Livrables
This Deliverable will contain the examination of the work and of the results obtained in WP4 against the current stateoftheart in railways It will report lessons learned weaknesses and strengths shown by each exploited technology technical and implementation recommendations unaddressed issues innovation needs Hence this Deliverable will provide WP5 with the necessary inputs to identify migration strategies and implement roadmaps for AI integration in the rail sector
Summary of existing relevant projects and state-of-the-art of AI application in railwaysThis Deliverable will provide a report on the existing AI applications in railways to determine current research and practice directions as well as a summary of the relevant work undertaken at a European level.
WP3 Report on experimentation, analysis and discussion of resultsThis Deliverable will describe the experimentation and analysis activities of the solutions and approaches described in D32 on real or realistic data It will describe analyses and simulations conducted applying the AI models and techniques to a set of case studies
WP2 Report on identification of future innovation needs and recommendations for improvementsThis Deliverable will contain a critical examination of the work and of the results obtained in WP2 also against the current stateoftheart in railways It will report lessons learned weaknesses and strengths shown by of each exploited technology technical and implementation recommendations unaddressed issues innovation needs Hence this Deliverable will provide WP5 with the necessary inputs to identify migration strategies and implement roadmaps for AI integration in the rail sector
WP4 Report on AI approaches and modelsThis Deliverable will provide a detailed description of the AIbased solutions and approaches for traffic planning and management AI techniques and Machine Learning models will be customized to the railway sector to support railway traffic operations
WP4 Report on case studies and analysis of transferability from other sectorsThis Deliverable will report activities and results related to the analysis of the stateoftheart and transferability of AI techniques used for maintenance to the rail domain with a special focus on traffic operations
Application AreasThis Deliverable will define a list of application areas for AI techniques and methods across railway domains, specifically in railway safety, smart maintenance, traffic planning and management.
WP2 Report on case studies and analysis of transferability from other sectorsThis Deliverable will report activities and results related to the applicability and transferability of machine learning techniques and other relevant approaches to the rail domain with a special focus on safe rail automation and will provide the definition of the case studies that will be developed throughout the WP Hence this Deliverable will provide the scope and the boundary of the research conducted in WP2
WP4 Report on experimentation, analysis and discussion of resultsThis Deliverable will describe the results obtained experimenting solutions and approaches described in D42 on real or realistic data It will describe analyses and simulations conducted applying the AI models and techniques to a set of case studies and it will discuss obtained results
WP2 Report on AI approaches and modelsThis Deliverable will report the core implementation of the research conducted in WP2 It will provide a detailed description of the AIbased solutions and approaches for safe rail automation developed for addressing the problems and the challenges posed by the case studies the related models and metrics the technological and operational issues Hence this Deliverable will provide the technological and methodological possible solutions alternatives and criticalities to be addressed by subsequent implementations
WP3 Report on case studies and analysis of transferability from other sectorsThis Deliverable will report activities and results related to the analysis of the stateoftheart and transferability of AI techniques used for maintenance to the rail domain with a special focus on predictive maintenance and defect detection
Definition of a reference taxonomy of AI in railwaysThis Deliverable will define a reference taxonomy of AI techniques capable of analysing, predicting and improving railway systems, also considering relevant applications from other high-tech sectors. It will define the set of AI techniques that would be appropriate for certain railway challenges taking into account the ethical dimension of AI.
Report on identification of migration strategies and roadmaps for AI integration in the rail sectorThis Deliverable will describe the identified migration strategies and roadmaps that enable the integration of relevant AI approaches either developed within this project or to be further explored in future research
WP2 Report on experimentation, analysis and discussion of resultsThis Deliverable will report the validation activities of the solutions and approaches described in D22 It will describe analyses and simulations conducted applying the AImodels and the other techniques developed in WP2 to the case studies in concrete operational scenarios Hence this Deliverable will provide meaningful insights and information on the validity of the research results and feasibility of the approach in real settings
Report on Dissemination and Exploitation activitiesThis Deliverable will describe the dissemination and exploitation activities carried out during the project and will discuss any deviations with respect to the plan
WP3 Report on AI approaches and modelsThis Deliverable will report the proposed AI approaches and models to enable smart maintenance in railways AI techniques and Machine Learning models will be customized to the railway sector
WP3 Report on identification of future innovation needs and recommendations for improvementsThis Deliverable will contain the examination of the work and of the results obtained in WP3 against the current stateoftheart in railways It will report lessons learned weaknesses and strengths shown by each exploited technology technical and implementation recommendations unaddressed issues innovation needs Hence this Deliverable will provide WP5 with the necessary inputs to identify migration strategies and implement roadmaps for AI integration in the rail sector
Publications
Auteurs:
Bešinović, Nikola; De Donato, Lorenzo; Flammini, Francesco; Goverde, Rob M. P.; Lin, Zhyiuan; Liu, Ronghui; Marrone, Stefano; Nardone, Roberto; Tang, Tianli; Vittorini, Valeria
Publié dans:
IEEE Transaction in Intelligent Transportation Systems, Numéro 23, 2022, Page(s) 14011-14024, ISSN 1524-9050
Éditeur:
Institute of Electrical and Electronics Engineers
DOI:
10.1109/tits.2021.3131637
Auteurs:
De Donato, Lorenzo; Flammini, Francesco; Marrone, Stefano; Mazzariello, Claudio; Nardone, Roberto; Sansone, Carlo; Vittorini, Valeria
Publié dans:
IEEE Access, Numéro 11, 2022, Page(s) 65376 - 65400, ISSN 2169-3536
Éditeur:
Institute of Electrical and Electronics Engineers Inc.
DOI:
10.1109/access.2022.3183102
Auteurs:
De Donato, Lorenzo; Marrone, Stefano; Flammini, Francesco; Sansone, Carlo; Vittorini, Valeria; Nardone, Roberto; Mazzariello, Claudio; Bernaudin, Frédéric
Publié dans:
Engineering Applications of Artificial Intelligence, Numéro 123, 2023, ISSN 0952-1976
Éditeur:
Pergamon Press Ltd.
DOI:
10.1016/j.engappai.2023.106405
Auteurs:
Mauro José Pappaterra, Francesco Flammini, Valeria Vittorini, Nikola Bešinović
Publié dans:
Infrastructures, Numéro 6/10, 2021, Page(s) 136, ISSN 2412-3811
Éditeur:
MDPI
DOI:
10.3390/infrastructures6100136
Auteurs:
De Donato, Lorenzo; Dirnfeld, Ruth; Somma, Alessandra; De Benedictis, Alessandra; Flammini, Francesco; Marrone, Stefano; Saman Azari, Mehdi; Vittorini, Valeria
Publié dans:
Journal of Reliable Intelligent Environments, Numéro 9, 2023, Page(s) 303–317, ISSN 0967-0912
Éditeur:
Institute of Materials
DOI:
10.1007/s40860-023-00208-6
Auteurs:
Basile, Giacomo; Napoletano, Elena; Petrillo, Alberto; Santini, Stefania
Publié dans:
Discover Artificial Intelligence, Numéro 2, 2022, ISSN 0967-0912
Éditeur:
Institute of Materials
DOI:
10.1007/s44163-022-00042-4
Auteurs:
Nijat Rajabli, Francesco Flammini, Roberto Nardone, Valeria Vittorini
Publié dans:
IEEE Access, Numéro 9, 2021, Page(s) 4797-4819, ISSN 2169-3536
Éditeur:
Institute of Electrical and Electronics Engineers Inc.
DOI:
10.1109/access.2020.3048047
Auteurs:
Tang, Ruifan; De Donato, Lorenzo; Bešinović, Nikola; Flammini, Francesco; Goverde, Rob M. P.; Lin, Zhyiuan; Liu, Ronghui; Tang, Tianli; Vittorini, Valeria; Wang, Ziyulong
Publié dans:
Transportation Research Part C: Emerging Technologies, Numéro 140, 2022, Page(s) 103679, ISSN 0968-090X
Éditeur:
Pergamon Press Ltd.
DOI:
10.1016/j.trc.2022.103679
Auteurs:
Lorenzo De Donato
Publié dans:
University of Naples Federico II, Numéro October 2020, 2020
Éditeur:
Università degli Studi di Napoli Federico II
DOI:
10.13140/rg.2.2.35490.96965/1
Auteurs:
Flammini, Francesco; De Donato, Lorenzo; Vittorini, Valeria; Fantechi, Alessandro
Publié dans:
Reliability, Safety, and Security of Railway Systems. LNCS Procs of RSSRail 2022, Numéro 13294, 2022, Page(s) 192–208, ISBN 978-3-031-05813-4
Éditeur:
Springer, Cham
DOI:
10.1007/978-3-031-05814-1_14
Recherche de données OpenAIRE...
Une erreur s’est produite lors de la recherche de données OpenAIRE
Aucun résultat disponible