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 2209.04207eess.SP
收藏

无线信道特性超分辨的多任务学习模型

A Multi-Task Learning Model for Super Resolution of Wireless Channel Characteristics

Xiping Wang, Zhao Zhang, Danping He, Ke Guan, Dongliang Liu, Jianwu Dou

摘要:

信道建模一直是通信系统设计和开发中的核心部分,特别是在5G和6G时代。传统的方法,如随机信道建模和基于射线跟踪(RT)的信道建模严重依赖于测量数据或仿真,这通常是昂贵的和耗时的。在本文中,我们提出了一种新的超分辨率(SR)模型产生的信道特征数据。该模型是基于多任务学习(MTL)卷积神经网络(CNN)与剩余连接。实验结果表明,所提出的SR模型在平均绝对误差和误差标准差方面都有很好的性能。与其他最先进的深度学习模型相比,该模型的优势得到了证明。消融实验也证明了多任务学习和模型设计技术的必要性。本文的研究成果可以大大减少仿真或测量的工作量,有助于信道建模、网络优化、定位等无线信道特性相关工作的开展。

英文摘要:

Channel modeling has always been the core part in communication system design and development, especially in 5G and 6G era. Traditional approaches like stochastic channel modeling and ray-tracing (RT) based channel modeling depend heavily on measurement data or simulation, which are usually expensive and time consuming. In this paper, we propose a novel super resolution (SR) model for generating channel characteristics data. The model is based on multi-task learning (MTL) convolutional neural networks (CNN) with residual connection. Experiments demonstrate that the proposed SR model could achieve excellent performances in mean absolute error and standard deviation of error. Advantages of the proposed model are demonstrated in comparisons with other state-of-the-art deep learning models. Ablation study also proved the necessity of multi-task learning and techniques in model design. The contribution in this paper could be helpful in channel modeling, network optimization, positioning and other wireless channel characteristics related work by largely reducing workload of simulation or measurement.

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。

↑