Scintillation caused by the electron density irregularities in the ionospheric plasma leads to rapid fluctuations in the amplitude and phase of the Global Navigation Satellite Systems (GNSS) signals. Ionospheric scintillation severely degrades the performance of the GNSS receiver in the signal acquisition, tracking, and positioning. By utilizing the GNSS signals, detecting and monitoring the scintillation effects to decrease the effect of the disturbing signals have gained importance, and machine learning-based algorithms have been started to be applied for the detection. In this paper, the performance of Support Vector Machines (SVM) for scintillation detection is discussed. The effect of the different kernel functions, namely, linear, Gaussian, and polynomial, on the performance of the SVM algorithm is analyzed. Performance is statistically assessed in terms of probabilities of detection and false alarm of the scintillation event. Real GNSS signals that are affected by significant phase and amplitude scintillation effect, collected at the South African Antarctic research base SANAE IV and Hanoi, Vietnam have been used in this study. This paper questions how to select a suitable kernel function by analyzing the data preparation, cross-validation, and experimental test stages of the SVM-based process for scintillation detection. It has been observed that the overall accuracy of fine Gaussian SVM outperforms the linear, which has the lowest complexity and running time. Moreover, the third-order polynomial kernel provides improved performance compared to linear, coarse, and medium Gaussian kernel SVMs, but it comes with a cost of increased complexity and running time.

This paper provides a comparative performance analysis of different acquisition and tracking methods of GPS L1 C/A and GPS L5 signals testing their robustness to the presence of scintillations in the propagation environment. The paper compares the different acquisition methods in terms of probabilities of detection/false alarm, peak-to-noise floor ratios for the acquired signal and execution time, assessing the performance loss in the presence of scintillations. Moreover, robust tracking architectures that are optimized to operate in a harsh ionospheric environment have been employed. The performance of the carrier tracking methods, namely, traditional Phase-Locked Loop (PLL) and Kalman filter based-PLL, have been compared in terms of the standard deviation of Doppler estimation, phase error, phase lock indicator (PLI) and phase jitter. The study is based on real GNSS signals affected by significant phase and amplitude scintillation effects, collected at the South African Antarctic research base (SANAE IV) and Brazilian Centro de Radioastronomia e Astrofisica Mackenzie (CRAAM) monitoring stations. Performance is assessed exploiting a fully software GNSS receiver which implements the different architectures. The comparative analysis allows to choose the best setting of the acquisition and tracking parameters, in order to allow the operation of signal acquisition and tracking at a required performance level under scintillation conditions.

GNSS is widely used to provide positions in an absolute reference frame in Unmanned Aerial Vehicles (UAV) and Unmanned Ground Vehicles (UGV), where GNSS is merged with the information provided by other sensors. Even if the main goal of GNSS signal processing is the positioning, multifrequency signals are a rich source of information about the propagation environment surrounding the mobile vehicle. In urban and harsh environment, situational awareness is essential to tailor the operations and take proper countermeasure to harsh propagation conditions. Given this framework the present paper will describe the use of GNSS as signals of opportunity for the characterization of the operative environment by processing the GNSS observables through Machine Learning (ML) algorithms that can be used as efficient features extractors. The paper will present some case studies of operational scenarios for UGVs and for a static monitoring station, showing how through combining DSP techniques with both unsupervised and supervised ML algorithms (K-means classes, Support Vector Machines) it is possible to retrieve the information about the propagation scenario for multipath, interference and atmospheric limitations.

The aim of this paper is to analyze the design of support vector machine (SVM)algorithm that belongs to the class of supervised machine learning algorithms for phase scintillation detection and to discuss the performance comparison of linear and Gaussian kernel implementations by considering the design parameter's effects. The algorithm processes the phase scintillation indices computed for GPS L1 signals through the designed linear and Gaussian kernel SVM models. The study is based on the real GNSS signals which are affected by phase scintillations, collected at South African Antarctic research base (SANAE IV).