RESEARCH PROJECTS
STRAWBERRIES
STRengthening Ai With BettEr data and tRustwoRthIer modElS
The STRAWBERRIES project aims to tackle key challenges in developing AI-based predictive models by enhancing their performance, reliability, and trustworthiness. It focuses on improving data quality and leveraging weak supervision and generative AI to address data sparsity. The project also emphasizes advancing algorithms to handle large datasets and complex interactions, while prioritizing robustness, fairness, explainability, and traceability. These efforts aim to create more effective and trustworthy models for real-world applications, with a strong emphasis on solving practical problems where the research group has prior experience.
Status: In progress
Funding entity: Spanish Ministry of Science and Innovation
Duration: December 2024 – December 2027
MA3MP
ADVANCED MACHINE LEARNING MODELS IN PREDICTIVE MAINTENANCE
The MA3MP project aims to advance predictive maintenance, a critical application of AI techniques in Industry 4.0 with significant economic and competitive implications for businesses. Its objective is to develop advanced machine learning models that are less data-intensive, more accurate, explainable, and interpretable. Key research areas include advanced data preprocessing, anomaly detection, event prediction, and explainable models. To validate the developed models, real-world case studies will address industrial challenges, such as maintenance for high-tonnage trucks and CNC milling machines, with data provided by collaborating organizations like the Spanish Army and Grupo Sevilla Control.
Status: In progress
Funding entity: Regional Government of Andalucia
Duration: December 2022 – December 2025
PreMAD
PREDICTIVE MAINTENANCE STRATEGIES BASED ON ANOMALY DETECTION: FRAMEWORK, CHALLENGES AND PROOFS OF CONCEPT
The PreMAD project aims to advance anomaly detection by addressing three key objectives. First, it focuses on developing new algorithms to tackle open challenges, including deep learning approaches, model interpretability, false positive mitigation, improved evaluation metrics, and solutions for big data and distributed environments. Second, it plans to design and implement a state-of-the-art software tool that integrates these advancements and serves as a foundation for developing new applications. Finally, the project will create a predictive maintenance tool as a proof of concept, applying it to real-world scenarios like high-tonnage transport trucks and naval ship engines.
Status: In progress
Funding entity: Spanish Ministry of Science and Innovation
Duration: December 2022 – November 2025
INTENSE
IMPROVING DATA SCIENCE USER’S EXPERIENCE WITH COMPUTATIONAL INTELLIGENCE
The aim of INTENSE project is to develop new methods and techniques to improve the experience of Data Science users, meaning both professionals in this field and data consumers who make use of the available tools to solve their knowledge discovery problems.
Status: In progress
Funding entity: Spanish Ministry of Science and Innovation
Duration: September 2021 – August 2024
MANPREDIC
MANTENIMIENTO PREDICTIVO PARA PLATAFORMAS TERRESTRES
The main objective of the MANPREDIC project is the development of a system that supports the predictive maintenance of land platforms of the army.
Status: Finished
Funding entity: Spanish Ministry of Defence
Duration: December 2019 – December 2021
Budget: 478,957 €
EMERALD
EMERGING TRENDS IN DATA ANALYSIS
Project EMERalD (EMERging trends in Data analysis) has as main objective to develop data analysis methodologies/proposals for solving complex problems in biomedicine and education.
Status: Finished
Funding entity: Spanish Ministry of Economy and Competitiveness
Duration: January 2018 – December 2020
Budget: 74,400 €
MARFIL
MINING DATA WITH MORE FLEXIBLE REPRESENTATIONS
Project MARFIL (Mining data with more flexible representations) has as objective to develop novel approaches for knowledge extraction in those contexts demanding some additional flexibility in data representation.
Status: Finished
Funding entity: Spanish Ministry of Economy and Competitiveness
Duration: January 2015 – December 2017
Budget: 69,900 €
iNsPIrED
NEW CHALLENGES IN KNOWLEDGE DISCOVERY: A GENETIC PROGRAMMING APPROACH
The Project iNsPIrED (New Problems In knowlEdge Discovery) has the main objective of developing new knowledge discovery methodologies using genetic programming and other evolutionary computation approaches, as well as their application in several real-world problems.
Status: Finished
Funding entity: Spanish Ministry of Economy and Competitiveness
Duration: January 2012 – December 2014
Budget: 63,526 €
KEEL-CTNC
KEEL: CURRENT TRENDS AND NEW CHALLENGES
The project KEEL-CTNC focuses on the extraction of knowledge based on genetic and evolutionary learning algorithms. KEEL integrates the construction and use of specific modules collecting the algorithms that make the state of the art on specific topics, such as module for fuzzy systems, learning algorithms module from low quality data (data vague and incomplete), unbalanced dataset learning algorithms, etc.
Status: Finished
Funding entity: Spanish Ministry of Economy and Competitiveness
Duration: January 2009 – December 2011
Budget: 112,530 €
ATECSE
APPLICATION OF KNOWLEDGE EXTRACTION TECHNIQUES OVER EDUCATIONAL ENVIRONMENTS
ATECSE project (Application of Knowledge Extraction Techniques over Educational Environments) is located in the context of the research area called Educational Data Mining (EDM) and consist of applying knowledge extraction techniques over the data generated/provided by educational domains. Our objective is to obtain new useful knowledge/information to the implicated agents/users (mainly, instructors/teacher and academic authorities).
Status: Finished
Funding entity: Regional Government of Andalucia
Duration: January 2009 – January 2013
Budget: 172,743.68 €
RESEARCH CONTRACTS
dreaMS, A telehealth tool for monitoring and treatment of Multiple Sclerosis patients (dreaMS)
Healios, UCO, IMIBIC
Multiple Sclerosis (MS) is one of the most common neurological disorders, which progression over 20 years leads to high patient disability and death. Detection of disease progression is unreliable with existing tool and leave patients at great risk of increased disability. dreaMS aims to support precise diagnosis and treatment optimisation by developing a new type of biomarkers through the use of consumer devices and data science. The solution will result in improved patient outcomes and well-being and new health economic benefits for the health system.
Status: Active
Duration: 11/7/2019 – 11/9/2020
Budget: 174,700 €
Incorporation of Educational Data Mining Processes into the different e-learning applications of the Santillana Group: application of predictive models in production and comparison of educational centres.
Santillana Global
Status: Finished
Duration: 01/01/2016 – 01/01/2017
Budget: 40,000 €
Incorporation of Educational Data Mining Processes into the different e-learning applications of the Santillana Group: design and implementation.
Santillana Global
Status: Finished
Duration: 20/05/2015 – 20/11/2015
Budget: 24,000 €
Incorporation of Educational Data Mining Processes into the different e-learning applications of the Santillana Group: analysis and preparation of information.
Santillana Global
Status: Finished
Duration: 27/11/2014 – 27/05/2015
Budget: 18,000 €