ABSTRACT
Aiming at the new coronavirus that appeared in 2019, which has caused a large number of infected patients worldwide due to its high contagiousness, in order to detect the source of infection in time and cut off the chain of transmission, we developed a new Chest X-ray (CXR) image classification algorithm with high accuracy, simple operation and fast processing for COVID-19. The algorithm is based on ConvNeXt pure convolutional neural network, we adjusted the network structure and loss function, added some new Data Augmentation methods and introduced attention mechanism. Compared with other classical convolutional neural network classification algorithms such as AlexNet, ResNet-34, ResNet-50, ResNet-101, ConvNeXt-tiny, ConvNeXt-small and ConvNeXt-base, the improved algorithm has better performance on COVID dataset.
ABSTRACT
Automobile cabin air filters have been ever-increasingly detected since the outburst of COVID-19. However, the dust sources adopted are varied due to the numerous standards. In this study, the effects of different dust sources on the test results of filtration efficiency were explored, and the causes for the different test media used in different standards were analyzed. The study results provide a reference for further improving the performance of vehicle cabin air filters. © 2021 SPIE
ABSTRACT
The COVID-19 outbreak that became a global pandemic in early 2020 is starting to affect agricultural supply chains and leading to a rapid rise in global food prices. As many grain exporting countries announced a ban on grain exports, food security issues in China have attracted a significant international attention. Based on the Suitability Distribution Model and Soybean-Cereal Constraint Model, we explored the relationship between soybean production potential and food security. We calculated that the soybean potential planting area in China is 164.3 million ha. If the outbreak prevents China from importing soybeans, soybean planting area will need to be increased by 6.9 times to satisfy the demands. In the meantime, cereal self-sufficiency rate will drop to 63.4%, which will greatly affect food security. Each additional unit of soybean production will reduce 3.9 units of cereal production, and 1% increase in the self-sufficiency rate of soybean will result in a 0.63% drop in the self-sufficiency rate of cereal. Without sacrificing the self-sufficiency rate of cereal, the self-sufficiency rate of soybean is limited to 42%. Consequently, China will still need to import more than 68% of the current import volume of soybean. Although in the short term, the outbreak will not affect food security in China, as soybean imports decrease, insufficient supply of soybeans will affect people's quality of life. To prevent the impact of the COVID-19 outbreak, China should increase soybean stocks and strengthen international cooperation. In the long term, increasing the self-sufficiency rate is a fundamental solution to solving soybean import dependency. The key to increasing soybean cultivation is by making soybean cultivation profitable and by building a sustainable soybean planting chain.
ABSTRACT
Graph is a natural representation encoding both the features of the data samples and relationships among them. Analysis with graphs is a classic topic in data mining and many techniques have been proposed in the past. In recent years, because of the rapid development of data mining and knowledge discovery, many novel graph analytics algorithms have been proposed and successfully applied in a variety of areas. The goal of this tutorial is to summarize the graph analytics algorithms developed recently and how they have been applied in healthcare. In particular, our tutorial will cover both the technical advances and the application in healthcare. On the technical aspect, we will introduce deep network embedding techniques, graph neural networks, knowledge graph construction and inference, graph generative models and graph neural ordinary differential equation models. On the healthcare side, we will introduce how these methods can be applied in predictive modeling of clinical risks (e.g., chronic disease onset, in-hospital mortality, condition exacerbation, etc.) and disease subtyping with multi-modal patient data (e.g., electronic health records, medical image and multi-omics), knowledge discovery from biomedical literature and integration with data-driven models, as well as pharmaceutical research and development (e.g., de-novo chemical compound design and optimization, patient similarity for clinical trial recruitment and pharmacovigilance). We will conclude the whole tutorial with a set of potential issues and challenges such as interpretability, fairness and security. In particular, considering the global pandemic of COVID-19, we will also summarize the existing research that have already leveraged graph analytics to help with the understanding the mechanism, transmission, treatment and prevention of COVID-19, as well as point out the available resources and potential opportunities for future research. © 2020 Owner/Author.