Francesco Marcelloni

Full Professor

Artificial Intelligence Group

Dipartimento di Ingegneria dell’Informazione

Largo Lucio Lazzarino 1 – 56122 Pisa

Personal info



FRANCESCO MARCELLONI is full professor of Data Mining and Machine Learning and is the coordinator of the Research and Development Lab “Intelligent Techniques for Process Automation and Optimization” (IT2PAO) joint between the Department of Information Engineering and LogObject AG, Ambassador Haus Thurgauerstrasse 101 A, CH-8152 Opfikon – Switzerland.

He has been vice Rector for international cooperation and relations, and Erasmus Institutional coordinator at the University of Pisa from 2016 to 2022. During this period, among the various initiatives, he has promoted and coordinated the opening of the branch of the University of Pisa at Tashkent (Uzbekistan) and the membership of the University of Pisa to the Circle U. European Universities Alliance. Further, he has activated the Visiting Fellow program and re-designed the Foundation Course program.

His main research interests include explainable artificial intelligence, federated learning, data mining for big data and streaming data, sentiment analysis and opinion mining, genetic fuzzy systems, fuzzy clustering algorithms. He has co-edited three volumes, four journal special issues, and is (co-)author of a book and of more than 240 papers in international journals, books and conference proceedings.

Recently, he has received the 2021 IEEE Transactions on Fuzzy Systems Outstanding Paper award and the 2022 IEEE Computational Intelligence Magazine Outstanding Paper award. Further, thanks to the idea of Federated Learning of Explainable Artificial Intelligence Models (FEDXAI) proposed by the AI group coordinated by Francesco Marcelloni in the Hexa-X project funded by the European Commission under Horizon 2020 the University of Pisa has been awarded as Key Innovator by the European Commission's Innovation Radar. He serves as associate editor of IEEE Transactions on Fuzzy Systems (IEEE), Information Sciences (Elsevier), Soft Computing (Springer) and Sensors (MDPI), and is on the editorial board of a number of other international journals. He has been invited speaker to a number of conferences and workshops. He has coordinated various research projects funded by both public and private entities. Further, recently, he has coordinated the Erasmus+ KA2 project: “Development of Higher education institutions Internationalization Policies”, and currently he is coordinating the Erasmus+ KA2 project: “ENhanced Learning and teaching in International Virtual ENvironments – ENLIVEN”.

Research Activities

Francesco Marcelloni’s research activity has focused on the following main fields: computational intelligence and its engineering applications; data mining algorithms for big data; explainable artificial intelligence; federated learning; data mining for big data and streaming data; sentiment analysis and opinion mining, genetic fuzzy systems, fuzzy clustering algorithms; software development methods; lot and process traceability infrastructures; service recommenders; data aggregation, data compression and node localization in wireless sensor networks; expert systems; medical image processing; services for smart cities.

A list of my publications is available here

Teaching Activities

Data Mining and Machine Learning (12 ECTS) – Master of Science in Artificial Intelligence and Data Engineering

Artificial Intelligence for Cybersecurity (6 ECTS) – Master of Science in Cybersecurity


Available Master Theses


o   Federated Learning of explainable Artificial Intelligence models (within the European Union’s Horizon 2020 Research and Innovation Program, “A flagship for B5G/6G vision and intelligent fabric of technology enablers connecting human, physical, and digital worlds - Hexa-X”, European 6G flagship research)

o   Crime predicition from real data (within the IT2PAO laboratory joint between Dipartimento di Ingegneria dell’Informazione e LogObject AG)

o   Federated Learning of Artificial Intelligence Models from Streaming Data

o   Opinion Mining and Sentiment Analysis