EXPeriment driven and user eXPerience oriented analytics for eXtremely Precise outcomes and decisions

Informazioni relative al progetto

ExtremeXP

ID dell’accordo di sovvenzione: 101093164

DOI 10.3030/101093164

Data della firma CE 16 Novembre 2022

Data di avvio 1 Gennaio 2023

Data di completamento 31 Dicembre 2025

Finanziato da

• Digital, Industry and Space

Costo totale € 10 011 820,00

Contributo UE € 10 011 820,00

Coordinato da

ATHINA-EREVNITIKO KENTRO KAINOTOMIAS STIS TECHNOLOGIES TIS PLIROFORIAS, TON EPIKOINONION KAI TIS GNOSIS
Grecia

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Dimostratori, piloti, prototipi (2)

Core framework services - Data and knowledge management

This deliverable will document the core framework services responsible for (a) the secure and distributed management of datasets, knowledge assets and experimentation-based learning outcomes and (b) defining and enforcing appropriate data authorisation by considering contextual information of the requestor, the artefact to be accessed and processed and their environment. It will include prototype libraries and/or tools and will document their implementation and usage information.

Data selection, integration, and simulation services

This deliverable will provide the first versions of (a) automated dataset selection strategies and feature augmentation methods, that will recommend the datasets that are fit-for-purpose for the current analytics task; (b) Analysis aware data integration and quality assurance services, that will support the interactive application of cleaning, interlinking, and enrichment methods to data gathered from various dispersed sources; (c) Data augmentation and simulation techniques, that will allow to detect the types and ranges of data that are missing in the datasets, in order to generate new data entries to balance the datasets with various augmentation techniques, and or deploy simulation models to produce new data. It will include prototype libraries and/or tools and will document their implementation and usage information.

Documenti, relazioni (2)

Initial architecture, languages and models for complex experiment-driven analytics

This deliverable will report on the design the architecture of the ExtremeXP framework, as well as the modelling language and the underlying models that will support experiment-driven analytics. It will provide the specifications of a domain specific modelling language, as well as knowledge graphs for semantically representing experiments. Finally, it will describe the architecture of the framework, which will comprise several independent, self-contained, and elastic core services that can be used to store knowledge assets from experiments, collect evaluation data including user feedback, plan experiments, and enact them (either locally or on remote systems) using virtualized resources and serverless functions.

Use case requirements

This deliverable will report on the requirements elicited from each use-case and will issue technical designs of the use-case pilots while contributing functional and technical expectations over the ExtremeXP project. For each use-case, this process includes the selection of adequate datasets, the domain modelling, the variability point identification, the specification of the experiment models, the elicitation of user intents, and the determination of the technical settings for evaluation.

Pubblicazioni

Atti di conferenza (20)

Optimizing Data Analytics Workflows through User-driven Experimentation

Autori: Keerthiga Rajenthiram
Pubblicato in: 3rd International Conference on AI Engineering – Software Engineering for AI (CAIN 2024), 2024
DOI: 10.1145/3644815.3644971

METIS: AN OPEN-ARCHITECTURE FOR BUILDING AI-READY CLOUD PLATFORMS – APPLICATION TO FOSTER RESEARCH ON HYDROLOGICAL MODELING

Autori: Vincent GAUDISSART, Yasmine BOULFANI, Kevin LARNIER, Gwendoline STEPHAN, Jacques COVES and Christophe TRIQUET
Pubblicato in: Proceedings of the 2023 conference on Big Data from Space (BiDS’23), Numero KJ-05-23-390-EN-N, 2023, ISBN 978-92-68-08696-4
Editore: Joint Research Centre (European Commission)
DOI: 10.2760/46796

Capturing Analytical Intents from Text

Autori: Gerard Pons, Miona Dimic, Besim Bilalli
Pubblicato in: 2020
Editore: Springer
DOI: 10.1007/s10844-020-00604-x

There is no Data Science without Data Governance: a Proposal Based on Knowledge Graphs

Autori: Besim Bilalli, Petar Jovanovic, Sergi Nadal, Anna Queralt, Oscar Romero
Pubblicato in: DOLAP 2024: 26th International Workshop on Design, Optimization, Languages and Analytical Processing of Big Data, 2024, ISSN 1613-0073
Editore: CEUR

Online ML Self-adaptation in Face of Traps

Autori: Topfer, Michal; Plasil, Frantisek; Bures, Tomas; Hnetynka, Petr; Krulis, Martin; Weyns, Danny
Pubblicato in: Proceedings of ACSOS 2023, Toronto, Canada, 2023
DOI: 10.48550/arxiv.2309.05805

Non-Expert Level Analysis of Self-Adaptive System

Autori: Claudia Raibulet and Xiaojun Ling
Pubblicato in: ASOCA2023@ICSOC 2023, 2023
Editore: Springer, Singapore
DOI: 10.1007/978-981-97-0989-2_8

An Empirical Performance Comparison between Matrix Multiplication Join and Hash Join on GPUs

Autori: Wenbo Sun; Asterios Katsifodimos; Rihan Hai
Pubblicato in: 2023 IEEE 39th International Conference on Data Engineering Workshops (ICDEW), 2023, ISBN 979-8-3503-2245-3
Editore: IEEE
DOI: 10.1109/ICDEW58674.2023.00034

Amalur: Data Integration Meets Machine Learning

Autori: Hai, R. (author); Koutras, C. (author); Ionescu, A. (author); Li, Z. (author); Sun, W. (author); van Schijndel, Jessie (author); Kang, Yan (author); Katsifodimos, A (author)
Pubblicato in: Crossref, 2023
DOI: 10.48550/arxiv.2205.09681

Discovery of Semantic Non-Syntactic Joins

Autori: Marc Maynou, Sergi Nadal
Pubblicato in: DOLAP 2024: 26th International Workshop on Design, Optimization, Languages and Analytical Processing of Big Data, 2024, ISSN 1613-0073
Editore: CEUR

Evolvability of Machine Learning-based Systems : An Architectural Design Decision Framework

Autori: Joran Leest, Ilias Gerostathopoulos, Claudia Raibulet
Pubblicato in: 2023 IEEE 20th International Conference on Software Architecture Companion (ICSA-C), 2023
Editore: IEEE
DOI: 10.1109/ICSA-C57050.2023.00033

Mitigating Data Sparsity in Integrated Data through Text Conceptualization

Autori: Md Ataur Rahman, Sergi Nadal, Oscar Romero, Dimitris Sacharidis
Pubblicato in: 2024 IEEE 40th International Conference on Data Engineering (ICDE), 2024
Editore: IEEE
DOI: 10.1109/ICDE60146.2024.00269

Auditing for Spatial Fairness

Autori: Sacharidis, Dimitris; Giannopoulos, Giorgos; Papastefanatos, George; Stefanidis, Kostas
Pubblicato in: 2023
DOI: 10.48550/arxiv.2302.12333

MAPE-K based Guidelines for Designing Reactive and Proactive Self-Adaptive Systems

Autori: Hendrik Jilderda and Claudia Raibulet
Pubblicato in: Post Proceedings of the ECSA 2023 Workshops, in press, 2023
Editore: Springer, Cham
DOI: 10.1007/978-3-031-66326-0_4

Adaptive Strategies Metric Suite

Autori: Koen Kraaijveld and Claudia Raibulet
Pubblicato in: 2024
Editore: Springer, Cham
DOI: 10.1007/978-3-031-64182-4_14

An Approach for Intelligent Behaviour-Based Threat Modelling with Explanations

Autori: S. Preetam, M. Compastié, V. Daza, and S. Siddiqui,
Pubblicato in: 2023, ISSN 2832-2231
Editore: IEEE
DOI: 10.1109/NFV-SDN59219.2023.10329587

AutoFeat: Transitive Feature Discovery over Join Paths

Autori: Andra Ionescu, Kiril Vasilev, Florena Buse, Rihan Hai, Asterios Katsifodimos
Pubblicato in: 2024 IEEE 40th International Conference on Data Engineering (ICDE), 2024
Editore: IEEE
DOI: 10.1109/ICDE60146.2024.00150

Model Selection with Model Zoo via Graph Learning

Autori: Ziyu Li, Hilco van der Wilk, Danning Zhan, Megha Khosla, Alessandro Bozzon, Rihan Hai
Pubblicato in: 2024 IEEE 40th International Conference on Data Engineering (ICDE), 2024
Editore: IEEE
DOI: 10.1109/ICDE60146.2024.00088

HYPPO: Using Equivalences to Optimise Pipelines in Exploratory Machine Learning

Autori: Antonis Kontaxakis, Dimitris Sacharidis, Alkis Simitsis, Alberto Abelló, Sergi Nadal:
Pubblicato in: 2024 IEEE 40th International Conference on Data Engineering (ICDE), 2024
Editore: IEEE
DOI: 10.1109/ICDE60146.2024.00024

Expert-Driven Monitoring of Operational ML Models

Autori: Leest, Joran; Raibulet, Claudia; Gerostathopoulos, Ilias; Lago, Patricia
Pubblicato in: International Conference on Software Engineering (ICSE), 2024, ISBN 979-8-4007-0217-4
DOI: 10.48550/arxiv.2401.11993

Visualization-aware Time Series Min-Max Caching with Error Bound Guarantees

Autori: Stavros Maroulis, Vassilis Stamatopoulos, George Papastefanatos, Manolis Terrovitis
Pubblicato in: 50th International Conference on Very Large Databases (VLDB 2024), 2024
Editore: VLDB Endowment
DOI: 10.14778/3659437.3659460

Articoli sottoposti a revisione paritaria (2)

Data Lakes: A Survey of Functions and Systems

Autori: Rihan Hai; Christos Koutras; Christoph Quix; Matthias Jarke
Pubblicato in: IEEE Transactions on Knowledge and Data Engineering, 2023, ISSN 1041-4347
Editore: IEEE
DOI: 10.48550/arxiv.2106.09592

Information Systems

Autori: Joseph Giovanelli, Besim Bilalli, Alberto Abelló, Fernando Silva-Coira, Guillermo de Bernardo
Pubblicato in: Information Systems, Numero 120, 2024, ISSN 0306-4379
Editore: Elsevier Science & Technology
DOI: 10.1016/j.is.2023.102314