RT-based dataset (V2.0) for 3D radio map under dynamic built-up scenario (1.25kmX1.25km)

The radio map, spectrum environment map (SEM), or RSSI map, can visualize the information of invisible electromagnetic spectrum, and is vital for monitoring, management, and security of spectrum
resources in cognitive radio (CR) networks. It is useful for the abnormal spectral activity detection,
radiation source localization, spectrum resource management, etc.

The performance of different 3D SEM construction methods should be compared based on the data under realistic scenarios. However, 3D RSSI data collecting by a spectrum sensing system is quite different and high costing. Moreover, it's unrepeatable and uncontrolable. So we obtained the RSSI by the RT-based calculation method under urban scenario . It includes two datasets as
1) dynamic scenario (radiation sources are moving for 600 seconds): Collecting data at the height of 2m, 25m, 50m and 80m.
2) static scenario (radiation sources are fixed) : Collecting data at the height of 2m, 10m, 20m, 30m, 40m, 50m, 80m.

The dataset has been applied and validated in the following references.
[1]. J. Wang, Q. Zhu, Z. Lin, Q. Wu, Y. Huang, X. Cai, et al., “Sparse Bayesian Learning-Based 3D Radio Environment Map Construction—Sampling Optimization, Scenario-Dependent Dictionary Construction and Sparse Recovery,” IEEE Transactions on Cognitive Communications and Networking, vol.10, pp.80-93, Feb. 2024.
[2]. J. Wang, Q. Zhu, Z. Lin, J. Chen, G. Ding, Q. Wu, G. Gu, Q. Gao, "Sparse Bayesian Learning-Based Hierarchical Construction for 3D Radio Environment Maps Incorporating Channel Shadowing," IEEE Transactions on Wireless Communications, vol.23, no.10, pp.14560-14574, Oct. 2024.
[3]. Q. Gao, Q. Zhu, Z. Lin et al., "Time-variant radio map reconstruction with optimized distributed sensors in dynamic spectrum environments,", IEEE Internet of Things Journal, early access, Feb. 2025, doi: 10.1109/JIOT.2025.3545542.
[4]. Y. Zhao, Q. Zhu, Z. Lin, L. Guo, Q. Wu, J. Wang, W. Zhong. “Temporal prediction for spectrum environment maps with moving radiation sources,” IET Communications, vol. 17, no. 5, pp. 538–548, 2023.

More details and instrucitons can be found in the guidemanual.pdf.

无线电地图、频谱环境图（Spectrum Environment Map，SEM）或接收信号强度指示图（Received Signal Strength Indicator，RSSI）可将不可见的电磁频谱信息可视化，在认知无线电（Cognitive Radio，CR）网络的频谱资源监测、管理与安全保障中发挥着关键作用，可应用于异常频谱活动检测、辐射源定位、频谱资源管理等场景。

需基于真实场景下的数据集对不同三维频谱环境图（SEM）构建方法的性能进行对比。然而，通过频谱感知系统采集的三维RSSI数据不仅采集流程复杂且成本高昂，同时具备不可复现与不可控的特性。因此本研究采用基于射线追踪（Ray Tracing，RT）的计算方法，在城市场景下获取RSSI数据。本数据集包含以下两类：
1. 动态场景（辐射源持续移动600秒）：在2m、25m、50m与80m四个高度采集数据。
2. 静态场景（辐射源保持固定）：在2m、10m、20m、30m、40m、50m与80m七个高度采集数据。

本数据集已在以下文献中得到应用与验证：
[1] J. Wang、Q. Zhu、Z. Lin、Q. Wu、Y. Huang、X. Cai等，"基于稀疏贝叶斯学习的三维无线电环境图构建——采样优化、场景相关字典构建与稀疏恢复"，《IEEE认知通信与网络汇刊》，第10卷，第80-93页，2024年2月。
[2] J. Wang、Q. Zhu、Z. Lin、J. Chen、G. Ding、Q. Wu、G. Gu、Q. Gao，"结合信道阴影效应的三维无线电环境图分层构建稀疏贝叶斯学习方法"，《IEEE无线通信汇刊》，第23卷第10期，第14560-14574页，2024年10月。
[3] Q. Gao、Q. Zhu、Z. Lin等，"动态频谱环境中基于优化分布式传感器的时变无线电地图重构"，《IEEE物联网期刊》，预出版，2025年2月，DOI: 10.1109/JIOT.2025.3545542。
[4] Y. Zhao、Q. Zhu、Z. Lin、L. Guo、Q. Wu、J. Wang、W. Zhong，"面向移动辐射源的频谱环境图时序预测"，《IET通信》，第17卷第5期，第538-548页，2023年。

更多细节与使用说明可参阅guidemanual.pdf文件。

搜集汇总

背景与挑战

背景概述

这是一个基于射线追踪的3D无线电地图数据集，用于动态建筑场景（1.25km×1.25km区域），包含动态和静态两种场景。数据集通过模拟方法生成，避免了实际采集的高成本和不可控性，数据以.mat格式提供，覆盖不同高度，并已应用于多篇学术论文验证。