AI Agents and Human Insight (ENFIELD educational material)
The third ENFIELD webinar was organized in the framework of the Horizon Project ENFIELD, having taken place online on November 21, 2025.
The webinar bought together young researchers, AI developers & Data Scientists, AI professionals, members of Digital Innovation Hubs, participants from related initiatives and projects, as well as people interested in AI Agents and their interaction with Humans.
This webinar featured a series of talks focused on the development and challenges of artificial intelligence (AI), with a particular emphasis on trustworthy and sustainable AI approaches, agent interactions, and multi-agent systems.
ENFIELD Workshop on Human-Centric AI (ENFIELD educational material)
The ENFIELD Workshop on Human-Centric AI was organized in the framework of the Horizon Project ENFIELD, having taken place in Bucharest, Romania, on September, 9 2025.
The workshop served as a showcase for presenting work carried out within the ENFIELD research project. It also received contributions from other research projects, initiatives, and interdisciplinary efforts addressing challenges in human-centered artificial intelligence.
The workshop brought together researchers, practitioners, and stakeholders to share insights, methodologies, and case studies that advance human-AI collaboration, explainability, and trust.
The workshop focused on advancing research and interdisciplinary solutions for, but not limited to:
- Novel explainable AI methods for decision-making
- Methodologies for evaluating human-AI shared decision making
- Interpretable data-driven decision support systems
- Societal impacts of AI-aided decision-making
What is AI
Lecture in greek
Abstract: The stakes of this lecture are as follows: Can an ordinary person having a high school education and genuine interest understand the basic principles of Artificial Intelligence in just an one-hour lecture? If so, there is hope that she/he can comprehend the current AI Science advances and become an informed citizen that can form her/his opinion about the AI impact in her/his profession (whether they are a taxi driver, artist, manager, or anything else) and even at more broad level. If not, people have to rely on various AI “gurus” and try to sense where AI Science and Engineering is heading. Even worse, they might become technophobic: history has shown that when a society relies on fear and prejudice, it is inevitably doomed (as seen in the Middle Ages and more recently in fascist regimes).
Should you require access to the resource, please contact the author directly.
Flood region segmentation on drone images
Climate change has increased the frequency and severity of flooding, presenting significant challenges for Natural Disaster Management (NDM). Effective emergency response depends on the timely detection of flooded areas and critical objects. Advanced Deep Neural Networks (DNNs) are applied for flood region segmentation and object detection, specifically focusing on persons, vehicles, and house roofs in high-resolution drone imagery. Drones offer real-time data acquisition over extensive and inaccessible areas, capturing the dynamic nature of floods. For object detection, state-of-the-art models like YOLOv6 and DETR are utilized to accurately identify essential objects. For flood region segmentation, PSPNet and CNN-I2I are examined for their effectiveness in segmenting and mapping submerged areas. Performance metrics such as mean Average Precision (mAP) and Intersection over Union (IoU) are used to evaluate model effectiveness comprehensively. The results underscore the potential of integrating drone technology with deep learning to enhance NDM strategies, enabling rapid decision-making and reducing the impacts of flooding events.
Lecture by Evgenios Vlachos, AUTH
Privacy Protection in Natural Disaster Management
Forest fire detection and fire/burnt region segmentation on drone images
With climate change on the rise, new challenges for Natural Disaster Management (NDM) arise, leading to rapid advancements in Deep Neural Networks (DNNs), specifically in wildfire scenarios. Forest fire detection and segmentation and burnt area segmentation are critical tasks that require DNNs to achieve precise decision-making in near real-time. Given the complex and dynamic conditions of wildfires, the majority of data is sourced from drone imagery, which facilitates more efficient detection and monitoring of fire behavior. Additionally, due to the spatial variability of fire, specific metrics like image-level mean Average Precision (ImAP) can yield better results, providing better insight into the capabilities of DNNs. Computer vision methodologies can help boost results significantly by efficiently pre-processing images (e.g., HSV, RGBS). These concepts, in addition to the already powerful state-of-the-art DNNs (e.g., PIDnet, CNN I2I), can enable real-time DNN inference providing vital insight into NDM strategies.
Lecture by Matthaios-Dimitrios Tzimas