Temporal-Correlated Deep-Learning Based GNSS Signal Classification in the Built Environment: a Comparative Experiment

As a key provider of Positioning, Navigation and Timing (PNT) information, the characteristics of Global Navigation Satellite System (GNSS) signals, including types, Quality Indicators (QIs), and measurements should be understood. This study employs temporal-correlated deep learning models to classify GNSS signals as Line-of-Sight (LOS) or non-LOS, using 4 QIs - elevation angle, Carrier to Noise Ratio (C / N0), code measurement’s standard deviation, and difference in azimuth angle. Autocorrelation analysis confirmed that these QIs exhibit significant temporal dependencies. The Bidirectional LSTM (Bi-LSTM) model, with 4 hidden layers, 64 units, and a sequence length of 18, achieved the best performance — 94.17% classification accuracy and a 2.61% False Positive (FP) rate. Positioning based on classified LOS signals significantly improved accuracy, reducing mean errors in the horizontal, vertical, and 3D domain by 36.6%, 81.4%, and 59.6%, respectively, and reducing Standard Deviation (STDEV) by 46.3%, 33.5%, and 45.5%. Moreover, The
non-LOS probabilities output enables flexible signal selection and mitigates the issue of insufficient signals. These results highlight the effectiveness of temporal-correlated models in GNSS signal classification and positioning performance.