Using Social Network Sentiment Analysis and Genetic Algorithm to Improve the Stock Prediction Accuracy of the Deep Learning-Based Approach

Traditionally, most investment tools used to predict stocks are based on quantitative variables, such as finance and capital flow. With the widespread impact of the Internet, investors and investment institutions designing investment strategies are also referring to online comments and discussions. However, multiple information sources, along with uncertainties accompanying international political and economic events and the recent pandemic, have left investors concerned about information interpretation approaches that could aid investment decision-making. To this end, this study proposes a method that combines social media sentiment, genetic algorithm (GA), and deep learning to predict changes in stock prices. First, it employs a hybrid genetic algorithm (HGA) combined with machine learning to identify chip-based indicators closely related to fluctuations in stock prices and then uses them as input for long short-term memory (LSTM) to establish a prediction model. Next, this study proposes five sentiment variables to analyze PTT social media on TSMC's stock price and performs a grey relational analysis (GRA) to identify the sentiment variables most closely related to stock price fluctuations. The sentiment variables are then combined with the selected chip-based indicators as input to build the LSTM prediction model. To improve the efficiency of the LSTM analysis, this study applies the Taguchi method to optimize the hyper-parameters. The results show that the proposed method of using HGA-screened chip-based variables and social media sentiment variables as input to establish an LSTM prediction model can effectively improve the prediction accuracy of stock price fluctuations.

Identification of COVID-19 pneumonia changes on CT scan thorax: Comparison between deep learning module and radiologists' findings

Introduction: During the initial pandemic phase, rapid diagnosis of COVID-19 pneumonia is crucial for disease prevention and management. This study aimed to compare the deep learning (DL) module (AXIAL Skymind version 1.0) and radiologists' findings in detecting COVID-19 pneumonia changes in CT-Thorax. Method(s): A cross-sectional study from March to August 2021. 10 case studies HRCT thorax i.e. 9 studies confirmed COVID-19 pneumonia and a normal study. Patient IDs were removed and labelled by research series number. Data collected from their HRCT reports were standardized including their site and type of lesions (ground glass changes, consolidation and crazy-paving patterns) which were commonly found in COVID-19 pneumonia cases. Inter-observer agreement was measured using Fleiss Kappa (95% confidence interval). The radiologist's findings compared with the results generated by the DL module, Axial Skymind version 1.0. Result(s): A total of 330 CT-scan reports by 33 trained radiologists analysed. We used 70% agreement among radiologists as significant findings. However, the DL module managed to detect and report ground glass changes only and could not identify consolidation and crazy-paving patterns. Comparing the radiologists' findings and DL modules on ground glass changes, the average percentage of agreement for the site was 72.5%, ranging from 0-100%. The severity of the ground glass changes was not detected by DL modules. Conclusion(s): There was significant differences between DL modules and radiologists' findings on HRCT Thorax of COVID-19 pneumonia. The DL module needs to be strengthened and improve its accuracy and reliability before the potential use in clinical practice.

A study investigating user adoptive behavior and the continuance intention to use mobile health applications during the COVID-19 pandemic era: Evidence from the telemedicine applications utilized in Indonesia

During the COVID-19 pandemic era that began in 2020, there has been a growing trend in the literature to tackle the problem of health stress (HS) for promoting a sense of public health. In turn, this developing area of research has a high level of relevancy linked to business and economic recovery (Cvirik, 2020). Since HS has increased sharply during the COVID-19 pandemic era, there has been a need to further investigate the balance between coping with HS and the positive continuous intention to use mobile health applications (mHealth apps) among the public. This is the first study that takes the Asia-Pacific region as its case study and empirically investigates the validity of extensions based on the theories of expectation confirmation theory (ECT) (Bhattacherjee, 2001) on user continuous behavior relating to mHealth apps during the COVID-19 pandemic. Results reveal that HS as an emotion can positively affect perceived usefulness and satisfaction in relation to the continuous intention to use mHealth apps. The differences between new and frequent users are confirmed. Discussion and implications for practices are provided in the end. (c) 2022 The Authors. Published by Elsevier B.V. on behalf of College of Management, National Cheng Kung University.

Massive-scale genomic analysis reveals SARS-CoV-2 mutation characteristics and evolutionary trends

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic resulted in significant societal costs. Hence, an in-depth understanding of SARS-CoV-2 virus mutation and its evolution will help determine the direction of the COVID-19 pandemic. In this study, we identified 296,728 de novo mutations in more than 2,800,000 high-quality SARS-CoV-2 genomes. All possible factors affecting the mutation frequency of SARS-CoV-2 in human hosts were analyzed, including zinc finger antiviral proteins, sequence context, amino acid change, and translation efficiency. As a result, we proposed that when adenine (A) and tyrosine (T) bases are in the context of AM (M stands for adenine or cytosine) or TA motif, A or T base has lower mutation frequency. Furthermore, we hypothesized that translation efficiency can affect the mutation frequency of the third position of the codon by the selection, which explains why SARS-CoV-2 prefers AT3 codons usage. In addition, we found a host-specific asymmetric dinucleotide mutation frequency in the SARS-CoV-2 genome, which provides a new basis for determining the origin of the SARS-CoV-2. Finally, we summarize all possible factors affecting mutation frequency and provide insights into the mutation characteristics and evolutionary trends of SARS-CoV-2. © 2022 The Authors. mLife published by John Wiley & Sons Australia, Ltd. on behalf of Institute of Microbiology, Chinese Academy of Sciences.

A YOLOv5-based Target Detection Algorithm Design

At the beginning of 2020 Gengzi, a new coronavirus pneumonia (COVID - 19) that swept the world from the sky ravaged the land of God. In order to effectively organize the massive spread of the epidemic, this paper proposes a system that combines YOLOv5 to provide detection of faces wearing masks. The system is in a situation where one or more persons wearing masks in different scenarios can be detected. The design first uses a collection of mask face data under a variety of different wearing conditions and obtains a trained detection model using the above method to achieve the detection of whether a face is wearing a mask. The detection system can effectively detect the face mask wearing situation detected in the local picture elements, local video elements and the camera real- time shooting screen. The recognition effect of the system is verified to be 0.945, which is a significant improvement compared with other algorithms. © 2022 IEEE.

Research on the Influence of Securities Markets on Cross-Border Capital Flows Based on the DCC-MVGARCH Model

In the study of the impact of cross-border capital flows, most scholars at home and abroad focus on the method of linear time series mainly based on the vector autoregressive model (VAR), ignoring the volatility of variables in time series. In order to make up for the deficiency, the dynamic conditional correlation-generalized autoregressive conditional heteroskedasticity (DCC-GARCH) model can be used to study the nonlinear time-varying correlation between variables. With the help of Eviews12 software and the DCC-MVGARCH model, this paper studies the impact of securities markets on cross-border capital flows in China from domestic and foreign perspectives in the context of two financial crises and COVID-19. The results indicate that financial crises affect the correlation between the securities markets and cross-border capital flows. China's stock market is positively correlated with short-term capital flows and negatively correlated with long-term capital flows. Its booming bond market promotes short-term capital flows but fails to affect the long-term capital flows, and China's short-term capital flows are increasingly linked to the volatility of foreign stock markets. Therefore, it is necessary to improve the mechanism for better monitoring and analyzing cross-border capital flows, promote further development of financial supervision, and guide market players to face the securities market rationally. © 2023 SPIE.

Generative Data Augmentation for Non-IID Problem in Decentralized Clinical Machine Learning

Swarm learning (SL) is an emerging promising decentralized machine learning paradigm and has achieved high performance in clinical applications. SL solves the problem of a central structure in federated learning by combining edge computing and blockchain-based peer-to-peer network. While there are promising results in the assumption of the independent and identically distributed (IID) data across participants, SL suffers from performance degradation as the degree of the non-IID data increases. To address this problem, we propose a generative augmentation framework in swarm learning called SL-GAN, which augments the non-IID data by generating the synthetic data from participants. SL-GAN trains generators and discriminators locally, and periodically aggregation via a randomly elected coordinator in SL network. Under the standard assumptions, we theoretically prove the convergence of SL-GAN using stochastic approximations. Experimental results demonstrate that SL-GAN outperforms state-of-art methods on three real world clinical datasets including Tuberculosis, Leukemia, COVID-19. © 2022 IEEE.

Cases of ICT applications in Taiwan for smart living and youth mental well-being under COVID-19

During the COVID-19 pandemic, a number of information and communications technology (ICT) applications have enabled governments and NGOs in Taiwan to enhance social welfare and citizens' well-being. Here we focus on two selected cases so as to explain how people adopt various changes relating to ICT implementations. The first case is a public e-service, a name-based face mask distribution system and live chat bot that employs the technologies of artificial intelligence and location-based information retrieval. As the need for facial masks reached high levels, chaos occurred. This live chat bot helps citizens to be informed with the necessary information and to be able to take advantage of "smart” living. The second case deals with a positive interpersonal and life orientation training program (PILOT). PILOT is a research programme conducted by the National Taiwan University Children & Family Research Center, which is sponsored by the CTBC (China Trust Commercial Bank) charity foundation. This programme started in 2013 and includes eight series of training programmes for enhancing young people's positive mental capacity to deal with stress, social skills, making sound decisions (Stop–Think–Go Model) and communications and reducing their use of substances. In 2020, the revised version of the PILOT programme was released and carried out in many regions in Taiwan. It has assisted adolescents under 18 to adapt to the changes of the social environment and deal positively with stress and mindfulness issues. The early results are promising, and they reveal that those who are involved in the PILOT programme have improved their level of resilience and shown less problematic behaviour. The authors share the Taiwan experience in the hope of providing useful information for other societies that suffer from the pandemic at the same time. © 2023 selection and editorial matter, Antonio López Peláez, Sang-Mok Suh and Sergei Zelenev;individual chapters, the contributors.

Counselling Services and Mental Health for International Chinese College Students in Post-Pandemic Thailand

Research has proven that counselling services are essential to solving the troubles in the mental health of international Chinese students in the post-epidemic stage. Online questionnaires were implemented for about 1000 international Chinese college students from three universities in Thailand. Results showed that female junior and senior students who stayed in post-pandemic Thailand longer than others were likely to suffer from mental health disorders. In addition, in Thailand, counselling has a significant positive association with the mental health status of the students. Therefore, it is recommended in this study that Thai universities should provide more counselling services to support students in focusing on education and adjusting or adapting to the environment abroad.

Applying alinguistic approach to examination of the psychological process of Taiwan's primary leaders in the fight against Covid-19

Objectives: We used the Linguistic Inquiry and Word Count (LIWC) program to capture the psychological process of Taiwan's primary leaders in the fight against COVID-19. Methods: We analyzed the word usage of the head of the Central Epidemic Command Center in Taiwan, Chen Shih-Chung, and the mayor of Taipei City, Ko Wen-Je, in daily press conferences during the level 3 epidemic alert in 2021. Results: We found that Chen had greater certainty and confidence and focused more on epidemic projections and response. By contrast, Ko was less certain and focused more on the past. In addition, each leader demonstrated significant differences in thinking style and motivation. Chen exhibited higher-level analytical thinking and was driven by the need for affiliation, whereas Ko exhibited dynamic thinking and was driven by the need for power. Conclusion: Our study indicated that these two major leaders faced the pandemic with different focuses, thinking styles, and motivations. Future studies are encouraged to explore how word usage affects the feeling and behavior of listeners. © 2022 Chinese Public Health Association of Taiwan. All rights reserved.

Research on the Sustainable Development and Dynamic Capabilities of China's Aircraft Leasing Industry Based on System Dynamics Theory

The Boeing 737 MAX crisis and COVID-19 pandemic have seriously influenced the development of China's aircraft leasing industry in the past two years. This paper applies system dynamics theory to explore the sustainable development of China's aircraft leasing industry. It analyses the dynamic mechanism and constructs a system dynamics model. Based on China's macroeconomic data and historical data from the financial, aviation, and leasing industries, it aims to stimulate the development of China's aircraft leasing industry in the next five years. Through sensitivity analysis, this research finds that changes in GDP growth have the most obvious impact on the sustainable development of China's aircraft leasing industry. Reducing the average financing cost and the income tax rate of aircraft leasing companies, increasing their investment in talent, and controlling risk will increase the market share of China's aircraft leasing companies and promote the development of the industry. However, increasing the number of aircraft leasing companies has little effect on market share. On this basis, this paper proposes policy recommendations to promote the sustainable development of China's aircraft leasing industry.

Adult Blaschkitis following COVID-19 vaccination: a case report

A 30-year-old female presented with multiple papules on right abdomen and right lower limb for 45 days. The diagnosis of adult Blaschkitis was made. He was vaccinated the first dose of COVID-19 vaccine one month before onset of illness and the second 15 days before onset of illness. © 2022 China Journal of Leprosy and Skin Diseases. All rights reserved.

Deep Reinforcement Learning based Haptic Enhancement for Tele-Diagnosis

Tele-Diagnosis is beneficial for medical care in areas with inadequate resources, which helps control the spread of Covid-19 in the current pandemic. Most teleoperated diagnostics are dependent on humans, possibly leading to cognitive issue caused by distanced communication. In this paper, we propose a local haptic enhancement framework to facilitate the remote palpation. The deep deterministic policy gradient (DDPG) algorithm is exploited to compensate for signal transmission due to latency, allowing human to operate without the sense of delay. With the help of weighted recursive least squares (WRLS) method, the interactive force can be estimated on the patient's side despite the lack of force sensors. Fuzzy inference is used to diagnose and classify the extent of disease based on the estimated force and motion state on the remote side, thereby leveraging the remote sensory information to conduct autonomous reasoning. Finally, the final diagnosis is derived by performing minimum risk Bayesian decision based on local and remote inference results. Comparative simulation results have validated the superior performances of the proposed scheme. © 2022 IEEE.

Epilogue: whither low-cost aviation

As an epilogue to the book, this closing chapter questions the futures of low-cost aviation in a (post-)pandemic world. It traces new (and ongoing) developments in the sector amid the COVID-19 crisis. The chapter notes the resilience of the low-cost carriers (LCCs) amid an unprecedented downturn and also highlights the reinforced dynamics of automation, securitization, and tensions affecting cost-conscious travel experiences. In addition to the contributions made by the various authors of the book, the chapter further reviews some promising research directions for the future. These include the sociocultural characteristics of low-cost aviation in the Global South;the labor behind LCC operations;“new” mobility streams such as youth travel, and long-distance commuting;and, finally, uses of information and communication technologies and the mobile phone in LCC (sub)cultures. This epilogue attests to the idea that they are countless stories yet to be told about how LCCs have caused people to turn their eyes to the sky. © 2022 Elsevier Inc. All rights reserved.

Constants and Changes in Russian Ideology in 2021

Russia's 2021 Duma elections after the sanctions from Europe and the coronavirus pandemic were held in context of protest sentiments. The Lower House of Parliament shifted from four to five factions for the first time since 1999, and in the context of recurrent outbreaks of a pandemic, the Russian public spent a year under the influence of the controversial legal arguments about the status of foreign media and the use of QR codes. It took place in the context of the 30th anniversary of the collapse of the Soviet Union.

Genomic and phylogenetic analysis of the ORF7b gene from a Chinese feline infectious peritonitis virus isolate

FCoV viruses exhibit great genetic diversity, leading to the presence of FIPV-causing variants. Current molecular evolution analysis and genetic variation studies of FCoV in China are predominately focused on gene encoding the spike protein or other structural proteins, while few studies have evaluated genetic variations in nonstructural FCoV genes, which can play an important role in disease pathogenesis. In this study, the gene encoding the open reading frame (ORF) 7b nonstructural FCoV protein of the Chinese Fujian strain FJLY20201 was amplified from the ascitic fluid of a Chinese domestic cat infected with FIPV and compared with ORF 7b from previously published FCoV strains. Multiple sequence alignment revealed that FJLY20201 exhibited high identity with other Chinese FCoV strains. Phylogenetic analyses indicated that the Chinese strains did not differentiate between type I and type II serotypes of FCoV based on S proteins. In addition, they formed clades and differed genetically from strains originating outside China. This study provides the molecular epidemiology data about the ORF 7b genes of FCoV strains in China. Our results show that the identity of ORF 7b genes was closer between the Chinese isolates, and suggest that variation in ORF 7b is more dependent on geographical origin.

Orally delivered perilla (Perilla frutescens) leaf extract effectively inhibits SARS-CoV-2 infection in a Syrian hamster model

On analyzing the results of cell-based assays, we have previously shown that perilla (Perilla frutescens) leaf extract (PLE), a food supplement and orally deliverable traditional Chinese medicine approved by the Taiwan Food and Drug Administration, effectively inhibits SARS-CoV-2 by directly targeting virions. PLE was also found to modulate virus-induced cytokine expression levels. In this study, we explored the anti-SARS-CoV-2 activity of PLE in a hamster model by examining viral loads and virus-induced immunopathology in lung tissues. Experimental animals were intranasally challenged with different SARS-CoV-2 doses. Jugular blood samples and lung tissue specimens were obtained in the acute disease stage (3-4 post-infection days). As expected, SARS-CoV-2 induced lung inflammation and hemorrhagic effusions in the alveoli and perivascular areas;additionally, it increased the expression of several immune markers of lung injury - including lung Ki67-positive cells, Iba-1-positive macrophages, and myeloperoxidase-positive neutrophils. Virus-induced lung alterations were significantly attenuated by orally administered PLE. In addition, pretreatment of hamsters with PLE significantly reduced viral loads and immune marker expression. A purified active fraction of PLE was found to confer higher antiviral protection. Notably, PLE prevented SARS-CoV-2-induced increase in serum markers of liver and kidney function as well as the decrease in serum high-density lipoprotein and total cholesterol levels in a dose-dependent fashion. Differently from lung pathology, monitoring of serum biomarkers in Syrian hamsters may allow a more humane assessment of the novel drugs with potential anti-SARS-CoV-2 activity. Our results expand prior research by confirming that PLE may exert an in vivo therapeutic activity against SARS-CoV-2 by attenuating viral loads and lung tissue inflammation, which may pave the way for future clinical applications.

University Students' Daily Activities and Physical Fitness during COVID-19 Pandemic

This study aims to evaluate university students' daily activities and the effect of physical activity on physical fitness, especially during the COVID-19 pandemic. This research used comparative and correlational research methods. Thirty research samples consisted of 13 junior year university students and 17 senior year university students were selected by the purposive sampling method. Every student was monitored for their daily activities for one week and categorized into sports, college, organization, and other activities. Physical fitness was measured using the MFT test to measure the VO2Max in ml/kg/min units. The data analysis results showed no significant difference between junior and senior semester students in VO2Max, physical exercise, organizational activities, lecture activities, sleeping, and other activities. There was a significant difference in VO2Max and physical exercises (sig < 0.05) between genders. Male students spent more time exercising (17.87 ± 11.1) than female students (10.80 ± 6.04). Furthermore, male students had a higher average VO2Max (42.38 ± 7.53) than female students (29.36 ± 6.07). Based on the regression analysis results, there is a significant value between physical exercises and sleeping toward VO2Max capacity (sig. < 0.05). © 2022 by authors.