Abstract
Land cover maps obtained at high spatial and temporal resolutions are necessary to support monitoring and management applications in areas with many smallholder and low-input agricultural systems, as those characteristic in Mozambique. Various regional and global land cover products based on Earth Observation data have been developed and made publicly available but their application in regions characterized by a large variety of agro-systems with a dynamic nature is limited by several constraints. Challenges in the classification of spatially heterogeneous landscapes, as in Mozambique, include the definition of the adequate spatial resolution and data input combinations for accurately mapping land cover. Therefore, several combinations of variables were tested for their suitability as input for random forest ensemble classifier aimed at mapping the spatial dynamics of smallholder agricultural landscape in Vilankulo district in Mozambique. The variables comprised spectral bands from Landsat 7 ETM+ and Landsat 8 OLI/TIRS, vegetation indices and textural features and the classification was performed within the Google Earth Engine cloud computing for the years 2012, 2015, and 2018. The study of three different years aimed at evaluating the temporal dynamics of the landscape, typically characterized by high shifting nature. For the three years, the best performing variables included three selected spectral bands and textural features extracted using a window size of 25. The classification overall accuracy was 0.94 for the year 2012, 0.98 for 2015, and 0.89 for 2018, suggesting that the produced maps are reliable. In addition, the areal statistics of the class classified as agriculture were very similar to the ground truth data as reported by the Servicos Distritais de Actividades Economicas (SDAE), with an average percentage deviation below 10%. When comparing the three years studied, the natural vegetation classes are the predominant covers while the agriculture is the most important cause of land cover changes.

Abstract
Human epidermal growth factor receptor 2 (HER2) evaluation commonly requires immunohistochemistry (IHC) tests on breast cancer tissue, in addition to the standard haematoxylin and eosin (H&E) staining tests. Additional costs and time spent on further testing might be avoided if HER2 overexpression could be effectively inferred from H&E stained slides, as a preliminary indication of the IHC result. In this paper, we propose the first method that aims to achieve this goal. The proposed method is based on multiple instance learning (MIL), using a convolutional neural network (CNN) that separately processes H&E stained slide tiles and outputs an IHC label. This CNN is pretrained on IHC stained slide tiles but does not use these data during inference/testing. H&E tiles are extracted from invasive tumour areas segmented with the HASHI algorithm. The individual tile labels are then combined to obtain a single label for the whole slide. The network was trained on slides from the HER2 Scoring Contest dataset (HER2SC) and tested on two disjoint subsets of slides from the HER2SC database and the TCGA-TCIA-BRCA (BRCA) collection. The proposed method attained83.3%classification accuracy on the HER2SC test set and 53.8% on the BRCA test set. Although further efforts should be devoted to achieving improved performance, the obtained results are promising, suggesting that it is possible to perform HER2 overexpression classification on H&E stained tissue slides.

Abstract
Phasor Measurement Unit (PMU) provides beneficial information for dynamic power system stability, analysis and control. One main application of such useful information is data-driven control. This paper is devoted to presenting an approach for optimal signal selection in PMU-based power system stabilizer (PSS) design. In this paper, for selecting the optimal input and output signals for PSS, an algorithm is suggested in which the combination of clustering the generators and the buses of the system with ICA, modal analysis and PCA techniques is used. The solution for optimal PSS input-output selection is found to increase the observability and damping of the power system. This method is simulated on a 68 buses system with 16 machines. To compare the results with the previous methods, the system is simulated and the results of two previously-developed algorithms are compared with the proposed approach. The results show the benefit of the suggested method in reducing the required signals, which lowers the number of required PMUs while the system damping is not deteriorated.

Abstract
The COVID-19 crisis exposed the vulnerability and poor resilience of the global supply chains. The objective of this research is to reflect on the possible impacts of the Coronavirus crisis in the global supply chains and provide some recommendations to overcome the present situation, offering suggestions for future research: (1) What are the contingency factors affecting Supply Chains in the complex COVID-19 operating environment? (2) How do these factors affect post-COVID-19 operating performance? After a contextualization of the COVID-19 pandemic crisis and its impacts, theoretical background on Supply Chains and Supply Chain Management are presented, and a summary of the main scenarios for the post-COVID-19 crisis are discussed. The propositions regarding the contingency factors and their impact on the Supply Chain operating performance in post-COVID-19 suggest that successful companies will focus on creating a new kind of operational performance and minimize risks. To that end, companies will aim to improve their operations' resilience (ability to resist, hold on, and recover from shocks) and accelerate the end-to-end digital transformation. Consumers will have to adapt to the contact-free economy, less low-cost supply chains, and put additional emphasis on service levels. Governments will reinforce the focus in the health sector supply chain and increase spending in the health and social care sectors. Furthermore, the longer, the more concentrated, the less transparent, and the more price sensitivity is the supply chain, the more challenging the adaptation to the new pos pandemic realities. Suggestions for future research are also provided.

Abstract

Abstract