用卷积神经网络直接从二维障碍物高度图预测路径损耗，无需人工设计特征。
Map-Based Path Loss Prediction in Multiple Cities Using Convolutional Neural Networks
- 基于2D障碍物高度图，用CNN自动提取路径特征
- 在多个城市环境中实现低预测误差，无需额外衍生指标
- 适合无线网络部署与频谱规划人员使用
无线通信部署和频谱规划依赖于路径损耗的准确预测。传统方法常将障碍物影响隐式处理，或通过代表性的地物高度、总遮挡深度等衍生指标来表征。本文提出一种基于路径的路径损耗预测方法，利用卷积神经网络（CNN）直接从二维障碍物高度图中自动提取特征。该方法在多种环境条件下均实现了较低的预测误差，且无需依赖人工构造的衍生指标。实验验证了其在多城市场景下的有效性与泛化能力。
原文摘要 · Abstract (English)
Radio deployments and spectrum planning benefit from path loss predictions. Obstructions along a communications link are often considered implicitly or through derived metrics such as representative clutter height or total obstruction depth. In this paper, we propose a path-specific path loss prediction method that uses convolutional neural networks to automatically perform feature extraction from 2-D obstruction height maps. Our methods result in low prediction error in a variety of environments without requiring derived metrics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。