Abstract

Abstract
The integration of Deep Learning techniques for grapevine yield estimation has led to significant advancements in Precision Viticulture. The accurate detection and counting of berries per bunch is a critical task that can explain up to 30% of yield variability, thereby enabling improved yield estimation. This study proposes a YOLO-based approach for the automated detection and counting of visible grapevine berries, using a dataset of more than 1500 images collected over three phenological stages. The selected YOLO models performed well in both detection and counting tasks, with all models achieving high detection accuracy (G-mAP ' 0.95) and estimation of visible berries (R2 ' 0.97). Among the evaluated models, YOLOv11n exhibited the highest detection performance (F1-Score = 0.954, G-mAP = 0.962), while YOLOv10n demonstrated the most consistent and reliable counting accuracy (MAPE = 4.764, MSE = 12.203, RMSE = 3.493). Beyond overall performance, the analysis revealed that ampelographic features such as berry size, occlusion, and bunch morphology can influence accuracy, although YOLOv10n showed no significant disparities across categories. To extend the scope, a complementary analysis demonstrated a strong linear relationship (R2 = 0.860) between visible counts and the total number of berries per bunch, supporting the potential of correction models to address occlusion. By systematically evaluating model behaviour across diverse viticultural conditions and incorporating correlation with total berry counts, this study provides a deeper understanding of the robustness and limitations of Deep Learning models, offering critical insights for future applications in vineyard monitoring, yield estimation, harvest optimisation, and management. © 2026 The Authors.

Abstract

Abstract
Aquaculture is the world's fastest-growing food production sector, yet it lags behind other industries in adopting upcoming digital technologies. Challenges, such as integrating multimodal data and maintaining reliable network connectivity, have hindered the development of digital twins for monitoring aquaculture systems. This paper addresses these challenges through two main contributions: (i) a novel edge-based architecture for digital twinning that enables distributed, localized monitoring and actuation, reducing dependence on centralized systems and robust networks; and (ii) a three-stage algorithmic approach for mortality monitoring tailored to edge computing environments. This approach enables early detection of rising mortality rates using data fused from diverse sources, including directly monitored environmental parameters (e.g. pH and temperature), and novel optical biosensors that make use of lightweight computer vision and machine learning techniques for the estimation of bacterial concentrations within edge devices. The algorithmic strategy was tested in a real-world recirculating aquaculture system for Solea senegalensis, where bacterial concentration was estimated with an F1-score of 0.83 across five concentration levels using biosensor imagery. Moreover, a multimodal drift detection algorithm successfully identified abnormal data trends aligned with significant changes in input distributions, with preemptive drift signals preceding critical 7-day mortality spikes.

Abstract
This article introduces and validates the concept of DC low-voltage ride-through (DC-LVRT) for critical DC loads through the utilization of a noninverting buck-boost converter (NIBBC), acting as a front-end converter in the DC power chain for powering polymer electrolyte membrane hydrogen electrolyzers. The objective of the control strategy for the NIBBC is to maintain a stable DC bus output even during severe input voltage disturbances, preventing protective shutdowns. The control scheme employs dual voltage-loop and single current-loop PI controllers, and a new feedforward mode-transition compensator designed to inject precise and fast duty support during sudden input voltage drops. A system-oriented model of the front-end and downstream conversion stages is developed as an equivalent load impedance for the controller design. An extensive stability and robustness analysis of the proposed strategy is presented and experimentally validated on a silicon-carbide-based prototype. The system was subjected to three disturbance profiles, operating the NIBBC in buck, buck-boost, and buck-boost marginal modes. Experimental results demonstrate that the control system maintains the output voltage within 20% of its 100-V reference, with recovery within 40 ms for all cases. The feedforward controller reduces voltage dips by up to 18%. A detailed hardware versus simulation analysis quantifies the impact of real-world imperfections on control performance, underscoring the importance of such considerations for reliable DC-LVRT implementation. © 2026 The AuthorsIEEE.

Abstract
In the evolving field of machine learning, ensuring group fairness has become a critical concern, prompting the development of algorithms designed to mitigate bias in decision-making processes. Group fairness refers to the principle that a model's decisions should be equitable across different groups defined by sensitive attributes such as gender or race, ensuring that individuals from privileged groups and unprivileged groups are treated fairly and receive similar outcomes. However, achieving fairness in the presence of group-specific concept drift remains an unexplored frontier, and our research represents pioneering efforts in this regard. Group-specific concept drift refers to situations where one group experiences concept drift over time, while another does not, leading to a decrease in fairness even if accuracy (ACC) remains fairly stable. Within the framework of federated learning (FL), where clients collaboratively train models, its distributed nature further amplifies these challenges since each client can experience group-specific concept drift independently while still sharing the same underlying concept, creating a complex and dynamic environment for maintaining fairness. The most significant contribution of our research is the formalization and introduction of the problem of group-specific concept drift and its distributed counterpart, shedding light on its critical importance in the field of fairness. In addition, leveraging insights from prior research, we adapt an existing distributed concept drift adaptation algorithm to tackle group-specific distributed concept drift, which uses a multimodel approach, a local group-specific drift detection mechanism, and continuous clustering of models over time. The findings from our experiments highlight the importance of addressing group-specific concept drift and its distributed counterpart to advance fairness in machine learning.