将标量特征作为图像通道输入，提升路径损耗模型泛化能力
Investigating Map-Based Path Loss Models: A Study of Feature Representations in Convolutional Neural Networks
- 将频率、距离等标量特征以图像通道形式输入卷积网络
- 图像通道表示法在三种配置中表现最佳，泛化能力最强
- 适合无线通信建模与深度学习融合研究者参考
路径损耗预测是高效利用射频频谱的有力工具。基于先前关于高分辨率地图路径损耗模型的研究，本文更深入地探讨了卷积神经网络中标量特征的表示方法。我们比较了将频率和距离作为卷积层输入通道或作为回归层标量输入的策略。通过三种不同特征配置评估模型性能，发现将标量特征表示为图像通道时，模型泛化能力最强。
原文摘要 · Abstract (English)
Path loss prediction is a beneficial tool for efficient use of the radio frequency spectrum. Building on prior research on high-resolution map-based path loss models, this paper studies convolutional neural network input representations in more detail. We investigate different methods of representing scalar features in convolutional neural networks. Specifically, we compare using frequency and distance as input channels to convolutional layers or as scalar inputs to regression layers. We assess model performance using three different feature configurations and find that representing scalar features as image channels results in the strongest generalization.
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。