Classifying Vessels Operating in the South China Sea by Origin with the Automatic Identification System

Abstract

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 vessels 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 vessels origin and provide insight into maritime patterns of behavior.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2018
Accession Number
AD1052543

Entities

People

  • Kimberly M. Cull

Organizations

  • Naval Postgraduate School

Tags

DTIC Thesaurus Topics

  • Accuracy
  • Anomaly Detection
  • Automatic Identification Systems
  • Big Data
  • Change Detection
  • Computer Programs
  • Computers
  • Data Mining
  • Data Science
  • Detection
  • Identification
  • Identification Systems
  • Information Science
  • Security
  • South China Sea
  • United States
  • United States Naval Academy

Readers

  • Asian Economic Studies
  • Computational Modeling and Simulation
  • Sensor Fusion and Tracking Systems.