Novel Big Data and Artificial Intelligence Analytics Methods for Tracking and Monitoring Maritime Traffics [supporting dataset]

Abstract of project report: Machine learning approaches have been proposed to predict ship speed over the ground and in monitoring and tracking vessels. The past decade has seen an explosion of machine learning research and applications; especially, deep learning methods have enabled key advances in many application domains, such as computer vision, speech processing, and in maritime vessel trajectories. However, the performance of many machine learning methods is very sensitive to a plethora of design decisions, which constitutes a considerable barrier for new users. The purpose of the field of Automated Machine Learning (AutoML) is to make these decisions in a data-driven, objective, and automated way. That is, the user simply provides data, and the AutoML system automatically determines the approach that performs best for this particular application. Therefore, the purpose of this project is to develop an AutoML model for monitoring and tracking maritime traffic, a state-of-the-art machine learning approach that is accessible to users of maritime historical and real-time databases interested in applying machine learning but do not have the resources to learn about the methods and technologies behind it in detail. Since the configuration of the global maritime network is organized along a circum-equatorial corridor linking North America, Europe, and Pacific Asia through the Suez Canal, the Strait of Malacca, and the Panama Canal (that is, linking all the choke points). The Machine Learning and hence the AutoML models are modified to capture maritime traffic in all global waters, including inland vessel traffics equip with the Automatic Identification System (AIS) transponders. The methodology is broken down into two major phases: Data-related activities and machine learning methods for maritime data analytics and vessel tracking activities. Data activities include data collection and data preparation. The machine learning methods for maritime data analysis includes the development and selection of models that are specific for historical and real-time maritime datasets and results. The uploaded documents consists of the MarTREC Project Report and the utilized AIS EXCEL DATASET.

• Dataset URL:
  https://doi.org/10.5281/zenodo.10699400
• Record URL:
  https://martrec.uark.edu/research/completedprojects/jsu_novel_big_data_final_acc.pdf
• Record URL:
  https://rosap.ntl.bts.gov/view/dot/73617
• Supplemental Notes:
  • The dataset supports report: Novel Big Data and Artificial Intelligence Analytics Methods for Tracking and Monitoring Maritime Traffics, available at the URL above. This document was sponsored by the U.S. Department of Transportation, University Transportation Centers Program.
• Corporate Authors:

  Maritime Transportation Research and Education Center (MarTREC)

  University of Arkansas
  4190 Bell Engineering Center
  Fayetteville, AR  United States  72701

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Authors:
  • Kwembe, Tor
  • 0000-0003-4720-2323
  • Whalin, Robert
  • 0000-0002-8712-9434
  • Jackson, Eric S
  • Nelson, Lancelot
  • Tchakoua, Ingrid K
• Publication Date: 2024-2-24

Language

• English

Media Info

• Media Type: Dataset
• Dataset: Version: 1.0 Integrity Hash:
• Dataset publisher:

  Zenodo

  ,    
• Features: References;

Subject/Index Terms

• TRT Terms: Algorithms; Artificial intelligence; Automatic tracking; Automatic vessel detection; Data; Machine learning; Water traffic
• Identifier Terms: National Automatic Identification System
• Subject Areas: Data and Information Technology; Marine Transportation; Planning and Forecasting;

Filing Info

• Accession Number: 01911854
• Record Type: Publication
• Contract Numbers: 69A3551747130
• Files: UTC, NTL, TRIS, USDOT
• Created Date: Mar 14 2024 9:38AM