Classifying vessels operating in the South China Sea by origin with the Automatic Identification System
Cull, Kimberly M.
Whitaker, Lyn R.
MetadataShow full item record
This research focuses on building classification models with multinomial responses based upon seven months of Automatic Identification System (AIS) data gathered from the South China Sea. The models, built using Gradient Boosted Machines (GBM), assess the validity of utilizing AIS to confirm an operating vessel’s origin, by country and geographical region. Two types of models are built. The first model captures the naturally dependent nature of AIS signals and serves as a proof of concept for how well a global model trained over many years could perform The second model attempts to reduce the dependency between AIS signals in order to characterize maritime patterns of behavior by country and region. With relative accuracy, both types of models are able to predict a vessel’s origin and provide insight into maritime patterns of behavior.
RightsThis publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.
Showing items related by title, author, creator and subject.
Salcido, Ryan; Kendall, Anthony; Zhao, Ying (AAAI, 2017);The primary research objective is to detect commercial flight baselines, anomalies and patterns using Automatic Dependent Surveillance – Broadcast (ADS-B) data to analyze aircraft tracks over a period time using Lexical ...
Vaniman, Daniel N. (Monterey, California. Naval Postgraduate School, 2007-12);ering level of jihadist activity in each country focus primarily on one foreign policy item: support or opposition to the Iraq war. However research shows a number of other critical items which also influence the level ...
Minimum-energy flight paths for UAVs using mesoscale wind forecasts and approximate dynamic programming Nachmani, Gil. (Monterey, California. Naval Postgraduate School, 2007-12);Fuel or battery consumption of unmanned aerial vehicles (UAVs) can be improved by utilizing or avoiding air currents. This thesis adopts a network modeling approach to formulate the problem of finding minimum energy ...