Projektdetaljer

Beskrivelse

The objective of AMIDST is to develop a toolbox providing a scalable framework that facilitates efficient analysis and prediction based on information captured in streaming data. The work includes developing and scaling up existing algorithms in order to make the AMIDST toolbox flexible and versatile enough as to cope with the needs and requirements of a wide variety of applications. The toolbox will be particularized to address three industrial use-cases. Each use-case solution will be used to rigorously test the framework on real and complex data.The consortium has a strong and balanced combination of research and industrial partners. The academic partners ensure a scientific approach to theoretical and methodological aspects of the project. The industrial partners illustrate the importance of the potential developments provided by AMIDST for the EU economy, as they represent four strategic EU areas: software development, automotive industry, energy, and finance. AMIDST will make significant contributions towards the expected impacts of the call objectives. It will provide a generic framework for analysis of extremely large volumes of streaming data, thereby adding, creating and increasing the value of existing and new data resources as well as providing a means for more timely and efficient decision making. Each use-case solution represents an important contribution to its application domain.The industrial and commercial involvement in AMIDST ensures a high degree of commercial exploitations of the solutions developed. Each use-case represents one domain of commercial exploitation of effective solutions whereas the general framework will be applicable to a wide range of other domains. With the objective of creating a strong positive synergy, AMIDST takes an integrated European approach and joins partners with high interests in probabilistic modeling methods as well as techniques and algorithms for analysis of extremely large data volumes.
AkronymAMIDST
StatusAfsluttet
Effektiv start/slut dato01/01/201431/12/2016

Finansiering

  • European Union’s Seventh Framework Programme for research, technological development and demonstration: kr 2.762.000,00

Fingerprint Udforsk forskningsemnerne, som dette projekt berører. Disse etiketter er oprettet på grundlag af de underliggende bevillinger/legater. Sammen danner de et unikt fingerprint.

  • Projekter

    1

    Bock, A. R.

    Projekter: ProjektForskning

    1

    Bock, A. R.

    Projekter: ProjektForskning

    Publikation

    • 16 Konferenceartikel i proceeding
    • 4 Tidsskriftartikel
    • 2 Poster

    A parallel algorithm for Bayesian network structure learning from large data sets

    Madsen, A. L., Jensen, F., Salmerón, A., Langseth, H. & Nielsen, T. D., 2017, I : Knowledge-Based Systems. 117, s. 46-55

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

    Åben adgang
    Fil
    29 Citationer (Scopus)
    137 Downloads (Pure)

    MAP inference in dynamic hybrid Bayesian networks

    Ramos-López, D., Masegosa, A., Martinez, A. M., Salmerón, A., Nielsen, T. D., Langseth, H. & Madsen, A. L., 2017, I : Progress in Artificial Intelligence. 6, 2, s. 133–144 12 s.

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

    Åben adgang
    Fil
    3 Citationer (Scopus)
    122 Downloads (Pure)

    A Java Toolbox for Analysis of MassIve Data STreams using Probabilistic Graphical Models

    Masegosa, A., Martinez, A. M., Ramos-López, D., Langseth, H., Nielsen, T. D., Salmerón, A., Cabanas, R. & Madsen, A. L., 2016.

    Publikation: Konferencebidrag uden forlag/tidsskriftPosterForskningpeer review

    Fil