Prevalence of depressive symptoms and associated factors during the COVID-19 pandemic: A national-based study.

BACKGROUND: Previous studies have reported that the prevalence of depression and depressive symptoms was significantly higher than that before the COVID-19 pandemic. This study aimed to explore the prevalence of depressive symptoms and evaluate the importance of influencing factors through Back Propagation Neural Network (BPNN). METHODS: Data were sourced from the psychology and behavior investigation of Chinese residents (PBICR). A total of 21,916 individuals in China were included in the current study. Multiple logistic regression was applied to preliminarily identify potential risk factors for depressive symptoms. BPNN was used to explore the order of contributing factors of depressive symptoms. RESULTS: The prevalence of depressive symptoms among the general population during the COVID-19 pandemic was 57.57 %. The top five important variables were determined based on the BPNN rank of importance: subjective sleep quality (100.00 %), loneliness (77.30 %), subjective well-being (67.90 %), stress (65.00 %), problematic internet use (51.20 %). CONCLUSIONS: The prevalence of depressive symptoms in the general population was high during the COVID-19 pandemic. The BPNN model established has significant preventive and clinical meaning to identify depressive symptoms lay theoretical foundation for individualized and targeted psychological intervention in the future.

Research on Prediction of Medical Training Effect Based on PSO-BP Neural Network

Today, the world is still suffering from Coronavirus disease 2019(COVID-19) and other disasters. Therefore, it is critical to improve medical emergency professional training, and ensuring the training effect has become the top priority. As a result, this paper builds a Particle Swarm Optimization Back Propagation(PSO-BP) neural network model using training data from the National Disaster Life Support(NDLS) course to predict NDLS training outcomes. The PSO algorithm is used to calculate the initial weights of the BP network, and the model is then trained using error back propagation to obtain the predicted value of the training effect. When compared to the standard BP neural network prediction results, experimental analysis shows that the prediction model's accuracy reaches 93.24 percentage, and the prediction accuracy is improved by 11.71 percentage. It is also better in terms of convergence speed, minimum error, global search ability, and learning smoothness. This approach is suitable for medical training effect prediction and additionally to assist the training providers in grasping trainees' learning effects in advance to improve training quality. © 2022 IEEE.

Dynamic Risk Assessment of Port Investment in Countries along the Belt and Road

China's port investments in countries along the Belt and Road are growing, while the global investment environment has deteriorated due to the Sino-US trade friction and the COVID-19 epidemic. However, the recent quantitative research on overseas port investment risk has not considered the time weight, and the related research is less. Therefore, this paper proposes a dynamic evaluation method specially for port investment risk of countries along the B&R based on entropy weight-TOPSIS and BP neural network. First, we figure out the static comprehensive risk value by entropy weight-TOPSIS method, and get the dynamic comprehensive risk value by time weighting method. Second, select three-dimensional data of 32 indicators in 18 host countries from 2010 to 2019 for empirical analysis, and obtain the risk level of each country. Lastly, compared with multiple regression, ridge regression, partial least square, we find BP neural network is the most effective means to estimate the simulation weight of evaluation indicators. The experimental result shows that, the proposed dynamic risk assessment approach for overseas port investment is able to assess risk well and can be extended to other fields. © 2022 IEEE.

A QoE Prediction Model Combining Network Parameters and Video Quality

The advent of the 5G era and the theater performing arts market woes caused by Corona Virus Disease 2019 (COVID- 2019) epidemic have accelerated the emergence and growth of the cloud performing arts business. To improve the quality of service for cloud performing arts and live performances, it is critical to develop a predictive model that accurately and timely reflects the Quality of Experience (QoE). In this paper, we first filter three of the seven recognized application layer Quality of Service (QoS) parameters that represent the input network quality in this QoE prediction model. Then one of the four different video quality evaluation methods is selected as the most effective method to represent the video quality. The purpose of combining network quality and video quality is to build a more accurate and effective QoE prediction model. © 2022 IEEE.

Evaluation and prediction of high-quality development in China: A time-spatial analysis from Hubei province

High-quality sustainable development is the common goal pursued by all countries in the world. China's high-quality development (HQD) includes five concepts of "innovation, coordination, green, opening-up, and sharing ". In this context, we established an evaluation system that included these five fundamental characteristics, used the comprehensive entropy method and BP neural network to evaluate and predict the high-quality development of Hubei Province in China, and conducted a spatiotemporal deductive analysis. The study found that: 1) Economic growth still has an important impact on HQD, for all the five main indicators, "opening-up " and "innovation " have the highest impact weights, which are 0.379 and 0.278, respectively, while the proportions of coordination and sharing are both less than 0.1. 2) There are huge differences in the level of high-quality development between regions in Hubei Province. From 2010 to 2020, the average comprehensive index of Wuhan City was greater than 0.5, which is 7 times that of the second Xiangyang City, and 46 times that of the last Shennongjia district. 3) In the past few years, the overall high-quality development of Hubei Province has shown a fluctuating upward trend. However, due to the impact of COVID-19, during the following years, its comprehensive development index will decline by an average of 5% annually, but starting from 2022, it will gradually increase. As a result, tailored and coordinated sustainable environmental policies of integrating institutional and open-market measures should be provided.

Cultivation of Positive Psychological Quality of College Students' English Learning Under the Online and Offline Teaching Mode During the Epidemic.

During the COVID-19 pandemic, long-term isolation and loneliness will cause college students' psychological fluctuations. Especially in online teaching, the lack of communication for a long time has led to a greatly reduced learning enthusiasm of college students. Therefore, this paper aims to explore the cultivation methods of the positive psychological quality of college students under the epidemic situation through the research on the positive psychology of college students' English learning. Aiming at the psychological status of college students, this paper focuses on analyzing the relationship between social support, psychological capital, and psychological health to explore more targeted ways of cultivating positive psychology. Because of the online and offline teaching mode, this paper focuses on analyzing the support environment of the online teaching mode, and analyses the current forms of English teaching. Experiments show that the direct path from psychological capital to mental health is not significant. However, the mediating path of psychological capital to mental health through social support was significant (p < 0.001). It shows that social support plays a complete mediating role, and the effect size of the mediation model reaches 49.70%. It shows that the current college students' English learning positive psychological quality is not high. In response to this, it is necessary to strengthen the tendency and ability to use social support and use the family environment to communicate more to achieve the cultivation of positive psychological quality.

The Prediction of Public Risk Perception by Internal Characteristics and External Environment: Machine Learning on Big Data.

Presently, the public's perception of risk in terms of topical social issues is mainly measured quantitively using a psychological scale, but this approach is not accurate enough for everyday data. In this paper, we explored the ways in which public risk perception can be more accurately predicted in the era of big data. We obtained internal characteristics and external environment predictor variables through a literature review, and then built our prediction model using the machine learning of a BP neural network via three steps: the calculation of the node number of the implication level, a performance test of the BP neural network, and the computation of the weight of every input node. Taking the public risk perception of the Sino-US trade friction and the COVID-19 pandemic in China as research cases, we found that, according to our tests, the node number of the implication level was 15 in terms of the Sino-US trade friction and 14 in terms of the COVID-19 pandemic. Following this, machine learning was conducted, through which we found that the R2 of the BP neural network prediction model was 0.88651 and 0.87125, respectively, for the two cases, which accurately predicted the public's risk perception of the data on a certain day, and simultaneously obtained the weight of every predictor variable in each case. In this paper, we provide comments and suggestions for building a model to predict the public's perception of topical issues.

Short-term passenger volume forecast and model analysis of Beijing public transport

The prediction of bus passenger volume is the fundamental research content of bus transfer optimization. In order to get more accurate passenger volume data and improve the utilization efficiency of urban traffic resources, according to randomness, time-varying and uncertainty of public transport passenger volume in Beijing, combined with the current new coronavirus pneumonia epidemic, this paper collected the relevant data of Beijing in the past 40 years, and predicted and analyzed them from four dimensions of public transport, urban scale and residents' economic level, taxi and sudden health events by BP neural network and regression analysis. The results show that BP neural network has good prediction results, and BP neural network is suitable for large sample size, which needs to fit or predict complex nonlinear relationships. © 2021 SPIE

Prediction of electricity consumption during epidemic period based on improved particle swarm optimization algorithm

A prediction method of electricity consumption is developed in order to address the problems of big change and imbalance in electricity consumption caused by COVID-19. In this method, BP (Back Propagation) neural network and improved particle swarm optimization (IPSO) algorithm are combined and applied. Firstly, Pearson correlation coefficient approach is utilized to conduct data correlation analysis. Then, the BP neural network prediction model is built, and IPSO algorithm is used to optimize the neural network’s initial weights and thresholds. Considering the medical data, public opinion data, policy data and historical data of electricity consumption during epidemic period, the electricity consumption of each industry in the future is predicted. The findings suggest that the proposed model performs well in terms of prediction. The Mean Absolute Percentage Error (MAPE) for each industry’s evaluation index is 1.41%, 1.70 %, and 1.37 %, respectively. Compared with other models, the prediction accuracy is higher. By exploring the predicted results of electricity consumption during epidemic period, it is hoped that a basis prediction method of electricity consumption for power grid companies in the event of a sudden outbreak will be provided.

Research on Intrusion Detection Based on Neural Network Optimized by Genetic Algorithm

With the development of 5G and the emergence of the COVID-19 epidemic, network traffic has surged, and network security has once again become a key concern. Intrusion detection system is an important means to protect network security. It can find abnormal conditions in the early stage of cyber attack. Intrusion detection is also a kind of abnormal detection in a broad sense. To improve the performance of the intrusion detection system, a cyber-attack detection method combining Borderline SMOTE and improved BP neural network (Back-Propagation neural network) is proposed. It mainly uses one-hot encoding, Borderline SMOTE data oversampling and other technologies to preprocess the data, and uses the BP neural network improved by genetic algorithm to predict cyber attacks. Finally, the model is compared with other traditional machine learning models through the core indicator recall and auxiliary indicators precision, roc curve, etc. The results show that the hybrid detection model proposed in this study has higher recall and lower running time, and performs better in intrusion detection. © 2022 IEEE.

Mathematical model establishment and simulation analysis of the spread of COVID-19 epidemic

In order to explore the intrinsic laws of the spread of COVID-19 across the globe, this paper applies partial differential equation and related theories to model and carry out theoretical analysis and numerical analysis. Firstly, by adding the free diffusion term to the traditional ordinary differential SEIRS epidemic model, the corresponding partial differential epidemic model is established. Secondly, the basic reproduction number R0 is calculated by using operator theory and spectral method, and it is testified that R0 is monotonically decreasing with respect to the diffusion coefficients of the exposed and infected individuals. Furthermore, we examine the asymptotic property of the endemic equilibrium with respect to the diffusion coefficient. Finally, we take the Canadian epidemic data as an example to carry out numerical simulation and parameter sensitivity analysis by applying difference method and BP neural network, the results show that strengthening the isolation of susceptible and exposed individuals, reducing the infection rate of infected individuals will help to better control the large-scale outbreak of the epidemic. © 2021 IEEE.

Research on warning and monitoring mechanism of economic operation of air passenger transport economic operation under the impact of COVID-19

The COVID-19 has had a great impact on the global air transport industry. This paper analyzes the impact on China's air economic operation, including the current situation, challenges and problems of the regulation mechanism. A warning system for the economic operation of air passenger transport industry is conducted. With the help of warning lights, it reflects the degree of hotness or coldness of economic operation in 2011-2020.In addition, the study establishes the BP neural network forecast model to predict the economic operation of civil aviation industry in the next three years, and proposes the specific early warning management mechanism from five aspects. The conclusion of this study provides a strong support for guiding the civil aviation industry to prevent economic operation risks and improving the anti-vulnerability and resilience of the development of China's civil aviation industry. © 2021 IEEE

Research on the Early-Warning Model of Network Public Opinion of Major Emergencies.

The rapid development of Internet in recent years has led to a proliferation of social media networks as people who can gather online to share information, knowledge, and opinions. However, the network public opinion tends to generate strongly misleading and a large number of messages can cause shocks to the public once major emergencies appear. Therefore, we need to make correct prediction regarding and timely identify a potential crisis in the early warning of network public opinion. In view of this, this study fully considers the features of development and the propagation characteristics, so as to construct a network public opinion early warning index system that includes 4 first-level indicators and 13 second-level indicators. The weight of each indicator is calculated by the "CRITIC" method, so that the comprehensive evaluation value of each time point can be obtained and the early warning level of internet public opinion can be divided. Then, the Back Propagation neural network based on Genetic Algorithm (GA-BP) is used to establish a network public opinion early warning model. Finally, the major public health emergency, COVID-19 pandemic, is taken as a case for empirical analysis. The results show that by comparing with the traditional classification methods, such as BP neural network, decision tree, random forest, support vector machine and naive Bayes, GA-BP neural network has a higher accuracy rate for early warning of network public opinion. Consequently, the index system and early warning model constructed in this study have good feasibility and can provide references for related research on internet public opinion.

An Empirical Study on the Equity Performance of China's Health Insurance Companies During the COVID-19 Pandemic-Based on Cases of Dominant Listed Companies.

The health insurance industry in China is undergoing great shocks and profound impacts induced by the worldwide COVID-19 pandemic. Taking for instance the three dominant listed companies, namely, China Life Insurance, Ping An Insurance, and Pacific Insurance, this paper investigates the equity performances of China's health insurance companies during the pandemic. We firstly construct a stock price forecasting methodology using the autoregressive integrated moving average, back propagation neural network, and long short-term memory (LSTM) neural network models. We then empirically study the stock price performances of the three listed companies and find out that the LSTM model does better than the other two based on the criteria of mean absolute error and mean square error. Finally, the above-mentioned models are used to predict the stock price performances of the three companies.

Intelligent Evaluation System of Government Emergency Management Based on BP Neural Network.

With the deepening of the global economic community, various emergencies emerge in endlessly, and the risks gradually increase. People's lives and property are threatened, which also causes a great burden on the social economy. Hitherto unknown novel coronavirus events occurred in China after the outbreak of the new coronavirus in 2019. The emergency management system is not perfect, so we start to study and improve the deficiencies of the emergency management system, but it is still difficult to effectively prevent and deal with all kinds of sudden and frequent social problems. Therefore, this paper puts forward the research of intelligent evaluation system of government emergency management based on BP neural network. In this paper, an intelligent evaluation system of government emergency management based on Internet of things environment is established, and then the system is deepened by BP neural network algorithm to avoid the interference of human factors. An objective intelligent evaluation system of government emergency management is constructed and verified by an example. We applied the system in a province, and proved that the system has strong executive ability, outstanding big data computing ability, and can objectively evaluate and analyze the government emergency management. The operability and accuracy of the intelligent evaluation system are verified. The effective evaluation content provides a new idea and method for government emergency management. And then continuously improve the emergency management measures to achieve the effect of dealing with things smoothly without panic.