Statistical Inference of Light Buoy Gyrocenter Based on Kernel Density Estimation

Inhalt:
A statistical inference method based on kernel density estimation is proposed to measure the light buoy gyrocenter. To justify the reasonableness of the statistical inference method, the following contents are mentioned. First, a two-dimensional Gaussian kernel function is used to estimate the probability density function of the latitude and longitude sample. Second, the probability density weighted average of probability density peak is used as a gyrocenter estimated value. Third, the gyration radius is calculated with the gyrocenter and the sample. Finally, the t-test is used to prove the numerical fluctuation cycle of gyration radius is not significantly different from the tidal cycle.