Abstract
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.
Highlights
Trans-ionospheric communication of the radio waves while traveling from transmitter to user is affected by the ionosphere that is highly variable and dynamic in both time and space [1].The ionosphere, highly varied propagation medium, has an irregular structure due to plasma instabilities and scintillation is basically random fluctuations of the parameters of trans-ionospheric waves
Amplitude scintillation is monitored by computing the S4 index which corresponds to the standard deviation of the detrended signal intensity [15]
The third-order polynomial kernel provides improved performance compared to linear, coarse, and medium Gaussian kernel Support Vector Machines (SVM), but it comes with a cost of increased complexity and time
Summary
Trans-ionospheric communication of the radio waves while traveling from transmitter to user is affected by the ionosphere that is highly variable and dynamic in both time and space [1]. Detecting and monitoring the scintillation effects in order to estimate the ionospheric scintillation in its early stages and measure the scintillation parameters gains importance In this sense, GNSS signals provide an excellent means for measuring scintillation effects due to the fact that they are available all the time and can be acquired through many points of the ionosphere simultaneously [11]. We extend our previous work [28] which involves the performance comparison of linear and Gaussian kernels for phase scintillation detection versus the analysis of both amplitude and phase scintillation events.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call