Abstract
Manual vineyard yield estimation approaches are easy to use and can provide relevant information at early stages of plant development. However, such methods are subject to spatial and temporal variability as they are sample-based and dependent on historical data. The present work aims at comparing the accuracy of a new non-invasive and multicultivar, image-based yield estimation approach with a manual method. Non-disturbed grapevine images were collected from six cultivars, at three vineyard plots in Portugal, at the very beginning of veraison, in a total of 213 images. A stepwise regression model was used to select the most appropriate set of variables to predict the yield. A combination of derived variables was obtained that included visible bunch area, estimated total bunch area, perimeter, visible berry number and bunch compactness. The model achieved an R-2 = 0.86 on the validation set. The image-based yield estimates outperformed manual ones on five out of six cultivar data sets, with most estimates achieving absolute errors below 10%. Higher errors were observed on vines with denser canopies. The studied approach has the potential to be fully automated and used across whole vineyards while being able to surpass most bunch occlusions by leaves.

Abstract
This study investigates the potential of dynamically adjusting WIP cap levels to maximize the throughput (TH) performance and minimize work in process (WIP), according to real-time system state arising from process variability associated with low volume and high-variety production systems. Using an innovative approach based on state-of-the-art deep reinforcement learning (proximal policy optimization algorithm), we attain WIP reductions of up to 50% and 30%, with practically no losses in throughput, against pure-push systems and the statistical throughput control method (STC), respectively. An exploratory study based on simulation experiments was performed to provide support to our research. The reinforcement learning agent's performance was shown to be robust to variability changes within the production systems.

Abstract
The George B. Moody PhysioNet Challenge 2022 explored the detection of abnormal heart function from phonocardiogram (PCG) recordings. Although ultrasound imaging is becoming more common for investigating heart defects, the PCG still has the potential to assist with rapid and low-cost screening, and the automated annotation of PCG recordings has the potential to further improve access. Therefore, for this Challenge, we asked participants to design working, open-source algorithms that use PCG recordings to identify heart murmurs and clinical outcomes. This Challenge makes several innovations. First, we sourced 5272 PCG recordings from 1568 patients in Brazil, providing high-quality data for an underrepresented population. Second, we required the Challenge teams to submit working code for training and running their models, improving the reproducibility and reusability of the algorithms. Third, we devised a cost-based evaluation metric that reflects the costs of screening, treatment, and diagnostic errors, facilitating the development of more clinically relevant algorithms. A total of 87 teams submitted 779 algorithms during the Challenge. These algorithms represent a diversity of approaches from both academia and industry for detecting abnormal cardiac function from PCG recordings. © 2022 Creative Commons.

Abstract
The evaluation of the diffusion properties of optical clearing agents in biological tissues, which are necessary to characterize the transparency mechanisms, has been traditionally made using ex vivo tissues. With the objective of performing such evaluation in vivo, this study was made to evaluate and compare those properties for propylene glycol in skeletal muscle, as obtained with the collimated transmittance and diffuse reflectance kinetics. The diffusion time and the diffusion coefficient of propylene glycol in the muscle that were calculated both from transmittance and reflectance kinetics presented a deviation of 0.8%, a result that opens the possibility to use such a method in vivo. © 2022 IEEE.

Abstract
Application execution requests in cloud architecture and fog paradigm are generally heterogeneous in terms of contexts at the device and application level. The scheduling of requests in these architectures is an optimization problem with multiple constraints. Despite numerous efforts, task scheduling in these architectures and paradigms still presents some enticing challenges that make us question how tasks are routed between different physical devices, fog, and cloud nodes. The fog is defined as an extension of the cloud, which provides processing, storage, and network services near the edge network, and due to the density and heterogeneity of devices, the scheduling is very complex, and, in the literature, we still find few studies. Trying to bring innovative contributions in these areas, in this paper, we propose a solution to the context-aware task-scheduling problem for fog paradigm. In our proposal, different context parameters are normalized through Min-Max normalization, requisition priorities are defined through the application of the Multiple Linear Regression (MLR) technique and scheduling is performed using Multi-Objective Non-Linear Programming Optimization (MONLIP) technique. The results obtained from simulations in the iFogSim toolkit, show that our proposal performs better compared to the non-context-aware proposals.

Abstract
Building rehabilitation is a reality, and all phases of rehabilitation work need to be efficient and sustainable. Current procedures for assessing construction conditions are time-consuming, laborious and expensive and pose threats to the health and safety of engineers, especially when inspecting locations not easy to access. In an initial step, a survey of the condition of the building is carried out, which subsequently implies the elaboration of a report of existing pathologies, intervention solutions and associated costs. This survey involves an inspection of the site (through photographs and videos). This work aims to detect and locate cracks defects in images of painted facade walls of buildings. A VGG16 pre-trained model was evaluated first on a public database with cracked and not cracked concrete surfaces and then on a private database of images of painted building facades with and without cracks. The predicted activation maps were analysed with Grad-CAM methods to validate the models’ prediction. The proposed model achieved 99% accuracy on the concrete public dataset and 78% on the building's facade private dataset. The limitations and the future works are identified. © 2022, University of Cantabria - Building Technology R&D Group. All rights reserved.