景下,我们提出一种基于注意力的视觉Transformer(ViT)架构,其聚焦于CSI矩阵中的角度延迟谱(ADP)。我们的方法在‘DeepMIMO’和‘ViWi’射线追踪数据集上得到验证,在DeepMIMO中室内定位均方根误差(RMSE)为0.55米、室外为13.59米,在ViWi的室外遮挡场景中为3.45米。该方案优于现有最优方案约38%,且在误差距离分布方面的表现显著优于我们所考虑的其他方法。
英文摘要:
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, validated on the `DeepMIMO' and `ViWi' ray-tracing datasets, achieves an Root Mean Squared Error (RMSE) of 0.55m indoors, 13.59m outdoors in DeepMIMO, and 3.45m in ViWi's outdoor blockage scenario. The proposed scheme outperforms state-of-the-art schemes by $\sim$ 38\%. It also performs substantially better than other approaches that we have considered in terms of the distribution of error distance.
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。