Robust Marine Buoy Placement for Ship Detection Using Dropout K-Means
This addresses the challenge of robust buoy placement for ship detection in marine surveillance, with incremental improvements over existing clustering methods.
The paper tackles the problem of placing marine buoys to detect ships for combating illegal fishing, proposing dropout k-means and dropout k-median to improve robustness against disruptions, resulting in detection probabilities up to 52% compared to 38-48% for classic methods with 5 buoys.
Marine buoys aid in the battle against Illegal, Unreported and Unregulated (IUU) fishing by detecting fishing vessels in their vicinity. Marine buoys, however, may be disrupted by natural causes and buoy vandalism. In this paper, we formulate marine buoy placement as a clustering problem, and propose dropout k-means and dropout k-median to improve placement robustness to buoy disruption. We simulated the passage of ships in the Gabonese waters near West Africa using historical Automatic Identification System (AIS) data, then compared the ship detection probability of dropout k-means to classic k-means and dropout k-median to classic k-median. With 5 buoys, the buoy arrangement computed by classic k-means, dropout k-means, classic k-median and dropout k-median have ship detection probabilities of 38%, 45%, 48% and 52%.