Answers are grounded in this paper and cite their sources.
In controlled BeiDou B1I simulation scenarios, traditional recognition and suppression algorithms may show limited adaptability when interference types and jamming-to-noise ratios vary. Based on time-frequency analysis, this paper studies a two-stage BeiDou positioning signal interference recognition and processing algorithm. First, signal models for six representative interference types are constructed, and their time-frequency characteristics are extracted. Second, a CNN-based recognition model is used to classify the time-frequency feature maps, while WPT is adopted for multi-scale interference suppression and signal reconstruction. The contribution of this study lies in integrating feature-guided CNN recognition with WPT-based suppression in a unified and computationally efficient pipeline for BeiDou B1I interference simulation. Experiments on independently generated simulated samples show that the CNN model achieves an average recognition accuracy of 94.01%, a false positive rate of 3.31%, and a recognition time of 3.25 s for six interference categories. The WPT-based suppression stage obtains an MSE of 2.54%, a signal recovery rate of 94.63%, an SNR of 28.44 dB, and a calculation time of 0.18 s. These results indicate that the proposed pipeline is effective under the tested simulation conditions; field-measured BeiDou/GNSS data and more complex composite interference should be further evaluated before extending the conclusions to practical electromagnetic environments.
No takes yet. Share an insight, caveat, or question.
Yuan et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: