About the  IDEA Lab

The IDEA Lab focuses on advancing research in intelligent data-driven systems. We aim to investigate intellectual challenges and contribute to developing state-of-the-art technologies in knowledge representation, artificial intelligence, and data analytics. The primary research objective of the lab is to design systems that can extract and represent information, as well as analyse and interpret data sets, to support informed decision-making, recommendations, and predictive analytics. The main goal of the IDEA Lab is to improve the effectiveness and efficiency of applications like knowledge extraction, recommender and decision support systems, and domain-specific applications based on intelligent agents by integrating complex data-driven methodologies.

Research 

Research Focus:

Knowledge Representation Methods and Techniques: Our research focuses on the development and enhancement of advanced knowledge representation methods and techniques. Specifically, we concentrate on the construction of knowledge models from text, enabling semantic annotation and precise information extraction. Our objective is to improve document retrieval by content, thereby ensuring the accessibility of relevant information. Utilizing Natural Language Processing (NLP) methodologies, we process domain-specific knowledge bases. Concurrently, Large Language Models (LLMs) are employed to generate and expand domain-specific content. This integrated strategy aims to produce comprehensive and accurate knowledge representations, supporting a broad spectrum of applications.

Recommendation Systems: Our work is dedicated to the design and implementation of recommendation systems tailored to specialized domains. The primary goal of this research is to create systems capable of providing context-dependent suggestions, thus enhancing user experience by offering relevant and timely recommendations. By integrating advanced algorithms with user behavior analysis, we aim to build systems that comprehend the unique needs and preferences of users within specific domains. This approach ensures that our recommendation systems are not only accurate but also highly pertinent to their contextual application.

Decision Support Systems: Our research is centred on the design and implementation of Decision Support Systems (DSS) that support decision-makers by providing timely, accurate, and relevant information, enhancing decision quality and efficiency. Exploiting data analytics, machine learning algorithms, and domain-specific knowledge, we create DSS that can analyse large datasets, predict outcomes, and suggest optimal actions. We combine theoretical research with practical applications, resulting in robust DSS solutions that support a wide array of decision-making processes.

Application of Artificial Intelligence Techniques to Specialized Domains: Our laboratory applies state-of-the-art Artificial Intelligence (AI) techniques across a range of specialized domains, including environmental science, agrifood, and Industry 4.0. In the environmental sector, we develop AI-driven solutions for monitoring and predicting ecosystem changes. Within the agrifood domain, our AI applications aim to optimize agricultural practices and enhance food security. For Industry 4.0, we leverage AI to improve manufacturing processes and operational efficiency. Our interdisciplinary approach ensures that our AI solutions are both innovative and impactful, addressing specific challenges within each field.

People  @ IDEA LAB

Principal Investigator  

 Flora Amato Professor at DIETI UNINA  

Faculty  

 Walter Balzano Researcher at DIETI UNINA   

 Vincenzo Moscato Professor at DIETI UNINA  

Research Fellow  

  Mattia Fonisto, Ph.D. in AI Artificial Intelligence

 Marcello Pelosi, Data Science

Ph.D. Students  

    Claudio Ciano Ph.D. in Information Technology and Electrical Engineering  

 Egidia Cirillo National Ph.D. AI Artificial Intelligence - Agrifood and Environment area

  Luigi Laezza, Ph.D. in Computational and Quantitative Biology 

 Alberto Moccardi National PhD AI Artificial Intelligence - Agrifood and Environment area

 Alessandro del Prete National PhD AI Artificial Intelligence - Agrifood and Environment area

 Zahida Mashaallah National PhD AI Artificial Intelligence - Agrifood and Environment area

Projects

(selection)

PNRR Project Future Artificial Intelligence Research (FAIR) Spoke 3 Resilient AI – W.P. 3.3 “Resilient multi-task learning on the edge from incomplete and/or noisy data”, CUP E63C22002150007, funded under the PNRR (Piano Nazionale Ripresa e Resilienza – National Recovery and Resilience Plan).

European project CREA3 - Conflict Resolution with Equitative Algorithms 3. Grant number: 101160564. JUST-2023-JACC-EJUSTICE. Grant amount: 799,386.00 euro. Coordinator: Universita Degli Studi Di Napoli Federico II - The project aims to develop a system that guides European citizens in dispute resolution by suggesting in accordance with the context the steps to be followed by means of a conversational agent based on Natural Language Processing for the management of domain information and on Large Language Model for its generation. The project received a rating of 90/100 (out of a threshold of 70) and was among the first to be accepted for funding. 9/2024-9/2026. Grant amount: 799,386.00 euros. 

European project CREA2- Conflict Resolution with Equitative Algorithms 2. Grant 101046629. 040489_CREA2 European Commission - Just Project Grants. 1/6/2022-31/5/2024. The project aims to develop a platform that implements techniques for automatic resolution, based on game theory algorithms, of conflicts in asset division. Total Grant Amount: 710,838.45 euros. UNINA Grant Amount: 127,597.50 euros. 

European Project CREA, Conflict Resolution with Equitative Algorithms   Grant Agreement number: 766463 - CREA - JUST-AG- 2016/JUST-AG- 2016-05. Project aimed at developing a game theory algorithm for automatic conflict resolution in the division of assets or companies located on the European Community.

European Project IDEA - I-tools to Design and Enhance Access to justice. Grant number: 101160528. The project aims to develop an intelligent interface that either supports parties in a negotiation or suggests where mediation or court action is best. Total Grant Amount: 747,451.00 euros. UNINA Grant Amount: 152,828.00 euros. 

European Project DEUCE, Digitalising European Uncontested Claims Enforcement. The project aims to build a platform for digitizing the legal domain procedure of European enforceable title. Grant 101138437. Total Grant Amount: 771,766.00 euros. UNINA Grant Amount: 192,215.00

MISE (now MIMI) Project  AI4Heritage Prot. nr: 61521 of 13/03/2024 - AOOIncentives FCS - Agreements for innovation referred to in D.M. 31.12. 2021 and D.D. 14.11.2022. Project share 1.5 M. UNINA fund: 222,187.50 euros. Project aimed at exploring applications of Artificial Intelligence techniques in the domain of Cultural Heritage. 

MISE (now MIMI) Project  ICARUS Intelligent Contract Automation for Rethinking User Services. In collaboration with the CNR and the company Eustema SpA. Project funded under the Call for Innovation Agreements 2022 (First Window). CUP F/310105/01-03/X56 (managed fund 375,825.25 euros).

Resources

Publications

(selection)

F. Amato, Mattia Fonisto, Marco Giacalone, Carlo Sansone. “An Intelligent Conversational Agent for the Legal Domain”, Information. ISSN 2078-2489. 14:6(2023), pp. 307-320., 10.3390/info14060307.

F. Amato, Walter Balzano, Giovanni Cozzolino. “Design of a Wearable Healthcare Emergency Detection Device for Elder Persons”. Applied Sciences. ISSN 2076-3417. 12:5(2022). 10.3390/app12052345.

F. Amato, G. Cozzolino, F. Moscato, V. Moscato, and F. Xhafa, “A Model for Verification and Validation of Law Compliance of Smart Contracts in IoT Environment,” IEEE Transactions on Industrial Informatics, 2021. 17(11), 7752-7759.

F. Amato, L. Coppolino, F. Mercaldo, F. Moscato, R. Nardone, and A. Santone, “CAN-Bus Attack Detection with Deep Learning”, IEEE Transactions on Intelligent Transportation Systems, 2021. 22(8), 5081-5090

F. Amato, A. Mazzeo, V. Moscato, and A. Picariello, “A system for semantic retrieval and long-term preservation of multimedia documents in the e-government domain,” International Journal of Web and Grid Services, 2009.

F. Amato, V. Casola, G. Cozzolino, A. De Benedictis, and F. Moscato, “Exploiting Workflow Languages and Semantics for Validation of Security Policies in IoT Composite Services” IEEE Internet of Things Journal, 7.5 (2019): 4655-4665.

F. Amato, L. Coppolino, G. Cozzolino, G., Mazzeo, F. Moscato, F., R. Nardone (2021). “Enhancing random forest classification with NLP in DAMEH: A system for DAta Management in eHealth Domain”. Neurocomputing, 444, 79-91.

F. Amato, F. Moscato, V. Moscato, F. Pascale, and A. Picariello, “An agent-based approach for recommending cultural tours” Pattern Recognition Letters, Elsevier, 2020. 131, 341-347.

F. Amato, F. Moscato, and F. Xhafa, “Generation of game contents by social media analysis and MAS planning” Computers in Human Behavior, Elsevier, 2019. 100, 286-294.

F. Amato, G. Cozzolino, V. Moscato, and F. Moscato, “Analyse digital forensic evidences through a semantic-based methodology and NLP techniques” Future Generation Computer Systems, Elsevier,2019. 98: 297-307.

F. Amato , Moscato V., Picariello A., Sperli’ì G., “Extreme events management using multimedia social networks” 2019 Future Generation Computer System. Elsevier.

F. Amato, Castiglione A., De Santo A., Moscato V., Picariello A., Persia F., Sperlí G., “Recognizing human behaviours in online social networks” 2018 Computers and Security. Elsevier.

F. Amato, G. De Pietro, M. Esposito, and N. Mazzocca, “An integrated framework for securing semi-structured health records”, Knowledge-Based Systems, Elsevier, 2015, 79: 99-117.

B. Grasso, V. La Gatta, V. Moscato, G. Sperlì. “KERMIT: Knowledge-EmpoweRed Model In harmful meme deTection” (2024) Information Fusion, 106, art. no. 102269. Elsevier B.V.

V.L. Gatta, V. Moscato, M. Pennone, M. Postiglione, G. Sperli. “Music Recommendation via Hypergraph Embedding” (2023) IEEE Transactions on Neural Networks and Learning Systems, 34 (10), pp. 7887-7899. IEEE Inc.

A. Ferraro, A. Galli, V. Moscato, G. Sperlì. “Evaluating eXplainable artificial intelligence tools for hard disk drive predictive maintenance” (2023) Artificial Intelligence Review, 56 (7), pp. 7279-7314. Springer Nature.

A. De Santo, A. Galli, M. Gravina, V. Moscato, G. Sperli, “Deep Learning for HDD Health Assessment: An Application Based on LSTM” (2022) IEEE Transactions on Computers, 71 (1), pp. 69-80. IEEE Computer Society.

Laboratory Location

Università degli Studi di Napoli Federico II

Corso Nicolangelo Protopisani, 80146 Napoli NA

Building  L1, Floor 2, Room n° 2-3  

Contact Us