A Modified Clustering Using Representatives to Enhance and Optimize Tracking and Monitoring of Maritime Traffic in Real-time Using Automatic Identification System Data

In this paper, we introduce a modification of the Clustering Using Representatives (CURE) algorithm to enhance and optimize the tracking and monitoring of maritime traffic in real-time using the Automatic Identification System (AIS) data. In doing so, we present a 2-D points data collection system f...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	2021 International Conference on Computational Science and Computational Intelligence (CSCI) s. 285 - 289
Hlavní autoři:	Manyfield-Donald, Cheronika, Kwembe, Tor A., Cheng, Jing-Ru C.
Médium:	Konferenční příspěvek
Jazyk:	angličtina
Vydáno:	IEEE 01.12.2021
Témata:	Automatic Identification System Big Data Clustering algorithms Clustering methods Clustering Using Representatives (CURE) Data collection Machine learning Machine learning algorithms Scientific computing Tracking
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	In this paper, we introduce a modification of the Clustering Using Representatives (CURE) algorithm to enhance and optimize the tracking and monitoring of maritime traffic in real-time using the Automatic Identification System (AIS) data. In doing so, we present a 2-D points data collection system for the utilization of a modified unsupervised machine learning clustering method of the CURE algorithm integrated with a data streaming algorithm to develop a more efficient method that will directly assist in adverting accidents and support in vessels avoiding dangerous environments. Results are presented that show tracking in inland as well as open sea waterways.
DOI:	10.1109/CSCI54926.2021.00119