Abstract
Face recognition technology, despite its advancements and increasing accuracy, still presents significant challenges in explainability and ethical concerns, especially when applied in sensitive domains such as surveillance, law enforcement, and access control. The opaque nature of deep learning models jeopardises transparency, bias, and user trust. Concurrently, the proliferation of web applications presents a unique opportunity to develop accessible and interactive tools for demonstrating and analysing these complex systems. These tools can facilitate model decision exploration with various images, aiding in bias mitigation or enhancing users’ trust by allowing them to see the model in action and understand its reasoning. We propose an explainable face recognition web application designed to support enrolment, identification, authentication, and verification while providing visual explanations through pixel-wise importance maps to clarify the model’s decision-making process. The system is built in compliance with the European Union General Data Protection Regulation, ensuring data privacy and user control over personal information. The application is also designed for scalability, capable of efficiently managing large datasets. Load tests conducted on databases containing up to 1,000,000 images confirm its efficiency. This scalability ensures robust performance and a seamless user experience even with database growth. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Abstract

Abstract
Optical Wireless Communications (OWC) has recently emerged as a viable alternative to radio-frequency technology, especially for the Internet of Things (IoT) domain. However, current simulation tools primarily focus on physical layer modelling, ignoring network-level issues and energy-constrained environments. This paper presents an energy-aware OWC module for ns-3 that addresses these limitations. The module includes specific PHY and MAC layers and integrates an energy model, a mobility model, and models of monochromatic transceivers and photodetectors, supporting both visible light and infrared (IR) communications. Verification against MATLAB simulations confirms the accuracy of our implementation. Additionally, mobility tests demonstrate that an energy-restricted end device transmitting via IR can maintain a stable connection with a gateway at distances up to 2.5 m, provided the SNR is above 10 dB. These results confirm the capabilities of our module and its potential to facilitate the development of energy-efficient OWC-based IoT systems. © 2025 IEEE.

Abstract

Abstract
Non-formal education seeks to address the limitations of formal education that do not reach all communities and do not provide all new competencies and capabilities that are essential for the integrated development of communities. The role of non-formal education becomes even more relevant in the context of developing countries where significant asymmetries in access to education emerge. This study adopts the Solutions Story Tracker provided by the Solutions Journalism Network to identify and explore solutions based on journalism stories in the non-formal education field. A total of 256 stories are identified and categorized into 14 dimensions. The findings reveal that practical, participatory, and volunteering dimensions are the three most common dimensions in these non-formal education initiatives. Furthermore, two emerging dimensions related to empowerment and sustainability are identified, allowing us to extend the theoretical knowledge in the non-formal education field. These conclusions are relevant for establishing public policies that can involve greater participation by local communities in non-formal education and for addressing sustainability challenges through bottom-up initiatives.

Abstract
Yield forecasting is of immeasurable value in modern viticulture to optimize harvest scheduling and quality management. The number of inflorescences and flowers per vine is one of the main components and their assessment serves as an early predictor, which can explain up to 85-90% of yield variability. This study introduces a sophisticated framework that integrates the benchmark of different advanced deep learning and classic image processing to automate the segmentation of grapevine inflorescences and the detection of single flowers, to achieve precise, early, and non-invasive yield predictions in viticulture. The YOLOv8n model achieved superior performance in localizing inflorescences ( F1-Score (Box) = 95.9%) and detecting individual flowers (F1-Score = 91.4%), while the YOLOv5n model excelled in the segmentation task ( F1-Score (Mask) = 98.6%). The models demonstrated a strong correlation (R-2 > 90.0%) between detected and visible flowers in inflorescences. A statistical analysis confirmed the robustness of the framework, with the YOLOv8 model once again standing out, showing no significant differences in error rates across diverse grapevine morphologies and varieties, ensuring wide applicability. The results demonstrate that these models can significantly improve the accuracy of early yield predictions, offering a noninvasive, scalable solution for Precision Viticulture. The findings underscore the potential for Computer Vision technology to enhance vineyard management practices, leading to better resource allocation and improved crop quality.