Radio Map Updating from Streaming Spectrum Measurements via Memory-Based Online Gaussian Processes
2026-07-20 • Information Theory
Information Theory
AI summaryⓘ
The authors developed a new method to create radio maps, which show how radio signals are spread out in an area, using data that arrives continuously. Their approach updates the map efficiently without having to reprocess all previous data every time new measurements come in. They use a smart way to remember some past data to avoid forgetting important information and adjust their method dynamically based on where measurements are taken. Tests show their method is more accurate and faster than older methods while also showing uncertainty in predictions.
Radio mapsSpectrum measurementsGaussian processVariational inferenceOnline learningSparse approximationInducing pointsCatastrophic forgettingUncertainty quantificationGrid-based methods
Authors
Yuanyuan Deng, Bo Zhou, Tian Chen, Shijian Gao, Jia Yan, Lantu Guo, Qiuming Zhu, Qihui Wu
Abstract
Radio maps, which estimate spatial radio-frequency characteristics from spectrum measurements, are essential for applications such as spectrum management and network planning. With the continuous arrival of spectrum measurements, conventional batch processing methods for radio map reconstruction become computationally prohibitive, as they require reprocessing all accumulated measurements for each radio map update. To address this, we propose a memory-based online sparse variational Gaussian process (M-OSVGP) method that efficiently updates radio maps from streaming spectrum measurements. Our method employs sparse variational inference and updates the posterior online by minimizing a hybrid objective that integrates newly received measurements and a memory subset of previous ones to mitigate catastrophic forgetting. To further improve posterior approximation as measurements accumulate over spatially diverse regions, we extend M-OSVGP with a grid-assisted online inducing point selection (GOIPS) algorithm. GOIPS dynamically adapts the number and locations of inducing points based on measurement density and spatial correlation, providing a more informative inducing set while maintaining computational efficiency. Extensive simulations demonstrate the effectiveness of our proposed methods in reconstruction accuracy, computational efficiency, and uncertainty quantification, compared to existing batch and online baselines across various scenarios.