LBLisana Berberi

Lisana Berberi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Lisana Berberi has a total of 36 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Evaluating Machine Learning Models for Trip Duration Prediction in Taxi Data

    by Lisana Berberi, Entelë Gavoçi, Senada Bushati, Fatjona Kroni

  • Exploring Federated Learning for Thermal Urban Feature Segmentation - A Comparison of Centralized and Decentralized Approaches

    by Leonhard Duda, Khadijeh Alibabaei, Elena Vollmer, Leon Klug, Valentin Kozlov, Lisana Berberi, Mishal Benz, Rebekka Volk, Juan Pedro Gutiérrez Hermosillo Muriedas, Markus Götz, et al.


  • Open Access

    Machine learning operations landscape: platforms and tools

    by Lisana Berberi, Valentin Kozlov, Giang Nguyen, Judith Sáinz-Pardo Díaz, Amanda Calatrava, Germán Moltó, Viet Tran, Álvaro López García

    As the field of machine learning advances, managing and monitoring intelligent models in production, also known as machine learning operations (MLOps), has become essential. Organizations are increasingly adopting artificial intelligence as a strategic tool, thus increasing the need for reliable, and scalable MLOps platforms. Consequently, every aspect of the machine learning life cycle, from workflow orchestration to performance monitoring, presents both challenges and opportunities that require sophisticated, flexible, and scalable technological solutions. This research addresses this demand by providing a comprehensive assessment framework of MLOps platforms highlighting the key features necessary for a robust MLOps solution. The paper examines 16 MLOps tools widely used, which revolve around capabilities within AI infrastructure management, including but not limited to experiment tracking, model deployment, and model inference. Our three-step evaluation framework starts with a feature analysis of the MLOps platforms, then GitHub stars growth assessment for adoption and prominence, and finally, a weighted scoring method to single out the most influential platforms. From this process, we derive valuable insights into the essential components of effective MLOps systems and provide a decision-making flowchart that simplifies platform selection. This framework provides hands-on guidance for organizations looking to initiate or enhance their MLOps strategies, whether they require an end-end solutions or specialized tools.


  • Open Access

    FAIR Principles Implementation in ML/AI - Findings from Skills4EOSC Delphi Study

    by Elda Osmenaj, Curtis J M Sharma, Ugo Moschini, Lisana Berberi, Valentina Pasquale

    Implementing the FAIR (Findable, Accessible, Interoperable, and Reusable) principles for scientific data management in machine learning (ML) and artificial intelligence (AI) offers numerous benefits, including higher model reliability, more collaborative research, and greater reproducibility. Despite these advantages, there is a lack of clear, practical guidelines for improving the FAIRness of ML/AI outputs, especially the models. To address this gap, Skills4EOSC Task 6.3.3a of Work Package 6: Professional Networks for Lifelong Learning conducted a Delphi Study to gather expert consensus on implementing FAIR principles in ML/AI model development. A Delphi study, involving two rounds of surveys followed by an online meeting, was conducted. In the first round, ML/AI experts from Europe and beyond rated suggested FAIR practices and proposed additional ones. The second round involved feedback and re-evaluation of these practices. The final meeting included detailed discussions on the Top 10 practices for FAIR principles implementation in ML/AI. The resulting Top 10 practices aim to provide guidelines for researchers and data management professionals to implement FAIR principles in ML/AI.

  • Open Access

    FAIR Principles Implementation in ML/AI - Findings from Skills4EOSC Delphi Study

    by Elda Osmenaj, Curtis J M Sharma, Ugo Moschini, Lisana Berberi, Valentina Pasquale

    Implementing the FAIR (Findable, Accessible, Interoperable, and Reusable) principles for scientific data management in machine learning (ML) and artificial intelligence (AI) offers numerous benefits, including higher model reliability, more collaborative research, and greater reproducibility. Despite these advantages, there is a lack of clear, practical guidelines for improving the FAIRness of ML/AI outputs, especially the models. To address this gap, Skills4EOSC Task 6.3.3a of Work Package 6: Professional Networks for Lifelong Learning conducted a Delphi Study to gather expert consensus on implementing FAIR principles in ML/AI model development. A Delphi study, involving two rounds of surveys followed by an online meeting, was conducted. In the first round, ML/AI experts from Europe and beyond rated suggested FAIR practices and proposed additional ones. The second round involved feedback and re-evaluation of these practices. The final meeting included detailed discussions on the Top 10 practices for FAIR principles implementation in ML/AI. The resulting Top 10 practices aim to provide guidelines for researchers and data management professionals to implement FAIR principles in ML/AI.


  • Open Access

    Landscape of machine learning evolution: privacy-preserving federated learning frameworks and tools

    by Giang Nguyen, Judith Sáinz-Pardo Díaz, Amanda Calatrava, Lisana Berberi, Oleksandr Lytvyn, Valentin Kozlov, Viet Tran, Germán Moltó, Álvaro López García

    Machine learning is one of the most widely used technologies in the field of Artificial Intelligence. As machine learning applications become increasingly ubiquitous, concerns about data privacy and security have also grown. The work in this paper presents a broad theoretical landscape concerning the evolution of machine learning and deep learning from centralized to distributed learning, first in relation to privacy-preserving machine learning and secondly in the area of privacy-enhancing technologies. It provides a comprehensive landscape of the synergy between distributed machine learning and privacy-enhancing technologies, with federated learning being one of the most prominent architectures. Various distributed learning approaches to privacy-aware techniques are structured in a review, followed by an in-depth description of relevant frameworks and libraries, more particularly in the context of federated learning. The paper also highlights the need for data protection and privacy addressed from different approaches, key findings in the field concerning AI applications, and advances in the development of related tools and techniques.


  • Open Access

    Personalized federated learning for improving radar based precipitation nowcasting on heterogeneous areas

    by Judith Sáinz-Pardo Díaz, María Castrillo, Juraj Bartok, Ignacio Heredia Cachá, Irina Malkin Ondík, Ivan Martynovskyi, Khadijeh Alibabaei, Lisana Berberi, Valentin Kozlov, Álvaro López García

    The increasing generation of data in different areas of life, such as the environment, highlights the need to explore new techniques for processing and exploiting data for useful purposes. In this context, artificial intelligence techniques, especially through deep learning models, are key tools to be used on the large amount of data that can be obtained, for example, from weather radars. In many cases, the information collected by these radars is not open, or belongs to different institutions, thus needing to deal with the distributed nature of this data. In this work, the applicability of a personalized federated learning architecture, which has been called adapFL, on distributed weather radar images is addressed. To this end, given a single available radar covering 400 km in diameter, the captured images are divided in such a way that they are disjointly distributed into four different federated clients. The results obtained with adapFL are analyzed in each zone, as well as in a central area covering part of the surface of each of the previously distributed areas. The ultimate goal of this work is to study the generalization capability of this type of learning technique for its extrapolation to use cases in which a representative number of radars is available, whose data can not be centralized due to technical, legal or administrative concerns. The results of this preliminary study indicate that the performance obtained in each zone with the adapFL approach allows improving the results of the federated learning approach, the individual deep learning models and the classical Continuity Tracking Radar Echoes by Correlation approach.


  • Open Access

    Personalized Federated Learning for improving radar based precipitation nowcasting on heterogeneous areas

    by Judith Sáinz-Pardo Díaz, María Castrillo, Juraj Bartok, Ignacio Heredia Cachá, Irina Malkin Ondík, Ivan Martynovskyi, Khadijeh Alibabaei, Lisana Berberi, Valentin Kozlov, Álvaro López García

    The increasing generation of data in different areas of life, such as the environment, highlights the need to explore new techniques for processing and exploiting data for useful purposes. In this context, artificial intelligence techniques, especially through deep learning models, are key tools to be used on the large amount of data that can be obtained, for example, from weather radars. In many cases, the information collected by these radars is not open, or belongs to different institutions, thus needing to deal with the distributed nature of this data. In this work, the applicability of a personalized federated learning architecture, which has been called adapFL, on distributed weather radar images is addressed. To this end, given a single available radar covering 400 km in diameter, the captured images are divided in such a way that they are disjointly distributed into four different federated clients. The results obtained with adapFL are analyzed in each zone, as well as in a central area covering part of the surface of each of the previously distributed areas. The ultimate goal of this work is to study the generalization capability of this type of learning technique for its extrapolation to use cases in which a representative number of radars is available, whose data can not be centralized due to technical, legal or administrative concerns. The results of this preliminary study indicate that the performance obtained in each zone with the adapFL approach allows improving the results of the federated learning approach, the individual deep learning models and the classical Continuity Tracking Radar Echoes by Correlation approach.

  • Open Access

    A Survey on Process Variants Meta-modelling Approaches

    by Lisana Berberi

    This paper introduces the concept of process variants in process-aware information systems (PAIS) during the design-time phase, where multiple variants of a single process must be specified. Today's organizations have to manage multiple variants of a given process, such as multiple order processes or payment processes for a specific product or service they offer. Traditional business process management tools lack in adequately capture and represent explicitly these variants. Hence, for more than a decade an array of approaches have been proposed to tackle this gap. A reference or customizable process model has been introduced to model these variants collections in a way that each variant could be derived by inserting/removing an activity according to a process context. This survey reviews current literature by providing an overview of meta-modelling approaches that have been extended in order to capture the variations of business processes. Moreover, we give a comparative analysis of these approaches based on different criteria we identified from the inventory activity, providing insights into their strengths and limitations. This paper concludes that current approaches to process variants meta-modelling provide a comprehensive view of the conceptual level of process variants and the control-flow process perspective. While some approaches go a step further by capturing variability in resources or specialization among activities/processes.

  • Developing the EOSC-Pillar RDM Training and Support Catalogue

    by Paula Oset Garcia, Lisana Berberi, Leonardo Candela, Inge Van Nieuwerburgh, Emma Lazzeri, Marie Czuray