.png){kind=icon}
.png){kind=icon}
Return
An Improved Kernel Density Estimation Method for Characterizing Buoy Offset
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3422228.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The AtoN department is responsible for mastering the drift characteristics of buoys, conducting targeted buoy inspections and resets, and providing accurate buoy position information for ship navigation. To analyze the buoy drift pattern, a K-Nearest Neighbor(KNN) improved Kernel Density Estimation(KED) method(KNN-KDE) is proposed to optimize the single bandwidth in the more complex distribution of the dataset can only depict the approximate trend of the data, while the details of the data changes can not be accurately estimated. KNN-KDE is utilized to estimate the coordinates of the buoy's gyration center and its radius of gyration, which establishes a mathematical model for buoy drift. Based on this approach, the telemetry position data from typical buoys in the main channel of Xiamen Harbor is collected to analyze the drift pattern of the buoys. This analysis provides a useful reference for the safety of navigation.
Keywords:
Kernel
Estimation
Navigation
Bandwidth
Mathematical models
Telemetry
Monitoring
Density measurement
Nearest neighbor methods
Buoys
kernel density estimation
drift pattern
K-nearest neighbors