LOS/Multipath/NLOS Measurement Classification using Machine Learning Approach

The traditional signal strength-based methods to achieve this, however, use a single variable (e.g. C/N₀) as the classifier. Because the single variable does not completely represent the multipath and NLOS characteristics of the signals, the traditional methods are not robust in the classification of signal reception. This paper uses a set of variables derived from the raw GPS measurements together with an algorithm based on a machine learning to classify direct, multipath-affected and NLOS measurements from GPS receiver.

This research is cooperated with Dr Rui Sun and Prof Washington Y. Ochieng

Adaptive GNSS/INS Integration Based on Supervised Machine Learning Approach

This study proposes an adaptive Kalman filter adjusting the noise covariance of GNSS measurements under different circumstances. The adaptive tuning is based on a proposed accuracy classification model trained a supervised machine learning method. Firstly, the principle component analysis is employed to identify the significant GNSS accuracy related features. Then, the supervised machine learning model is trained based on a random forest learning algorithm with the labelled real GNSS dataset covering most of scenarios in modern urban areas. To reduce the cases of miss-classifying GNSS accuracy, a fuzzy logic algorithm is designated to consider the GNSS accuracy propagation. Besides, the process noise covariance of INS is determined using Allan variance analysis. The results show that the proposed adaptive Kalman filter using random forest with fuzzy logic can achieve better classification of GNSS accuracy comparing with others.