Deep Learning-Based Indoor Path Loss Prediction Model With Spatial Attention

Abstract

Path loss (PL) prediction is critical for wireless networks and most data traffic originates indoors. Effective network planning and base station deployment in high-frequency bands of 5G/6G systems necessitate addressing the accuracy–efficiency tradeoff. We propose a deep learning framework that combines dilated convolutions with spatial attention mechanisms to enhance PL prediction accuracy. Our model adaptively extracts multiscale environmental features while focusing on site-specific PL through attention-driven localization. Experimental results demonstrate superior performance over conventional models. In addition, the proposed architecture eliminates input size constraints and enables direct fine-tuning with measurement data, offering practical advantages for facilitating real-world deployment.