An Attention-Based Convolutional Network Framework for Detection and Localization of GNSS Interference Sources

Global navigation satellite system (GNSS) interference severely affects the quality of automatic dependent surveillance-broadcast (ADS-B) data, thereby jeopardizing aviation safety. Therefore, this article proposes an attention-based machine learning methodology for detecting and localizing GNSS interference sources. By exploring the spatio-temporal relationship between the interfered ADS-B data and the GNSS interference source, the interference source can be detected and located. Initially, we use the logistic regression algorithm to approximately detect and locate interference in an area. Subsequently, we propose an attention mechanism convolutional network (AMCN) to accurately localize interference sources. The proposed AMCN comprises two main blocks: A convolutional network that captures local features of individual aircraft and an attention network that captures the overall features of all associated aircraft. Within the attention network, an improved position embedding method maps sample sequences to their actual spatial locations. We demonstrate the effectiveness of our approach by achieving significant improvements over the state-of-the-art on actual aviation data. The proposed approach has the potential to effectively detect and locate GNSS interference sources, thereby reducing the security risk in civil aviation.