Machine Learning-Based GPS Multipath Detection Method Using Dual Antennas
This addresses positioning errors for GPS users in urban environments, but it is incremental as it builds on existing machine learning techniques with dual antennas.
The study tackled GPS multipath detection in urban areas by proposing a machine learning method using dual antennas, achieving classification accuracies of 82%-96% for same-location data but dropping to 44%-77% for different-location data.
In urban areas, global navigation satellite system (GNSS) signals are often reflected or blocked by buildings, thus resulting in large positioning errors. In this study, we proposed a machine learning approach for global positioning system (GPS) multipath detection that uses dual antennas. A machine learning model that could classify GPS signal reception conditions was trained with several GPS measurements selected as suggested features. We applied five features for machine learning, including a feature obtained from the dual antennas, and evaluated the classification performance of the model, after applying four machine learning algorithms: gradient boosting decision tree (GBDT), random forest, decision tree, and K-nearest neighbor (KNN). It was found that a classification accuracy of 82%-96% was achieved when the test data set was collected at the same locations as those of the training data set. However, when the test data set was collected at locations different from those of the training data, a classification accuracy of 44%-77% was obtained.