EA-RMENet -- Path Loss Prediction in Urban Environments using Deep Learning
Machine Learning
Summary
The authors created a new deep learning model called EA-RMENet to predict how wireless signals weaken over distance, which helps in planning wireless networks. Their model uses a special design that combines efficient processing with a way to focus on important information and look at details at multiple scales. They tested it on a dataset and got accurate results quickly. It also performed well in a competition, showing it could work well in real-world scenarios.
Authors
Jonathan O'Shea, Conor Brennan
Abstract
Accurate path loss prediction is a critical component of wireless network planning. Current path loss prediction methods typically struggle to balance the trade-off between accuracy and computational efficiency. This paper proposes the Efficient Attention Radio Map Estimation Network (EA-RMENet) which is an image data-driven, deep learning (DL) model designed for radio map estimation (RME). EA-RMENet uses a U-Net framework with an EfficientNetB5 encoder, Attention Gated (AG) skip connections, and Atrous Spatial Pyramid Pooling (ASPP). The EfficientNet encoder uses compound scaling to balance accuracy and efficiency. AG skip connections suppress irrelevant features, and the ASPP captures a multi-scale context. The model has a test prediction RMSE of 0.0334 on the RadioMapSeer3D dataset with an inference time of 0.022 seconds/sample. In the ICASSP 2023 Radio Map Prediction Challenge, the model ranks third with a competitive RMSE of 0.0406 this highlights the models potential for real-world RME.