Loading…

Design and Development of an AIoT Architecture for Introducing a Vessel ETA Cognitive Service in a Legacy Port Management Solution

Current Internet of Things (IoT) stacks are frequently focused on handling an increasing volume of data that require a sophisticated interpretation through analytics to improve decision making and thus generate business value. In this paper, a cognitive IoT architecture based on FIWARE IoT principle...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2021-12, Vol.21 (23), p.8133
Main Authors: Valero, Clara I., Ivancos Pla, Enrique, Vaño, Rafael, Garro, Eduardo, Boronat, Fernando, Palau, Carlos E.
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Current Internet of Things (IoT) stacks are frequently focused on handling an increasing volume of data that require a sophisticated interpretation through analytics to improve decision making and thus generate business value. In this paper, a cognitive IoT architecture based on FIWARE IoT principles is presented. The architecture incorporates a new cognitive component that enables the incorporation of intelligent services to the FIWARE framework, allowing to modernize IoT infrastructures with Artificial Intelligence (AI) technologies. This allows to extend the effective life of the legacy system, using existing assets and reducing costs. Using the architecture, a cognitive service capable of predicting with high accuracy the vessel port arrival is developed and integrated in a legacy sea traffic management solution. The cognitive service uses automatic identification system (AIS) and maritime oceanographic data to predict time of arrival of ships. The validation has been carried out using the port of Valencia. The results indicate that the incorporation of AI into the legacy system allows to predict the arrival time with higher accuracy, thus improving the efficiency of port operations. Moreover, the architecture is generic, allowing an easy integration of the cognitive services in other domains.
ISSN:1424-8220
1424-8220
DOI:10.3390/s21238133