Abstract
SummaryThe general Global Navigation Satellite System (GNSS) receiver faces several challenges because of jamming signals, spoofing signals, and multipath signals, which severely influence its safety. In this paper, a receiver scheme with an interference recognition function is designed. In the latter, the correlation peak with different shapes is produced according to different interferences. The machine learning method is then applied to recognize and classify these feature maps. This transforms the interference recognition problem into a machine learning‐based classification problem. In order to reduce the complexity of the machine learning network, only the finite‐length correlation peak region of interest (ROI) is extracted as network input, endowing the shallow neural network with the interference recognition function. Afterward, five data acquisition environments are designed: authentic, spoofing, jamming, non‐line‐of‐sight (NLOS) multipath, and line‐of‐sight (LOS) multipath. Moreover, several experimental data are acquired, followed by the production of the correlation peak maps dataset, that are then learned and tested using two machine learning networks: one‐dimensional convolutional neural network (1D‐CNN) and bidirectional long short‐term memory neural network (BiLSTM‐NN). The results demonstrate that a recognition accuracy rate of over 98% can be reached using the shallow machine learning network.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have