Rossana Caputo of European Commission - Banca popolare di Bari - Italy

Harnessing the Power of Blockchain in the Agri-Food Sector: A Meta-Analysis of Current Research and Best Practices

Blockchain is a shared and immutable data structure defined as a digital register whose entries are grouped into blocks, concatenated in chronological order, and whose integrity is guaranteed through the use of cryptography. Blockchain technology in agriculture and agribusiness has gained significant attention as a potential solution to various challenges the agri-food industry faces. In this paper, we conduct a meta-analysis exploring the various applications of Blockchain in agriculture and agribusiness. We examine the types of technology used, the specific product branches involved, and the security protocols employed.

Our findings show that several experiments and pilot projects have been conducted in the field and that Blockchain applications such as Hyperledger Fabric and Corda are ready for real-world implementation in the agri-food sector. We also identify potential benefits of using Blockchain in the agri-food sector, including enhanced product quality guarantees, improved traceability and transparency, assurance of provenance, and more equitable distribution of profits along the agri-food supply chain. Overall, our review suggests that the use of Blockchain in agriculture and agribusiness has the potential to address a range of challenges faced by these sectors and drive innovation, technical, and economic efficiencies.

Biography:

Rossana Caputo is a dynamic and compassionate author of impactful solutions in the fields of Green and Blue Economy. As the Chairperson | President of the Mediterranean Institute for Innovation, Communications and Technology (MIICT), she goes beyond traditional management to actively create and implement projects that address pressing environmental challenges with empathy and innovation.

With over 20 years of experience in project management, particularly with EU-funded Programmes, Rossana’s expertise lies in building bridges between cutting-edge technology and sustainable practices. She is a recognized expert in agrifood, smart cities, clean technologies, and circular economy, consistently authoring frameworks that leverage innovation for the greater good.

Currently, Rossana Caputo's work is focused on the VISTA (Visual Imaging for Satellite Tracking and Analysis) project based on the paper “Satellite-Based Detection of Microplastics in Aquatic Environments: A Review of Current Approaches, Challenges, and Future Directions “. She drives a vast consortium of 23 international partners. VISTA is a project to create the first end-to-end evidence pipeline for marine pollution. It fuses multi-sensor data from satellites and drones to produce calibrated maps of plastic aggregates and co-pollutants. The goal is to provide legally and regulatorily defensible evidence to address the pollution crisis. The project is a collaboration between the European Union and India to ensure global portability and reliability.

Her leadership is best exemplified by her role in authoring and directing two key projects that merge blockchain with the green and blue economies

Email:

Address:Italy

Bernard Mallia of Mediterranean Institute of Innovation, Communications and Technology (MIICT)

Traditional recommender systems either present static ranked lists or engage users in multi‑turn dialogues. Recent advances in large language models (LLMs) enable a new “one‑shot” conversational paradigm that bridges the speed of a single search query with the personalisation of dialogue‑based recommendation. This talk introduces the Guided‑Choice Framework, an architecture that integrates an LLM‑driven dialogue front‑end, a conventional recommender engine, and an uncertainty‑estimation module that decides whether a clarifying question is required – at most one per interaction.

A prototype built on the MovieLens dataset demonstrates how the system parses natural‑language intent, optionally asks a targeted clarification, retrieves candidate items, ranks them, and generates a concise, explainable recommendation. Six design principles distilled from literature and empirical evaluation that maximise information from minimal input, judicious clarification, contextual personalisation, transparent explanation, grounding in factual data, and calibrated user trust, guide the development of robust one‑shot CRS. The presentation will discuss performance insights, practical challenges such as hallucination mitigation and handling out‑of‑scope requests, as well as future research directions toward adaptive multi‑turn policies, domain‑wide applicability, and hybrid LLM‑recommender models.

Biography:

Bernard Mallia is a senior technology strategist with over two decades of experience at the intersection of Artificial Intelligence, data analytics, infrastructure, and public‑policy research. As CEO of Equinox Group, he leads a consultancy that advises private sector clients on technology and European institutions on large‑scale funding programmes (EU‑COST, Horizon Europe, CINEA).

 He also chairs the Mediterranean Institute of Innovation, Communications and Technology (MIICT) and presides over the Institute for the Research and Improvement in Social Sciences (IRISS), where he drives interdisciplinary research on AI‑enabled recommender systems, digital governance, and sustainable development. His expertise spans telecommunications, energy, transport, and IoT, complemented by a strong background in regulatory compliance (GDPR, e‑Privacy, AML) and advanced statistical modelling (time‑series forecasting, Bayesian inference).

 Bernard has authored peer‑reviewed papers on sentiment analysis, LLMs, AI‑driven recommendation, contributed to EU‑funding policy reports, and delivered workshops and keynote speeches at conferences across Africa and Europe, including the European Commission’s DG CNECT, Mediterranean Institute of Innovation events, and industry forums for telecoms and energy. His recent research delves into recommender systems, sentiment analysis, LLM hallucinations, self-driven laboratories, AI in Earth Observation datasets, and AI-driven business transformation, bridging existing knowledge gaps between traditional search and interactive systems designed efficiency, explainability, and user trust.

 Through this talk, Bernard will share practical insights from his prototype implementation, highlight design principles that can be adopted across domains (e‑commerce, media, education), and outline pathways for future research to advance one‑shot conversational AI in real‑world applications.

Email:

Address:Italy