This website requires JavaScript.

RME-GAN: A Learning Framework for Radio Map Estimation based on Conditional Generative Adversarial Network

Songyang ZhangAchintha WijesingheZhi Ding
Dec 2022
摘要
Outdoor radio map estimation is an important tool for network planning andresource management in modern Internet of Things (IoT) and cellular systems.Radio map describes spatial signal strength distribution and provides networkcoverage information. A practical goal is to estimate fine-resolution radiomaps from sparse radio strength measurements. However, non-uniformly positionedmeasurements and access obstacles can make it difficult for accurate radio mapestimation (RME) and spectrum planning in many outdoor environments. In thiswork, we develop a two-phase learning framework for radio map estimation byintegrating radio propagation model and designing a conditional generativeadversarial network (cGAN). We first explore global information to extract theradio propagation patterns. We then focus on the local features to estimate theeffect of shadowing on radio maps in order to train and optimize the cGAN. Ourexperimental results demonstrate the efficacy of the proposed framework forradio map estimation based on generative models from sparse observations inoutdoor scenarios.
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答