Skip to main content

ENABLING MARITIME DIGITALIZATION BY EXTREME-SCALE ANALYTICS, AI AND DIGITAL TWINS

Deliverables

VesselAI HPC Hw/Sw Requirements and Specifications

Requirements and Specifications for VesselAI HPC HwSw

Final VesselAI Methodology

This deliverable based on the feedback received by the projects end users will update the VesselAI methodology as well as any main components needed Any updates in the work implemented in D11 will also be considered finalising preliminary user requirements and integrated VesselAIs value chain

VesselAI Models, AI methods and Tools- v1.00

These deliverables will include the research design and delivery of all modules of the AI services including the data feed module the Model development module the model serving module as well as the resulting trained models

Plan for Dissemination, Communication and Stakeholder Engagement

This deliverable is related to the provision of a detailed plan for all dissemination communication community building and awareness creation activities that will be scheduled for the first reporting period of the project

Specifications of the AI On-Demand platform extensions and research activities-V2.00

These deliverables will include the specifications of the Vessel AI services as extensions to AI On demand existing services as well as all contributions to the ongoing AI4EU research activities

Specifications of the AI On-Demand platform extensions and research activities

These deliverables will include the specifications of the Vessel AI services as extensions to AI On demand existing services as well as all contributions to the ongoing AI4EU research activities

VesselAI Validation and Evaluation Framework

This deliverable is related to the documentation of the evaluation framework and validation methodology defining the various practices for obtaining feedback from endusers and including a set of testcases to be executed by the endusers

VesselAI Extreme-scale data processing, management services and semantics - v1.00

These series of deliverables will report the scientific foundations the design requirements and final services of the VesselAI project on the involved data services technologies as studied and researched within tasks T21T25 including the Data Ingestion and Management Module the Semantic Enrichment Module the Triplestore and Reasoning Engine and the Distributed Query Execution Engine

State-of-the-art analysis and data sources

This deliverable will include a thorough stateofplay analysis of the current landscape in terms of HPC BigData AI and advanced data processing techniques for extreme scale analytics and vessel models in particular including components tools and methodologies eventually promoting the most appropriate ones for the needs of VesselAI Moreover a definition of the VesselAI value chain the corresponding stakeholders and important information sources to be exploited will also be included The needs coming from the projects end users will also constitute a main output of this deliverable as a result of a 1st iteration of interviews and surveys separate part of this deliverable will deal with the definition of content IPR handling and sharing throughout the platform

VesselAI Methodology and MVP

The integrated project methodology as well as the Most Valuable Product MVP of VesselAI will be reported in the terms of this deliverable

VesselAI Technology Requirements & User Stories

This deliverable is related to the activities to be performed under Tasks 51 and will provide the user stories as well as the technology requirements for the VesselAI solution in alignment with the AI4EU platform as envisioned by the different user groups and will flesh out the concept

VesselAI Platform Components, Services & APIs Architecture

D52 will include the architecture diagrams and all design documents regarding the platform the components and the tobedeveloped VesselAI services while it will also define and describe the API interfaces that will be implemented

Dissemination, Communication and Stakeholder Engagement Report and Plan - Interim Version

This deliverable is related to the provision of a detailed plan for all dissemination communication community building and awareness creation activities that will be scheduled for the second reporting period of the project while it will also summarise all activities performed during the first reporting period of VesselAI

VesselAI Pilots Readiness Documentation and Execution Scenarios

Documentation of the set of scenarios realising the test cases in the given context and scope of the enduserorganisation that will run during each pilot including the actors involved the evaluation indicators the overall time plan and a detailed analysis of the required data sources per pilot and the an initial analysis on how each is envisioned to be leveraged in the scope of the pilot

Data Management Handling Plan

This deliverable is related to the detailed plan about which data will be collected and generated during the project and how it will be shared and opened This information is essential to decide the best sustainability model for project results and disseminate according to this plan the open data provided by the project The deliverable will be updated at end of the project

Project's Website and Web 2.0 Channels

This deliverable is related to the provision of the Website of the project and will set up all needed web and social channels that will be used during the project for communication

Searching for OpenAIRE data...

Publications

MaSEC: Discovering Anchorages and Co-movement Patterns on Streaming Vessel Trajectories

Author(s): Tritsarolis Andreas, Kontoulis Yannis, Pelekis Nikos, Theodoridis Yannis
Published in: 17th International Symposium on Spatial and Temporal Databases (SSTD '21), 2021
Publisher: Association for Computing Machinerυ
DOI: 10.1145/3469830.3470909

Methodology for Approval of Autonomous Ship Systems CONOPS

Author(s): Hagaseth Marianne, Rødseth Ørnulf Jan, Meland Per Håkon, Wille Egil, Meling Pia, Murray Brian
Published in: 21st International Conference on Computer and IT Applications in the Maritime Industries (COMPIT'22), Pontignano, Italy., 2022
Publisher: COMPIT
DOI: 10.5281/zenodo.6792507

ST_VISIONS: A Python Library for Interactive Visualization of Spatio-temporal Data

Author(s): Tritsarolis Andreas, Doulkeridis Christos, Pelekis Nikos, Theodoridis Yannis
Published in: 2021 22nd IEEE International Conference on Mobile Data Management (MDM), 2021
Publisher: IEEE
DOI: 10.1109/mdm52706.2021.00048

Vessel Collision Risk Assessment using AIS Data: A Machine Learning Approach

Author(s): Tritsarolis Andreas, Chondrodima Eva, Pelekis Nikos, Theodoridis Yannis
Published in: 3rd IEEE International Maritime Big Data Workshop of the 23rd MDM Conference, Paphos, Cyprus, June 6, 2022, June 6, 2022, 2022
Publisher: IEEE
DOI: 10.5281/zenodo.6795554

Data-driven digital twins for the maritime domain

Author(s): Troupiotis Alexandros, Kaliorakis Manolis, Zissis Dimitris, Mouzakitis Spiros, Tsapelas Giannis, Artikis Alexander, Chondrodima Eva, Theodoridis Yannis
Published in: 20th International Conference on Ship and Maritime Research (NAV 2022), Genova- La Spezia, Italy, 15-17 June 2022, 15-17 June 2022, 2022
Publisher: Associazione Italiana di Tecnica Navale
DOI: 10.5281/zenodo.6795530

Optimizing complex event forecasting

Author(s): Stavropoulos Vasileios, Alevizos Elias, Giatrakos Nikos, Artikis Alexander
Published in: 16th ACM International Conference on Distributed and Event-Based Systems (DEBS'22), Copenhagen, Denmark, June 27 - 30, 2022, June 27 - 30, 2022, 2022
Publisher: Association for Computing Machinery
DOI: 10.1145/3524860.3539810

MARVEL Workshop - DATAWEEK2022 - The challenges of the extreme-scale multi-modal analytics applications

Author(s): Sotiris Ioannidis, Manfredo Atzori, Nikolaos Passalis, Paulo Figueiras
Published in: MARVEL Workshop - DATAWEEK2022 - The challenges of the extreme-scale multi-modal analytics applications., June 19 2022, 2022
Publisher: Big Data Value Association and the EUHubs4Data project
DOI: 10.5281/zenodo.6667599

Machine Learning Models for Vessel Traffic Flow Forecasting: An Experimental Comparison

Author(s): Mandalis Petros, Chondrodima Eva, Kontoulis Yannis, Pelekis Nikos, Theodoridis Yannis
Published in: 3rd IEEE International Maritime Big Data Workshop of the 23rd MDM Conference, Paphos, Cyprus, June 6, 2022, June 6, 2022, 2022
Publisher: IEEE
DOI: 10.5281/zenodo.6795546

Machine Learning Models for Vessel Route Forecasting: An Experimental Comparison

Author(s): Chondrodima Eva, Mandalis Petros, Pelekis Nikos, Theodoridis Yannis
Published in: 23rd IEEE International Conference on Mobile Data Management (MDM), June 6 – 9, 2022, June 6 – 9, 2022, 2022
Publisher: IEEE
DOI: 10.5281/zenodo.6795539

Bridging the Chasm between Science and Reality

Author(s): Kersten Martin, Koutsourakis Panagiotis, Niels Nes, Zhang Ying
Published in: Conference on Innovative Data Systems Research 2021 (CIDR), 2021
Publisher: CIDR
DOI: 10.5281/zenodo.6782789

Detecting representative trajectories from global AIS datasets

Author(s): Zygouras Nikolas, Spiliopoulos Giannis, Zissis Dimitris
Published in: 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), Indianapolis, IN, USA, 19-22 September 2021, 2021
Publisher: IEEE
DOI: 10.1109/itsc48978.2021.9564657

ATSC-NEX: Automated Time Series Classification With Sequential Model-Based Optimization and Nested Cross-Validation

Author(s): Tahkola Mikko, Guangrong Zou
Published in: IEEE Access, Volume 10, 2022, Page(s) 39299-39312, ISSN 2169-3536
Publisher: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2022.3166525

The Piraeus AIS dataset for large-scale maritime data analytics

Author(s): Tritsarolis Andreas, Kontoulis Yannis, Theodoridis Yannis
Published in: Data in Brief, Volume 41, April 2022, 2022, Page(s) Pages 107940, ISSN 2352-3409
Publisher: Elsevier BV
DOI: 10.1016/j.dib.2021.107782

A Survey on Big Data Processing Frameworks for Mobility Analytics

Author(s): Doulkeridis Christos, Vlachou Akrivi, Pelekis Nikos, Theodoridis Yannis
Published in: ACM SIGMOD Record, Volume 50, Issue 2, 2021, Page(s) 18-29, ISSN 0163-5808
Publisher: Association for Computing Machinary, Inc.
DOI: 10.1145/3484622.3484626