A Data-and-Semantic Dual-Driven Intelligent Inference Framework for Simultaneously Spectrum Map Construction and Signal Source Localization

Abstract

With the rapid development of wireless communication services, spectrum map-based localization has become an important technology in the sixth-generation (6G) wireless communication networks due to their low cost and ease of implementation. However, signal source localization based on spectrum map construction is heavily dependent on the construction accuracy of the spectrum map. This challenge is further exacerbated in urban environments due to high-density connections and complex terrain. To address the aforementioned challenges, a data-and-semantic dual-driven method is proposed, which incorporates semantic knowledge of both binary city maps and binary sampling location maps. This approach first extracts spatial dimension information that reflects signal propagation, improving the accuracy of the constructed spectrum map and signal source localization in the complex urban environments. Then, to reduce the reliance of signal source localization on the accuracy of spectrum map construction, a data-and-semantic dual-driven intelligent inference framework for simultaneously spectrum map construction and signal source localization (DSD-SCL) is proposed. Moreover, a joint training framework is employed to collaboratively optimize both spectrum map construction and signal source localization. Simulation results demonstrate that DSD-SCL exhibits superior performance in terms of stability and convergence speed. Meanwhile, it significantly enhances the construction accuracy of spectrum maps and the localization accuracy of signal sources, particularly in low sampling density and multisignal source scenarios.