An Efficient and Explainable KAN Framework for Wireless Radiation Field Prediction
This work addresses the problem of wireless radiation field prediction for communication systems, presenting an incremental improvement by integrating KAN with transformers for better performance.
The paper tackles the challenge of accurately modeling wireless channels by learning comprehensive representations of complete rays instead of individual points, resulting in outperforming existing methods in various scenarios.
Modeling wireless channels accurately remains a challenge due to environmental variations and signal uncertainties. Recent neural networks can learn radio frequency~(RF) signal propagation patterns, but they process each voxel on the ray independently, without considering global context or environmental factors. Our paper presents a new approach that learns comprehensive representations of complete rays rather than individual points, capturing more detailed environmental features. We integrate a Kolmogorov-Arnold network (KAN) architecture with transformer modules to achieve better performance across realistic and synthetic scenes while maintaining computational efficiency. Our experimental results show that this approach outperforms existing methods in various scenarios. Ablation studies confirm that each component of our model contributes to its effectiveness. Additional experiments provide clear explanations for our model's performance.