No abstract

The scientific outcomes of the 2022 Landslide4Sense (L4S) competition organized by the Institute of Advanced Research in Artificial Intelligence (IARAI) are presented here. The objective of the competition is to automatically detect landslides based on large-scale multiple sources of satellite imagery collected globally. The 2022 L4S aims to foster interdisciplinary research on recent developments in deep learning (DL) models for the semantic segmentation task using satellite imagery. In the past few years, DL-based models have achieved performance that meets expectations on image interpretation, due to the development of convolutional neural networks (CNNs). The main objective of this article is to present the details and the bestperforming algorithms featured in this competition. The winning solutions are elaborated with state-of-the-art models like the Swin Transformer, SegFormer, and U-Net. Advanced machine learning techniques and strategies such as hard example mining, self-training, and mix-up data augmentation are also considered. Moreover, we describe the L4S benchmark data set in order to facilitate further comparisons, and report the results of the accuracy assessment online. The data is accessible on Future Development Leaderboard for future evaluation at https://www. iarai.ac.at/landslide4sense/challenge/, and researchers are invited to submit more prediction results, evaluate the accuracy of their Manuscript received XX 2021.

Summary This paper presents a complete model of collector system layout optimization for offshore wind farms, which consists of both internal and external designs. The internal design uses the algorithm of self‐tracking minimum spanning tree (ST‐MST) combined with added functions of automatic cable selecting (ACS) and cable crossing avoiding (CCA) to form a radial topology. In addition, the features above are also integrated with the use of direct current transmission in the external design, which applies a self‐designed searching method to find the optimal locations for VSC converters. The internal and external designs constitute the whole model of the offshore wind farm. More specifically, the internal connection begins with the Fuzzy C‐means clustering method to divide the farm into clusters, where each center of the cluster locates a substation connecting to the turbines belonging to it. The external connection of the wind farm considers the use of high voltage direct current, which saves a great amount of reactive power in long distance transmission. Both the internal and external designs apply ST‐MST with ACS and CCA, while the external connection is also given a higher priority as it uses the cables with larger cross sections compared with internal connection.

Candida infections have become an increasingly significant problem, mainly because of the widespread nature of Candida and drug resistance. There is an urgent need to develop new classes of drugs for the treatment of opportunistic Candida infections, especially in medically complex patients. Previous studies have confirmed that 2‐amino‐nonyl‐6‐methoxyl‐tetralin muriate (10b) possesses powerful antifungal activity in vitro against Candia albicans. To clarify the underlying action mechanism, an oligonucleotide microarray study was performed in C. albicans SC5314 without and with 10b treatment. The analytical results showed that energy metabolism‐related genes, including glycolysis‐related genes (PFK1, CDC19 and HXK2), fermentation‐related genes (PDC11, ALD5 and ADH1) and respiratory electron transport chain‐related genes (CBP3, COR1 and QCR8), were downregulated significantly. Functional analysis revealed that 10b treatment increased the generation of endogenous reactive oxygen species, and decreased mitochondrial membrane potential, ubiquinone–cytochrome c reductase (complex III) activity and intracellular ATP levels in C. albicans SC5314. Also, addition of the antioxidant ascorbic acid reduced the antifungal activity of 10b significantly. These results suggest that mitochondrial aerobic respiration shift and endogenous reactive oxygen species augmentation might contribute to the antifungal activity of 10b against C. albicans. This information may prove to be useful for the development of new strategies to treat Candida infections.

No abstract