Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 8
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Federating Medical Deep Learning Models from Private Jupyter Notebooks to Distributed Institutions

  • Launet, Laetitia Mariana
  • Wang, Yuandou
  • Koulouzis, Spiros
  • Bianchi, Riccardo
  • Mosquera-Zamudio, Andrés
  • Monteagudo, Carlos
  • Zhao, Zhiming
  • Colomer, Adrián|||0000-0002-7616-6029
  • Igual García, Jorge|||0000-0003-3408-4014
  • Pulgarín-Ospina, Cristian Camilo|||0000-0002-9759-3791
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
[EN] Deep learning-based algorithms have led to tremendous progress over the last years, but they face a bottleneck as their optimal development highly relies on access to large datasets. To mitigate this limitation, cross-silo federated learning has emerged as a way to train collaborative models among multiple institutions without having to share the raw data used for model training. However, although artificial intelligence experts have the expertise to develop state-of-the-art models and actively share their code through notebook environments, implementing a federated learning system in real-world applications entails significant engineering and deployment efforts. To reduce the complexity of federation setups and bridge the gap between federated learning and notebook users, this paper introduces a solution that leverages the Jupyter environment as part of the federated learning pipeline and simplifies its automation, the Notebook Federator. The feasibility of this approach is then demonstrated with a collaborative model solving a digital pathology image analysis task in which the federated model reaches an accuracy of 0.8633 on the test set, as compared to the centralized configurations for each institution obtaining 0.7881, 0.6514, and 0.8096, respectively. As a fast and reproducible tool, the proposed solution enables the deployment of a cross-country federated environment in only a few minutes., This work has been partially funded by the European Union s Horizon 2020 research and innovation programme with the project CLARIFY under Marie Sklodowska-Curie (860627), ENVRI-FAIR (824068), BlueCloud (862409), and ARTICONF (825134). This work is also supported by LifeWatch ERIC, GVA through projects PROMETEO/2019/109 and INNEST/2021/321 (SAMUEL), and the Spanish Ministry of Economy and Competitiveness through project PID2019-105142RB-C21 (AI4SKIN). The work of Adrián Colomer has been supported by the ValgrAI Valencian Graduate School and Research Network for Artificial Intelligence & Generalitat Valenciana and Universitat Politècnica de València (PAID-PD-22).
Dipòsit Digital de la UB
Publication Artículo científico (JournalArticle)

FAIR Principles: Interpretations and Implementation Considerations

  • Jacobsen, Annika
  • Miranda Azevedo, Ricardo de
  • Juty, Nick
  • Batista, Dominique
  • Coles, Simon J.
  • Cornet, Ronald
  • Courtot, Mélanie
  • Crosas, Mercè
  • Dumontier, Michel
  • Evelo Chris, T.
  • Goble, Carole
  • Guizzardi, Giancarlo
  • Kryger-Hansen, Karsten
  • Hasnain, Ali
  • Hettne, Kristina
  • Heringa, Jaap
  • Hooft, Rob W. W.
  • Imming, Melanie
  • Jeffery, Keith G.
  • Kaliyaperumal, Rajaram
  • Kersloot, Martijn G.
  • Kirkpatrick, Christine R.
  • Kuhn, Tobias
  • Labastida i Juan, Ignasi, 1970-
  • Magagna, Barbara
  • McQuilton, Peter
  • Meyers, Natalie
  • Montesanti, Annalisa
  • van-Reisen, Mirjam
  • Rocca-Serra, Philippe
  • Pergl, Robert
  • Sansone, Susanna-Assunta
  • Bonino da Silva Santos, Luiz Olavo
  • Schneider, Juliane
  • Strawn, George
  • Thompson, Mark
  • Waagmeester, Andra
  • Weigel, Tobias
  • Wilkinson, Mark D.
  • Willighagen, Egon
The FAIR principles have been widely cited, endorsed and adopted by a broad range of stakeholders since their publication in 2016. By intention, the 15 FAIR guiding principles do not dictate specific technological implementations, but provide guidance for improving Findability, Accessibility, Interoperability and Reusability of digital resources. This has likely contributed to the broad adoption of the FAIR principles, because individual stakeholder communities can implement their own FAIR solutions. However, it has also resulted in inconsistent interpretations that carry the risk of leading to incompatible implementations. Thus, while the FAIR principles are formulated on a high level and may be interpreted and implemented in different ways, for true interoperability we need to support convergence in implementation choices that are widely accessible and (re)-usable. We introduce the concept of FAIR implementation considerations to assist accelerated global participation and convergence towards accessible, robust, widespread and consistent FAIR implementations. Any self-identified stakeholder community may either choose to reuse solutions from existing implementations, or when they spot a gap, accept the challenge to create the needed solution, which, ideally, can be used again by other communities in the future. Here, we provide interpretations and implementation considerations (choices and challenges) for each FAIR principle.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

EMSO ERIC’s authentication and authorization infrastructure

  • Rodero, Iván
  • Fornós, Andreu
  • Bardají, Raúl
  • Dañobeitia, Juan José
Special issue 9th MARTECH: International Workshop on Marine Technology: 16-18 June 2021, Vigo, Spain.-- 2 pages, 1 figure, A fundamental component of the EMSO ERIC cyber-infrastructure that integrates multiple ocean variables from EMSO ERIC regional facilities is its data management platform. The EMSO data management platform transition to pre-production enabled the deployment of EMSO ERIC data services based on harmonization, widely used specifcations, and FAIR principles. It establishes an appropriate workfow for taking stewardship of every stage of the data lifecycle on an architecture based on robustness and fault tolerance, including redundancy and failover capabilities, scalability, and security. This work presents EMSO ERIC’s authentication and authorization infrastructure, which provides security and accountability and enables personalized services, This work is supported by the European Union’s Horizon 2020 research and innovation Programme under grant agreement 824068, by the CSIC Intramural Project EMSO-Laboratorios Submarinos Profundos,and it is sponsored by EGI and the EOSC-hub H2020 project with the dedicated support of the CESGA and RECAS-BARI providers
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

The role of the marine research infrastructures in the European marine observation landscape: present and future perspectives

  • Dañobeitia, Juan José
  • Pouliquen, Sylvie
  • Pade, Nicolas
  • Arvanitidis, Christos
  • Sanders, Richard J.
  • Stanica, Adrian
  • Gourcuff, Claire
  • Petihakis, George
  • Tegas, Valentina
  • Favali, Paolo
13 pages, 3 figures, 1 table, The ocean regulates the exchange, storage of carbon dioxide, plays a key role in global control of Earth climate and life, absorbs most of the heat excess from greenhouse gas emissions and provides a remarkable number of resources for the human being. Most of the geo-hazards occur in oceanic areas. Thus, high-quality systematic observations are necessary tools for improving our understanding, and subsequent assimilation to provide early warning systems. A holistic scientific approach for the understanding of the ocean’s interrelated processes requires coordinated and complementary monitoring and observation programmes. Research Infrastructures (RIs) are large-scale facilities that provide resources and services for the scientific communities to conduct high-level research and foster innovation. RIs benefit from strong governance and multi-annual funding from their member states with operational life spans in decades. RIs promote knowledge, outreach and education to public, private, and policy stakeholders, and they play a key role in enabling and developing research in all scientific domains and currently represent a growing share of coordinated investment in research, and also in providing essential observations to operational services such as Copernicus. They are strategically important for Europe to lead a global movement towards a data-driven, interconnected, open digital twin that brings together different disciplines, clean technologies, public and private sectors and a broad scientific/technological community, as well as education and training. In Europe several marine RIs have been established, which are maintained by national and European Union (EU) resources. The aims of these infrastructures are aligned with the key priorities of the UN Decade of Ocean Science for Sustainable Development; and with the new European Research Area (ERA) Policy Agenda annexed to the Council conclusions on the ERA governance1, which set out 20 concrete actions for 2022-2024 to contribute to the priority areas defined in the EU Pact for R&I2. The purpose of this paper is to demonstrate that the combined expertise and assets of Europe’s marine RIs can form a comprehensive and holistic framework for long-term, sustainable integrated marine observation. Through this integration process the marine RIs can become better and better a significant pillar of the European Ocean Observing System (EOOS). Such a framework must be built as part of interfaces of interaction and promote not only scientific excellence but also innovation at all levels, Euro-Argo RISE Funded by the EU Horizon 2020 research and innovation programme under grant agreement n°824131. Euro-Sea: Funded from the EU Horizon 2020 research and innovation programme under grant agreement n°862626. ENVRI-FAIR: Funded from the EU Horizon 2020 research and innovation programme under grant agreement n°824068. Additionally, the authors gratefully acknowledge the support of their home institutions, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Fair principles: Interpretations and implementation considerations

  • Jacobsen, Annika
  • De Miranda Azevedo, Ricardo
  • Juty, Nick
  • Batista, Dominique
  • Coles, Simon
  • Cornet, Ronald
  • Courtot, Mélanie
  • Crosas, Mercè
  • Dumontier, Michel
  • Evelo, Chris T. A.
  • Goble, Carole
  • Guizzardi, Giancarlo
  • Hansen, Karsten
  • Hasnain, Ali
  • Hettne, Kristina
  • Heringa, Jaap
  • Hooft, Rob W.W.
  • Imming, Melanie
  • Jeffery, Keith
  • Kaliyaperumal, Rajaram
  • Kersloot, Martijn
  • Kirkpatrick, Christine R.
  • Kuhn, Tobias
  • Labastida, Ignasi
  • Magagna, Barbara
  • McQuilton, Peter
  • Meyers, Natalie
  • Montesanti, Annalisa
  • Van Reisen, Mirjam
  • Rocca-Serra, Philippe
  • Pergl, Robert
  • Sansone, Susanna Assunta
  • Santos, Luiz Olavo Bonino da Silva
  • Schneider, Juliane
  • Strawn, George
  • Thompson, Mark
  • Waagmeester, Andra S.
  • Weigel, Tobias
  • Wilkinson, Mark D.
  • Willighagen, Egon L.
  • Wittenburg, Peter
  • Roos, Marco
  • Mons, Barend
  • Schultes, Erik
The FAIR principles have been widely cited, endorsed and adopted by a broad range of stakeholders since their publication in 2016. By intention, the 15 FAIR guiding principles do not dictate specific technological implementations, but provide guidance for improving Findability, Accessibility, Interoperability and Reusability of digital resources. This has likely contributed to the broad adoption of the FAIR principles, because individual stakeholder communities can implement their own FAIR solutions. However, it has also resulted in inconsistent interpretations that carry the risk of leading to incompatible implementations. Thus, while the FAIR principles are formulated on a high level and may be interpreted and implemented in different ways, for true interoperability we need to support convergence in implementation choices that are widely accessible and (re)-usable. We introduce the concept of FAIR implementation considerations to assist accelerated global participation and convergence towards accessible, robust, widespread and consistent FAIR implementations. Any self-identified stakeholder community may either choose to reuse solutions from existing implementations, or when they spot a gap, accept the challenge to create the needed solution, which, ideally, can be used again by other communities in the future. Here, we provide interpretations and implementation considerations (choices and challenges) for each FAIR principle., The work of A. Jacobsen, C. Evelo, M. Thompson, R. Cornet, R. Kaliyaperuma and M. Roos is supported by funding from the European Union’s Horizon 2020 research and innovation program under the EJP RD COFUND-EJP N° 825575. The work of A. Jacobsen, C. Evelo, C. Goble, M. Thompson, N. Juty, R. Hooft, M. Roos, S-A. Sansone, P. McQuilton, P. Rocca-Serra and D. Batista is supported by funding from ELIXIR EXCELERATE, H2020 grant agreement number 676559. R. Hooft was further funded by NL NWO NRGWI. obrug.2018.009. N. Juty and C. Goble were funded by CORBEL (H2020 grant agreement 654248). N. Juty, C. Goble, S-A. Sansone, P. McQuilton, P. Rocca-Serra and D. Batista were funded by FAIRplus (IMI grant agreement 802750). N. Juty, C. Goble, M. Thompson, M. Roos, S-A. Sansone, P. McQuilton, P. Rocca-Serra and D. Batista were funded by EOSClife H2020-EU (grant agreement number 824087). C. Goble was funded by DMMCore (BBSRC BB/M013189/). M. Thompson, M. Roos received funding from NWO (VWData 400.17.605). S-A. Sansone, P. McQuilton, P. Rocca-Serra and D. Batista have been funded by grants awarded to S-A. Sansone from the UK BBSRC and Research Councils (BB/L024101/1; BB/L005069/1), EU (H2020-EU 634107; H2020-EU 654241, IMI (IMPRiND 116060), NIH Data Common Fund, and from the Wellcome Trust (ISA-InterMine 212930/Z/18/Z; FAIRsharing 208381/A/17/Z). The work of A. Waagmeester has been funded by grant award number GM089820 from the National Institutes of Health. M. Kersloot was funded by the European Regional Development Fund (KVW-00163). The work of N. Meyers was funded by the National Science Foundation (OAC 1839030). The work of M.D. Wilkinson is funded by Isaac Peral/Marie Curie cofund with the Universidad Politécnica de Madrid and the Ministerio de Economía y Competitividad grant number TIN2014-55993-RM. The work of B. Magagna, E. Schultes, L. da Silva Santos and K. Jeffery is funded by the H2020-EU 824068. The work of B. Magagna, E. Schultes and L. da Silva Santos is funded by the GO FAIR ISCO grant of the Dutch Ministry of Science and Culture. The work of G. Guizzardi is supported by the OCEAN Project (FUB). M. Courtot received funding from the Innovative Medicines Initiative 2 Joint Undertaking under grant agreement No. 802750. R. Cornet was further funded by FAIR4Health (H2020-EU grant agreement number 824666). K. Jeffery received funding from EPOS-IP H2020-EU agreement 676564 and ENVRIplus H2020-EU agreement 654182., Peer reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Metadata-driven universal real-time ocean sound measurement architecture

  • Martínez Padró, Enoc|||0000-0003-1233-7105
  • Garcia Benadí, Albert|||0000-0002-5560-4392
  • Toma, Daniel|||0000-0003-0472-1190
  • Delory, Eric
  • Gomáriz Castro, Spartacus|||0000-0001-9765-2176
  • Río Fernández, Joaquín del|||0000-0002-6191-2201
Underwater sound in the oceans has been significantly rising in the past decades due to an increase in human activities, adversely affecting the marine environment. In order to assess and limit the impact of underwater noise, the European Commission’s Marine Strategy Framework Directive (MSFD) included the long-term monitoring of low-frequency underwater sound as a relevant indicator to achieve a good environmental status. There is a wide range of commercial hydrophones and observing platforms able to perform such measurements. However, heterogeneity and lack of standardization in both hydrophones and observing platforms makes the integration and data management tasks time-consuming and error-prone. Moreover, their power and communications constraints need to be addressed to make them suitable for long-term ocean sound monitoring. Measured underwater sound levels are challenging to compare because different measurement methodologies are used, leading to a risk of misunderstandings and data misinterpretation. Furthermore, the exact methodology applied is not always public or accessible, significantly reducing ocean sound data re-usability. Within this work, a universal architecture for ocean sound measurement is presented, addressing hydrophone integration, real-time in situ processing and data management challenges. Emphasis is placed on generic and re-usable components, so it can be seamlessly replicated and deployed in new scenarios regardless of the underlying hardware and software constraints (hydrophone model, observing platform, operating system, etc.). Within the proposed architecture, a generic implementation of an underwater sound algorithm based on underwater noise measurement best practices is provided. Standardized and coherent metadata with emphasis on strong semantics is discussed, providing the building blocks for FAIR (Findable, Accessible, Interoperable, Reusable) ocean sound data management., This work has been funded by the Spanish government project RESBIO (grant agreement TEC2017-87861-R), the EU projects ENVRI-FAIR (grant agreement 824068), the JONAS INTERREG Atlantic Area-funded project (EAPA_52/2018), partly by the Generalitat de Catalunya SARTI-MAR project (grant agreement 2017 SGR 371) and partly by the FPI-UPC_2015 scholarship program., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Metadata-driven universal real-time ocean sound measurement architecture

  • Martínez Padró, Enoc
  • Garcia Benadí, Albert
  • Toma, Daniel
  • Delory, Eric
  • Gomáriz Castro, Spartacus
  • Río Fernández, Joaquín del
Underwater sound in the oceans has been significantly rising in the past decades due to an increase in human activities, adversely affecting the marine environment. In order to assess and limit the impact of underwater noise, the European Commission’s Marine Strategy Framework Directive (MSFD) included the long-term monitoring of low-frequency underwater sound as a relevant indicator to achieve a good environmental status. There is a wide range of commercial hydrophones and observing platforms able to perform such measurements. However, heterogeneity and lack of standardization in both hydrophones and observing platforms makes the integration and data management tasks time-consuming and error-prone. Moreover, their power and communications constraints need to be addressed to make them suitable for long-term ocean sound monitoring. Measured underwater sound levels are challenging to compare because different measurement methodologies are used, leading to a risk of misunderstandings and data misinterpretation. Furthermore, the exact methodology applied is not always public or accessible, significantly reducing ocean sound data re-usability. Within this work, a universal architecture for ocean sound measurement is presented, addressing hydrophone integration, real-time in situ processing and data management challenges. Emphasis is placed on generic and re-usable components, so it can be seamlessly replicated and deployed in new scenarios regardless of the underlying hardware and software constraints (hydrophone model, observing platform, operating system, etc.). Within the proposed architecture, a generic implementation of an underwater sound algorithm based on underwater noise measurement best practices is provided. Standardized and coherent metadata with emphasis on strong semantics is discussed, providing the building blocks for FAIR (Findable, Accessible, Interoperable, Reusable) ocean sound data management., This work has been funded by the Spanish government project RESBIO (grant agreement TEC2017-87861-R), the EU projects ENVRI-FAIR (grant agreement 824068), the JONAS INTERREG Atlantic Area-funded project (EAPA_52/2018), partly by the Generalitat de Catalunya SARTI-MAR project (grant agreement 2017 SGR 371) and partly by the FPI-UPC_2015 scholarship program., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

FAIR Principles: Interpretations and Implementation Considerations

  • Jacobsen, Annika
  • Miranda Azevedo, Ricardo de
  • Juty, Nick
  • Batista, Dominique
  • Coles, Simon J.
  • Cornet, Ronald
  • Courtot, Mélanie
  • Crosas, Mercè
  • Dumontier, Michel
  • Evelo Chris, T.
  • Goble, Carole
  • Guizzardi, Giancarlo
  • Kryger-Hansen, Karsten
  • Hasnain, Ali
  • Hettne, Kristina
  • Heringa, Jaap
  • Hooft, Rob W. W.
  • Imming, Melanie
  • Jeffery, Keith G.
  • Kaliyaperumal, Rajaram
  • Kersloot, Martijn G.
  • Kirkpatrick, Christine R.
  • Kuhn, Tobias
  • Labastida i Juan, Ignasi, 1970-
  • Magagna, Barbara
  • McQuilton, Peter
  • Meyers, Natalie
  • Montesanti, Annalisa
  • van-Reisen, Mirjam
  • Rocca-Serra, Philippe
  • Pergl, Robert
  • Sansone, Susanna-Assunta
  • Bonino da Silva Santos, Luiz Olavo
  • Schneider, Juliane
  • Strawn, George
  • Thompson, Mark
  • Waagmeester, Andra
  • Weigel, Tobias
  • Wilkinson, Mark D.
  • Willighagen, Egon
The FAIR principles have been widely cited, endorsed and adopted by a broad range of stakeholders since their publication in 2016. By intention, the 15 FAIR guiding principles do not dictate specific technological implementations, but provide guidance for improving Findability, Accessibility, Interoperability and Reusability of digital resources. This has likely contributed to the broad adoption of the FAIR principles, because individual stakeholder communities can implement their own FAIR solutions. However, it has also resulted in inconsistent interpretations that carry the risk of leading to incompatible implementations. Thus, while the FAIR principles are formulated on a high level and may be interpreted and implemented in different ways, for true interoperability we need to support convergence in implementation choices that are widely accessible and (re)-usable. We introduce the concept of FAIR implementation considerations to assist accelerated global participation and convergence towards accessible, robust, widespread and consistent FAIR implementations. Any self-identified stakeholder community may either choose to reuse solutions from existing implementations, or when they spot a gap, accept the challenge to create the needed solution, which, ideally, can be used again by other communities in the future. Here, we provide interpretations and implementation considerations (choices and challenges) for each FAIR principle.