SeaMate: Virtual Agent Based on AI, LLM and IoT Analytics for Smart Management in Nautical

Dec 1, 2024
projects
  • Period: December 2024 – November 2027
  • My role: FESB lead (FESB is a partner institution)
  • Funding: European Union, Integrated Territorial Programme 2021 – 2027, IP.1.1.03.0098
  • Team: Toni Perković (FESB lead), Petar Šolić, Ivo Stančić
  • Record: CroRIS

About the project

The SeaMate project explores the potential of applying artificial intelligence (AI) and the Internet of Things (IoT) to improve safety, efficiency and sustainability in smart nautical systems management, combining large language models (LLM), AI and IoT analytics to optimize the user experience in nautical tourism and improve vessel management.

The project focuses on the development of a virtual assistant for sailors, based on LLM and AI systems that enable real-time data analysis, personalized recommendations and automated responses via augmented reality (XR). The assistant provides information on safety procedures, weather conditions and technical support, which significantly contributes to the optimization of navigation and the reduction of risks in maritime traffic.

In addition, an IoT sensor network system is being investigated that includes monitoring of environmental conditions, energy consumption and vessel performance. The use of LPWAN technologies, satellite radio communications in combination with meteorological sensors, universal radio devices will enable real-time data collection and analysis. The data is processed using neural networks for advanced analytics, enabling predictive maintenance and optimization of ship trajectories.

This research contributes to the development of smart IoT solutions applicable in various fields, from maritime transport to emergency medical care. Through the synergy of AI, IoT and LLM technologies, the project offers an innovative approach to digitization and optimization of the nautical sector, increasing its competitiveness and environmental sustainability.

Project description from the CroRIS record.

FESB Lead EU Funding Current
Toni Perković
Authors
Toni Perković
Full Professor
I am a Full Professor in the Department of Electronics and Computing at the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture (FESB), University of Split, Croatia, where I teach wireless network security, wireless communication networks, data science and reinforcement learning. My research spans information security, applied cryptography and the Internet of Things. Before returning to FESB in 2020, I was an assistant and then associate professor at the University Department of Forensic Sciences in Split. I co-founded the SpliTech international conference and serve on the editorial board of the Journal of Communications Software and Systems.