ABSTRACT
Having broken out in late 2019, COVID-19 has resulted in a once-in-a-century health emergency that has rapidly evolved into a global socio-economic crisis. As of March 2022, more than 450 million people were infected by the SARS-CoV-2 virus, the cause of COVID-19, resulting in more than six million deaths (WHO, Coronavirus disease (COVID-19) situation dashboard, 2022). The medical systems of many countries have been stretched to the verge of collapse and more than half of the global labor force has stood down. Not only has the pandemic doubled the number of people at risk of starvation to 270 million (Nature, 589:329-330, 2021), but it also pushed 100 million people into poverty in 2020, triggering the worst global recession since World War II (Blake and Wadhwa, 2020 year in review: the impact of COVID-19 in 12 charts, 2020), and increasing the risk of exposure to other pandemics related to ecosystem degradation (IPBES, Workshop report on biodiversity and pandemics of the intergovernmental platform on biodiversity and ecosystem services. Retrieved from Bonn, Germany, 2020;Yin et al., Geogr Sustain 2(1):68-73, 2021). The normal functioning of many organizations has also been hampered by the pandemic and disruptions to the global travel and tourism industry have been unprecedented. By way of an example, travel restrictions led to the postponement of the 2020 34th International Geographical Congress to the following year and, ultimately, the decision was made to transition to an entirely online format for the event. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.
ABSTRACT
In 2020, COVID-19 swept the world. To prevent the spread of the outbreak, it is crucial to ensure that everyone wears a mask during daily travel and in public places. However, relying on human inspection alone is inevitably negligent and there is a potential risk of cross-contamination between people. Automated detection by means of cameras and artificial intelligence becomes a technical solution. By training convolutional neural networks, image recognition can be implemented and image classification can be performed as a solution to the target mask-wearing detection problem. To this end, in this thesis, three typical convolutional neural network architectures, VGG-16, Inception V3, and DenseNet-121, are used as models based on deep learning to investigate the mask-wearing detection problem by using transfer learning ideas. By building six different models and comparing the performance of different typical network architectures on the same dataset using two transfer learning methods, feature extraction and fine-tuning, we can conclude that DenseNet-121 is the typical architecture with the best performance among the three networks, and fine-tuning has better transfer ability than feature extraction in solving the target mask wearing detection problem. © 2022 IEEE.
ABSTRACT
Objective: To investigate a SARS-CoV-2 epidemic reported in Rongcheng City, Weihai, Shandong Province. Methods: The SARS-CoV-2 nucleic acid positive patients and their close contacts were investigated, and the whole genome sequencing and genetic evolution analysis of 9 variant viruses were carried out. An infection source investigation and analysis were carried out from two sources of home and abroad, and three aspects of human, material and environment. Results: A total of 15 asymptomatic infections were reported in this epidemic, including 13 cases as employees of workshop of aquatic products processing company, with an infection rate of 21.67% (13/60). Two cases were infected people's neighbors in the same village (conjugal relation). The first six positive persons were processing workers engaged in the first process of removing squid viscera in the workshop of the company. The nucleic acid Ct value of the first time were concentrated between 15 and 29, suggesting that the virus load was high, which was suspected to be caused by one-time homologous exposure. The whole genome sequence of 9 SARS-CoV-2 strains was highly homologous, belonging to VOC/Gamma (Lineage P.1.15). No highly homologous sequences were found from previous native and imported cases in China. It was highly homologous with the six virus sequences sampled from May 5 to 26, 2021 uploaded by Chile. The infection source investigation showed that the company had used the squid raw materials captured in the ocean near Chile and Argentina from May to June 2021 over the last 14 days. Many samples of raw materials, products and their outer packages in the inventory were tested positive for nucleic acid. Conclusion: This epidemic is the first local epidemic caused by the VOC/Gamma of SARS-CoV-2 in China. It is speculated that the VOC/Gamma, which was prevalent in South America from May to June 2021, could be imported into China through frozen squid.