COVID-19 X-RAY IMAGE DETECTION ALGORITHM BASED ON DEEP LEARNING

In order to enhance the ability to diagnose and distinguish COVID-19 from ordinary pneumonia, and to assist medical staff in chest X-ray detection of pneumonia patients, this paper proposes a COVID-19 X-ray image detection algorithm based on deep learning network. First of all, a model of deep learning network is set up based on VGG - 16, and then, the network structure and parameter optimization is adjusted, which makes the network model can be applied to COVID - 19 x ray imaging detection task. In the end, through adjusting the image size of the original data set, the input data meets the requirements of the deep learning network. Experimental results show that the proposed algorithm can effectively learn the characteristics of the COVID-19 X-ray image data set and accurately detect three states of COVID-19, common viral pneumonia and non-pneumonia, with a very high detection accuracy of 95.8%. © 2023 SPIE.

Engagement Estimation using Time-series Facial and Body Features in an Unstable Dataset

The global education sector has been deeply shaken by COVID-19 and forced to shift to an online teaching model. However, the lack of face-to-face communication and interaction in online learning is critical to high-quality teaching and learning. Research on engagement is a crucial part of solving this problem. Because engagement is of time-series data with an ongoing change, research datasets used for engagement analysis need a certain preprocessing method to capture time-series related engagement features. This research proposed a novel deep learning preprocessing method for improving engagement estimation using time-series facial and body information to restore traditional scenes in online learning environments. Such information includes head pose, mouth shape, eye movement, and body distance from the screen. We conducted a preliminary experiment on the DAiSEE dataset for engagement estimation. We applied skipped moving average in data preprocessing to reduce the influence of the extracted noises and oversampled the low engagement level data to balance the engaged/unengaged data. Since engagement is continuous and cannot be captured at a particular instant in time or single images, temporal video classification generally performs better than static classifiers. Therefore, we adopted long short-term memory (LSTM) and Quasi-recurrent neural networks (QRNNs)sequence models to train models and achieved the correct rate of 55.7% (LSTM) and 51.1% (QRNN) using the original key points extracted from OpenPose. Finally, we proposed the optimization structure network achieved the engagement estimation correct rate of 68.5% in proposed LSTM models and 64.2% in QRNN models. The achieved correct rate is 10% higher than the baseline in the DAiSEE dataset. © 30th International Conference on Computers in Education Conference, ICCE 2022 - Proceedings.

Impact of multi-lattice inner structures on FDM PLA 3D printed orthosis using Industry 4.0 concepts

The use of digital manufacturing for the construction of orthosis and prostheses has become common since the popularization of 3D printers and the advent of Industry 4.0. Furthermore, due to the fact that the manufacture of orthosis is interactive and for personal use, generic production is difficult. In this sense, the large-scale production of these products lacks of improvements, standardization of processes and production optimization. An aggravation of this is the recent social distance due to the COVID-19 pandemic, which makes the use of temporary orthosis made in 3D printers to have a recent growth. Parallel to this, the use of multi-lattice inner structures for internal structuring of prints has also been increasing and taking on a more consolidated form. This article aims to present the multi-lattice optimization as a solution to this problem, in order to reduce material waste while maintaining the mechanical behavior of printed parts. © 2022, The Author(s), under exclusive licence to Springer-Verlag France SAS, part of Springer Nature.

Structure and Toughness Optimization of Multi-layer Weighted Regional Logistics Network: Taking the Central Region of China as an Example

The operation of the regional logistics network is often interrupted by emergencies such as rainstorms and earthquakes, especially the COVID-19 pandemic in recent years. Therefore, it is particularly important to improve the toughness of the regional logistics network to resist the risk of emergencies. This paper firstly constructed a multi-layered weighted regional logistics network of highways and railways in the central region of China based on the gravity model, analyzed its network structure characteristics by using dominant flow and social network analysis methods, then simulated the evolution trend of network toughness under different strategies. Finally, the optimization model of logistics network structural toughness under fixed cost was proposed to explore the optimization path of network structural toughness. The results show that: (1) The economically developed cities are located in the core area of the regional logistics network, on the contrary, they are located in the edge area of the regional logistics network. (2) The network as a whole has formed a "two main and four auxiliary” distribution pattern with Zhengzhou and Wuhan as the two main cores in the north and south, and Taiyuan, Hefei, Changsha, and Nanchang as the four auxiliary cores. (3) The network has higher toughness under the node random order failure strategy than under the node specified order failure strategy, and the optimization plans improve the structural toughness of the regional logistics network by 11.68%. © 2022 SPIE.

The Policy Choice and Economic Assessment of High Emissions Industries to Achieve the Carbon Peak Target under Energy Shortage—A Case Study of Guangdong Province

In recent years, due to the rise in energy prices and the impact of COVID-19, energy shortages have led to unsafe power supply environments. High emissions industries which account for more than 58% of the carbon emissions of Guangdong Province have played an important role in achieving the carbon peak goal, alleviating social energy shortage and promoting economic growth. Controlling high emissions industries will help to adjust the industrial structure and increase renewable energy investment. Therefore, it is necessary to comprehensively evaluate the policies of energy security and the investments of high emission industries. This paper builds the ICEEH-GD (comprehensive assessment model of climate, economy, environment and health of Guangdong Province) model, designs the Energy Security scenario (ES), the Restrict High Carbon Emission Sector scenario (RHS) and the Comprehensive Policy scenario (CP), and studies the impact of limiting high emissions industries and renewable energy policies on the transformation of investment structure, macro-economy and society. The results show that under the Energy Security scenario (ES), carbon emissions will peak in 2029, with a peak of 681 million tons. Under the condition of ensuring energy security, the installed capacity of coal-fired power generation will remain unchanged from 2025 to 2035. Under the Restrict High Carbon Emission Sector scenario (RHS), the GDP will increase by 8 billion yuan compared with the ES scenario by 2035. At the same time, it can promote the whole society to increase 10,500 employment opportunities, and more investment will flow to the low emissions industries. In the Comprehensive Policy scenario (CP), although the GDP loss will reach 33 billion yuan by 2035 compared with the Energy Security scenario (ES), the transportation and service industries will participate in carbon trading by optimizing the distribution of carbon restrictions in the whole society, which will reduce the carbon cost of the whole society by more than 48%, and promote the employment growth of 104,000 people through industrial structure optimization. Therefore, the power sector should increase investment in renewable energy to ensure energy security, limit the new production capacity of high emissions industries such as cement, steel and ceramics, and increase the green transition and efficiency improvement of existing high emissions industries. © 2022 by the authors.

Decision Support System for Fast Provision of Healthcare Facilities in Response to COVID-19 Pandemic Outbreak

The Coronavirus disease 2019 (COVID-19) rapid spread across the world has unfortunately led to huge number of fatalities and large number of cases overflowing the capacity of health care facilities (HCF) causing a global public health issue. This health crisis has gotten worse with the new corona virus variant, which transmits even faster leading to critical shortage in hospital care beds and ventilators. To address this shortage, efforts are directed towards the fast construction of HCFs or conversion of non-medical facilities into temporary medical ones. However, there is a lack of structured support systems behind the decisions made. Disaster management has recently been growing in importance. It mainly addresses humanitarian logistics and emergency responses in case of disasters using various methodologies including operation research approaches. However, it did not tackle yet the emergency cases of pandemics and outbreaks. Accordingly, this paper presents the framework for a decision support system (DSS) that would help arrive at the best decision for fast provision HCFs in a timely and cost-effective manner amid health crises. The DSS consists of two modules: (1) first module determines the optimum structural system for fast construction of new HCFs considering the construction cost and duration and the associated life cycle costs, and (2) the second module determines the optimum selection of candidate non-medical facilities that can be converted into temporary HCFs considering multiple attributes. The proposed DSS will help policy makers respond quickly to pandemic crises and confine its disastrous impact on the society. © 2023, Canadian Society for Civil Engineering.

THE INFLUENCE OF WOODLOTS ON THE PHOTOCLIMATE OF GREEN AREAS AND THE QUALITY OF RECREATION

The quality of people's recreation in urban green areas (parks, municipal forests etc.) is remarkably influenced by the availability of sunlight. Especially the intended shaping of woodlots (landscape architecture) can have a very positive local impact on the sense of thermal comfort, diversified sun exposure, etc. The appropriate tree cover can regulate the degree of insolation of the site in the daily and seasonal aspects. The optimal structure of tall green forms (e.g. spatial and age structure, species composition) is the condition to achieve it. Due to the proper spatial arrangement of trees, it is possible to expose places that should be in full sun, keeping other areas in the periodic partial shade. The desired solar exposure can also be obtained by the selection of tree species (tall, low, broadly branched, columnar, etc.), the proper planting density and the distribution of trees regarding other forms of land development (topography, water system, road layout, buildings, etc.). Tree stands with a luminous, loose and airy structure have particular recreational and hygienic values. During recreation in a bright tree stand of parks and forests, the availability of sunlight has long been recognized as having great health-promoting importance due to the increased natural possibility of skin synthesis of vitamin D3 (the so-called "sun vitamin"). Also, with the favourable availability of solar radiation, the therapeutic impact of urban green areas becomes significant, especially during the COVID-19 pandemic. © 2022 Public Recreation and Landscape Protection - With Environment Hand in Hand? Proceedings of the 13th Conference. All rights reserved.

COLLABORATIVE HIGH FIDELITY AND HIGH PERFORMANCE COMPUTING-BASED MDO STRATEGIES FOR TRANSPORT AIRCRAFT DESIGN

Aviation is undergoing a transformation, fueled by the Corona pandemic, and methods to evaluate new technologies for more economical and environment-friendly flight in a timelier manner and to enable new aircraft to be designed (almost) exclusively using computers are sought after. The DLR project Victoria brings together disciplinary methods and tools of different fidelity for collaborative multidisciplinary design optimization (MDO) of long-range passenger aircraft configurations, necessitating the use of high-performance computing. Three different approaches are being followed to master complex interactions of disciplines and software aspects: an integrated aero-structural wing optimization based on high-fidelity methods, a multi-fidelity gradient-based approach capable of efficiently dealing with many design parameters and many load cases, and a many-discipline highly-parallel approach, which is a novel approach towards computationally demanding and collaboration intensive MDO. The XRF-1, an Airbus provided research aircraft configuration representing a typical long-range wide-body aircraft, is used as a common test case to demonstrate the different MDO strategies. Parametric disciplinary models are used in terms of overall aircraft design synthesis, loads analysis, flutter, structural analysis and optimization, engine design, and aircraft performance. The different MDO strategies are shown to be effective in dealing with complex, real-world MDO problems in a highly collaborative, cross-institutional design environment, involving many disciplinary groups and experts and a mix of commercial and in-house design and analysis software. © 2021 32nd Congress of the International Council of the Aeronautical Sciences, ICAS 2021. All rights reserved.

Optimization of Cross-border E-commerce Marketing Strategy During the Pandemic

Cross-border e-commerce, as a new business model, has gradually replaced the traditional trade model. However, during the COVID-19 pandemic, many companies encountered bottlenecks, mainly because products could not adapt to the rapid changes in consumption and products were out of stock due to weak logistics system. Through our observation of the current marketing situation and problems, we analyze that sellers need to enhance their adaptability and risk resistance in the pandemic environment, especially in the face of the new trends in cross-border e-commerce. Based on this, we propose a strategic optimization plan, including product optimization, sales channel optimization, brand optimization and logistics optimization. To ensure the implementation of the strategy, we designed a guaranteed roadmap, including user-demand oriented product development management, improvement of human resource management structure, optimization of operation structure and logistics supply chain enhancement. Finally, we hope this solution to be effective in a pandemic situation. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

Investigation of hybrid neo-fuzzy neural networks in the problem of pandemic forecasting

The problem of covid-19 forecasting was considered and investigated. Review of different models and methods of pandemic forecasting are presented. For short-term forecasting indicators of covid-19 the application new class neural networks – hybrid neo-fuzzy networks based on GMDH is suggested. The application of GMDH enables to construct the structure of hybrid network and accelerate the speed of learning neural weights. The experimental investigations were carried out during which the optimal parameters of hybrid network were found sliding window size, forecasting interval and network architecture. The efficiency of hybrid neo-fuzzy network in the pandemic forecasting problem was estimated and compared with Back Propagation neural network. © 2021 Copyright for this paper by its authors.