COVID-19 Image Segmentation Algorithms Based on Conditional Generative Adversarial Network

The size and location of the lesions in CT images of novel corona virus pneumonia (COVID-19) change all the time, and the lesion areas have low contrast and blurred boundaries, resulting in difficult segmentation. To solve this problem, a COVID-19 image segmentation algorithm based on conditional generative adversarial network (CGAN) is proposed. Uses the improved DeeplabV3+ network as a generator, which enhances the extraction of multi-scale contextual features, reduces the number of network parameters and improves the training speed. A Markov discriminator with 6 fully convolutional layers is proposed instead of a common discriminator, with the aim of focusing more on the local features of the CT image. By continuously adversarial training between the generator and the discriminator, the network weights are optimised so that the final segmented image generated by the generator is infinitely close to the ground truth. On the COVID-19 CT public dataset, the area under the curve of ROC, F1-Score and dice similarity coefficient achieved 96.64%, 84.15% and 86.14% respectively. The experimental results show that the proposed algorithm is accurate and robust, and it has the possibility of becoming a safe, inexpensive, and time-saving medical assistant tool in clinical diagnosis, which provides a reference for computer-aided diagnosis. © 2022 ACM.

Different Moments Create Different Spillovers: A Study of Commodity Markets

Although the spillover effects of return and volatility risk across commodity markets have been demonstrated, evidence of extreme risk spillovers is limited. Using an autoregressive conditional density model, this study estimates the conditional skewness of nine S&P Goldman Sachs Commodity indices and then applies the Diebold-Yilmaz TVP-VAR-based approach to investigate the higher moment spillovers across commodity markets. Our findings provide evidence of extreme risk transfers from one commodity index to another. Among three energy indices including crude oil, natural gas and gasoil, crude oil transmits the most return, volatility risk and extreme risk to the agricultural indices and precious metal indices. Furthermore, our results confirm that spillovers in all three moments were significantly strengthened by extreme events such as the September 11 attacks, the global financial crisis, the food price crisis, the violent shock of international oil prices and the coronavirus disease of 2019. However, different events may have different impacts on spillovers. Finally, the results indicate that return spillover and skewness are affected by extreme events with almost the same intensity and direction for most periods.

A joint and simultaneous prediction framework of weekday and weekend daily-activity travel pattern using conditional dependency networks

Daily activity pattern (DAP) prediction models within the Activity-based Modelling paradigm are being currently developed without adequate consideration of the various interdependencies among activities within a multi-day planning horizon. We hereby propose a conditional dependency network structure based interdependent multilabel-multiclass classification framework for joint and simultaneous prediction of weekday and weekend DAP of an individual. The prime advantage of the proposed modelling framework is flexibility of application of any algorithm for parameter estimation. Random Forest Decision Tree (RFDT), eXtreme Gradient Boosting and Light Gradient Boosting Machine (LightGBM) as the base classifier and probabilistic and non-probabilistic inference approaches are explored for measuring their comparative performance to provide insights for future researchers. Several variables representing neighbourhood characteristics are also investigated as DAP de-terminants along with socio-economic characteristics of individuals for the first time.This model is estimated based on two-days (weekday and weekend) activity-travel diary of 1808 households (6521 individuals) in Bidhanangar Municipal Corporation, India. The non-probabilistic approach-based models are found to achieve higher accuracy (0.81-0.92) compared to probabilistic models (0.76 to 0.82). RFDT and LightGBM are found to be the best performers in the probabilistic and non-probabilistic frameworks respectively. External validation results show that all proposed multiday-interdependent models (80%-94%) perform better than independent models (64%-83%).This framework can be applied to other transportations planning problems like household interaction in ac-tivity generation, joint destination and mode choice. This is also one of the first attempts to investigate the determinants of DAPs of urban commuters in an emerging country like India.

Contagion between selected European indexes during the Covid-19 pandemic

The main aim of this study is to examine dynamic dependence and proof of contagion during the Covid-2019 pandemic. The empirical data are daily prices from six European indexes. The FTSE, DAX and CAC indexes represent the largest and most developed stock markets in Europe, while the Austrian ATX index represents small developed markets. The WIG and BUX indexes represent emerging European markets. This empirical study, based on the Dynamic Conditional Correlation model, which is applied to different pairs of indexes, aims to convince the reader of the increase in the correlation between the time of the pandemic (after 30 December 2019) and the period before the beginning of the pandemic. For all pairs, the mean value of the conditional correlations in the pre-Covid period was statistically below the values in the Covid period. The results indicate contagion in Europe after the outbreak of the Covid-2019 pandemic.

Preference Shifts During Health Shocks: Foreign Tourists' Expenditure-Price Elasticity Throughout the Pandemic

This study evaluates the changes in the expenditure-price elasticities of foreign tourists in the summer periods of 2019, 2020, and 2021. We first develop a theoretical characterization that combines microeconomic, loss aversion, price inequality and precautionary savings theories. Next, exploiting microdata for more than 34,000 foreign tourists visiting Spain, we estimate OLS and quantile regressions to empirically examine the expenditure elasticities with respect to the prices of transport services, leisure activities and bars and restaurants at the destination (17 regions). We find that (i) the expenditure-price elasticity of transportation (leisure activities) increases (decreases) during the pandemic, whereas that of bars and restaurants remains unchanged, (ii) foreign tourists are comparatively less expenditure-price elastic at high expenditure levels in transportation and bars and restaurants, and (iii) expenditure-price elasticities are highly heterogeneous depending on the origin country. Managerial and theoretical implications of the findings for firms' pricing strategies are discussed.

The relationship between crude oil futures and exchange rates in the context of the Covid-19 shock: a tale of two markets

We examine the high-frequency intraday return and volatility transmission between crude oil futures prices and exchange rates during the 2020 Covid-19 pandemic in the context of two markets: the newly established renminbi-denominated Shanghai International Energy Exchange in China and the US-dollar-denominated Brent market in the United Kingdom. By controlling for the influence of the stock markets, our findings reveal significant disparities in return linkages, yet fairly comparable volatility transmission patterns. The International Energy Exchange shows no return linkages with exchange rates except before the shock, while Brent consistently shows return spillovers from crude oil futures prices to exchange rates. In both markets, the volatility spillovers from exchange rates to crude oil futures prices are unidirectional prior to the shock but become bidirectional as a result of the shock. Nevertheless, both the return and volatility spillover patterns in China resemble those in the United Kingdom when utilizing offshore instead of onshore exchange rates. Such similarities in return and volatility spillovers can also be observed during the 2022 Covid-19 shock that emerged in Shanghai. These findings have significant practical implications. © Infopro Digital Limited 2023.

Achieving sustainability: Determinants of conscious green purchasing behavior during the COVID-19 pandemic.

The COVID-19 pandemic has spread worldwide, resulting in crises in public health and sustainable development. Aimed at understanding the determinants of conscious green purchasing behavior (GPB), this paper developed a comprehensive framework linking the moderating effect of negative environmental affective reactions (NEAR) to COVID-19 based on the S-O-R paradigm. Using randomly selected urban residents from China's Yangtze River Delta and Bohai Rim regions, the empirical study was conducted using 559 valid responses. The results show that media and peers are the major social forces activating altruistic and egoistic motivations, while family influence was not significant. Dual motivations significantly mediated the relationships of unconditional and conditional GPB with media exposure and peer influence. Contrary to expectations, NEAR negatively moderated the formation process of conscious GPB. The findings indicate that the influence of peers on conscious GPB through dual motivations is stronger compared to media. Negative affective reactions to COVID-19 were also found to inhibit the impact of peer influence on altruistic and egoistic motivations, as well as the path of altruistic motivation on unconditional GPB. The results of this study have important theoretical and practical implications for enterprise marketing and environmental campaigns, and narrowing the green attitude-behavior gap.

Three-way investment decisions during the epidemic with Choquet-based bi-projection method

The outbreak of epidemic has had a big impact on the investment market of China. Facing the turbulence in the investment market, many enterprises find it difficult to judge the development prospects of investment projects and make the right investment decisions. The three-way decisions offer a novel study perspective to solve this problem. Then the developed model is applied to select the investment projects. Firstly, some relevant attributes of the project are described with the double hierarchy hesitant fuzzy linguistic term sets. And a double hierarchy hesitant fuzzy linguistic information system is constructed for each project. Secondly, the weights of attributes are determined with the Choquet integral method. And the closeness degree calculated by Choquet-based bi-projection method is taken as the conditional probability that the project will be profitable. Next, considering the influence of the bounded rationality of decision makers, the threshold parameters are calculated based on prospect theory. Finally, the decision results about investment projects during four stages are deduced based on the principle of maximum-utility, which demonstrates the practicability and effectiveness of the proposed model.

A risk-averse two-stage stochastic programming model for a joint multi-item capacitated line balancing and lot-sizing problem

In this paper, a comprehensive production planning problem under uncertain demand is investigated. The problem intertwines two NP-hard optimization problems: an assembly line balancing problem and a capacitated lot-sizing problem. The problem is modelled as a two-stage stochastic program assuming a risk-averse decision maker. Efficient solution procedures are proposed for tackling the problem. A case study related to mask production is presented. Several insights are provided stemming from the COVID-19 pandemic. Finally, the results of a series of computational tests are reported. (c) 2021 Elsevier B.V. All rights reserved.

Re-examining oil and BRICS' stock markets: new evidence from wavelet and MGARCH-DCC

This study examines how the relationship between oil and stock market return of BRICS behaves at different investment horizons. Using data ranging from 2006 to 2020, the wavelet and MGARCH-DCC found that the stock markets' return of Russia, Brazil, and South Africa are comparatively more correlated with oil price return across the investment horizons and more volatile particularly during the Covid-19 period. However, the stock markets' return of China and India is less correlated with oil price return and less volatile. It is also revealed that oil price return leads the BRICS' stock markets' return and both are positively correlated.

Volatility Spillovers between Stock and Energy Markets during Crises: A Comparative Assessment between the 2008 Global Financial Crisis and the Covid-19 Pandemic Crisis

This paper investigates volatility spillovers between energy and stock markets during periods of crises. Our main findings reveal that transmissions of volatilities among these markets during the Covid-19 pandemic crisis exceeded the ones recorded throughout the 2008 global financial crisis. All stock markets are net transmitters of volatility to energy markets during the 2008 global financial crisis while they show different patterns during the Covid-19 crisis. We also provide evidence of asymmetric volatility spillovers among stock and energy markets. Our results also indicate that on average natural gas provides better hedging effectiveness to the stock markets than crude oil.

Spectral adjustment for spatial confounding

Adjusting for an unmeasured confounder is generally an intractable problem, but in the spatial setting it may be possible under certain conditions. We derive necessary conditions on the coherence between the exposure and the unmeasured confounder that ensure the effect of exposure is estimable. We specify our model and assumptions in the spectral domain to allow for different degrees of confounding at different spatial resolutions. One assumption that ensures identifiability is that confounding present at global scales dissipates at local scales. We show that this assumption in the spectral domain is equivalent to adjusting for global-scale confounding in the spatial domain by adding a spatially smoothed version of the exposure to the mean of the response variable. Within this general framework, we propose a sequence of confounder adjustment methods that range from parametric adjustments based on the Matern coherence function to more robust semiparametric methods that use smoothing splines. These ideas are applied to areal and geostatistical data for both simulated and real datasets.

Analysing spatiotemporal patterns of Covid-19 confirmed deaths at the NUTS-2 regional level

During the ongoing Covid-19 pandemic, understanding the spatiotemporal patterns of the virus is crucial for policymakers to intervene promptly. The relevance of spatial proximity in the spread of the pandemic necessitates adequate tools, and noisy data must be properly treated. This study proposes obtaining clusters of European regions using smoothed curves of daily deaths from March 2020-March 2022. A functional representation of the curves w<s implemented to extract the features used in a clustering algorithm that allows spatial proximity. In a spatial regression model, the authors also investigated the role of clusters and pre-existing conditions on cumulative deaths, and observed that air pollution, health conditions, and population age structure are significantly associated with Covid-19 confirmed deaths.

DeepDrive: A braking decision making approach using optimized GAN and Deep CNN for advanced driver assistance systems

Reduction of the number of traffic accidents is a vital requirement in many countries over the world. In these circumstances, the Human–Robot Interaction (HRI) mechanisms utilization is currently exposed as a possible solution to recompense human limits. It is crucial to create a braking decision-making model in order to produce the optimal decisions possible because many braking decision-making approaches are launched with minimal performance. An effective braking decision-making system, named Optimized Deep Drive decision model is developed for making braking decisions. The video frames are extracted and the segmentation process is done using a Generative Adversarial Network (GAN). GAN is trained using the newly developed optimization technique known as the Autoregressive Anti Corona Virus Optimization (ARACVO) algorithm. ARACVO is created by combining the Conditional Autoregressive Value at Risk by Regression Quantiles (CAViaR) and Anti Corona Virus Optimization (ACVO) models. After retrieving the useful information for processing, the Deep Convolutional Neural Network (Deep CNN) is next used to decide whether to apply the brakes. The proposed approach improved performance by achieving maximum values of 0.911, 0.906, 0.924, and 0.933 for segmentation accuracy, accuracy, sensitivity, and specificity. © 2023 Elsevier Ltd

Long memory in Bitcoin and ether returns and volatility and Covid-19 pandemic

PurposeThe purpose of this research is to analyze the Bitcoin (BTC) and Ether (ETH) long memory and conditional volatility.Design/methodology/approachThe empirical approach includes ARFIMA-HYGARCH and ARFIMA-FIGARCH, both models under Student‘s t-distribution, during the period (ETH: November 9, 2017 to November 25, 2021 and BTC: September 17, 2014 to November 25, 2021).FindingsFindings suggest that ARFIMA-HYGARCH is the best model to analyze BTC volatility, and ARFIMA-FIGARCH is the best approach to model ETH volatility. Empirical evidence also confirms the existence of long memory on returns and on BTC volatility parameters. Results evidence that the models proposed are not as suitable for modeling ETH volatility as they are for the BTC.Originality/valueFindings allow to confirm the fractal market hypothesis in BTC market. The data confirm that, despite the impact of the Covid-19 crisis, the dynamics of BTC returns, and volatility maintained their patterns, i.e. the way in which they evolve, in relation to the prepandemic era, did not change, but it is rather reaffirmed. Yet, ETH conditional volatility was more affected, as it is apparently higher during Covid-19. The originality of the research lies in the focus of the analysis, the proposed methodology and the variables and periods of study.

INVESTMENT IN VIRTUAL DIGITAL ASSETS VIS-A-VIS EQUITY STOCK AND COMMODITY: A POST-COVID VOLATILITY ANALYSIS

Virtual digital assets including cryptocurrencies, non-fungible tokens and decentralized financial asset have been initially used as an alternative currency but are currently being purchased as an asset and hedging instruments. Exponentially growing trading volume witnesses the growing inclination of investors towards these assets, and this calls for volatility analysis of these assets. In this reference, the present study assessed and compared the volatility of returns from investment in virtual digital assets, equity and commodity market. Daily closing prices of selected cryptocurrencies, non-fungible tokens and decentralized financial assets, stock indices and commodities have been analysed forthe post-covid period. Since returns were observed to be heteroscedastic, autoregressive conditional heteroscedastic models have been used to assess the volatility. The results indicate a low correlation of commodity investment with all other investment opportunities. Also, Tether and Dai have been observed to be negatively correlated with stock market. This indicates the possibility of minimizing risk through portfolio diversification. In terms of average returns, virtual digital assets are discerned to be better options than equity stock or commodity yet the variance scenario of these investment avenues is not very rosy. The volatility parameters reveal that unlike commodity market, virtual digital assets have got a significant impact of external shocks in the short-run. Further, the long run persistency of shocks is observed to be higher for the UK stock market, followed by Ethereum, Tether and Dai. The present analysis is crucial as the decision about its acceptance as legal tender money is still sub-judice in some countries. The results are expected to provide insight to regulatory bodies about these assets. © Author(s) 2022.

The effect of consumption value on consumer changes behavior in usage of food delivery applications in the era of society 5.0

The outbreak of the Covid-19 pandemic and the introduction of Society 5.0 by the Japanese gov-ernment in 2019 have resulted in significant changes to consumer behavior. The aim of this research is to examine the impacts of consumption value on customers' behavioral shifts. Further-more, quantitative methods were used with a sample of 344 respondents, and data analysis using the structural equation model with the Lisrel 8.72 application. The stages in the structural equation analysis of this model are: development of theoretical models, development of path diagrams, conversion of path diagrams to structural equations, selecting input matrices and types of esti-mates, identifying models, assessing goodness of fit criteria, and interpreting results. The results obtained showed that consumers' attitudes and habits toward utilizing meal delivery applications can be influenced by factors such as their social, conditional, emotional, epistemic, and functional values. In the use of food delivery applications, consumers are not only interested in tangible benefits, but also in less tangible benefits, such as information provided by businesses. © 2023 by the authors;licensee Growing Science, Canada.

Different Deep Learning Based Classification Models for COVID-19 CT-Scans and Lesion Segmentation Through the cGAN-UNet Hybrid Method

The new coronavirus, which emerged in early 2020, caused a major global health crisis in 7 continents. An essential step towards fighting this virus is computed tomography (CT) scans. CT scans are an effective radiological method to detecting the diagnosis in early stage, but have greatly increased the workload of radiologists. For this reason, there are systems needed that will reduce the duration of CT examinations and assist radiologists. In this study, a two-stage system has been proposed for COVID-19 detection. First, a hybrid method is proposed that can segment the infected region from CT images. The reason for this is that there is not always a reference image in the datasets used in the classification. For this purpose;UNet, UNet++, SegNet and PsPNet were used both separately and as hybrids with GAN, to automatically segment infected areas from chest CT slices. According to the segmentation results, cGAN-UNet hybrid system was selected as the most successful method. Experimental results show that the proposed method achieves a segmentation success with a dice score of 92.32% and IoU score of 86.41%. In the second stage, three classifiers which include a Convolutional Neural Network (CNN), a PatchCNN and a Capsule Neural Network (CapsNet) were used to classify the generated masks as either COVID-19 or not, using the segmented images obtained from cGAN-UNet. Success of these classifiers was 99.20%, 92.55% and 73.84%, respectively. According to these results, the highest success was achieved in the system where cGAN-Unet and CNN are used together. © 2023 Lavoisier. All rights reserved.

LCA-GAN: Low-Complexity Attention-Generative Adversarial Network for Age Estimation with Mask-Occluded Facial Images

Facial-image-based age estimation is being increasingly used in various fields. Examples include statistical marketing analysis based on age-specific product preferences, medical applications such as beauty products and telemedicine, and age-based suspect tracking in intelligent surveillance camera systems. Masks are increasingly worn for hygiene, personal privacy concerns, and fashion. In particular, the acquisition of mask-occluded facial images has become more frequent due to the COVID-19 pandemic. These images cause a loss of important features and information for age estimation, which reduces the accuracy of age estimation. Existing de-occlusion studies have investigated masquerade masks that do not completely occlude the eyes, nose, and mouth;however, no studies have investigated the de-occlusion of masks that completely occlude the nose and mouth and its use for age estimation, which is the goal of this study. Accordingly, this study proposes a novel low-complexity attention-generative adversarial network (LCA-GAN) for facial age estimation that combines an attention architecture and conditional generative adversarial network (conditional GAN) to de-occlude mask-occluded human facial images. The open databases MORPH and PAL were used to conduct experiments. According to the results, the mean absolution error (MAE) of age estimation with the de-occluded facial images reconstructed using the proposed LCA-GAN is 6.64 and 6.12 years, respectively. Thus, the proposed method yielded higher age estimation accuracy than when using occluded images or images reconstructed using the state-of-the-art method.

Name Entity Recognition on Covid-19 Dataset using Machine Learning algorithms

The COVID-19 pandemic has been accompanied by such an explosive increase in media coverage and scientific publications that researchers find it difficult to keep up. So we are working on COVID-19 dataset on Omicron variant to recognise the name entity from a given text. We collect the COVID related data from newspaper or from tweets. This article covered the name entity like COVID variant name, organization name and location name, vaccine name. It include tokenisation, POS tagging, Chunking, levelling, editing and for run the program. It will help us to recognise the name entity like where the COVID spread (location) most, which variant spread most (variant name), which vaccine has been given (vaccine name) from huge dataset. In this work, we have identified the names. If we assume unemployment, economic downfall, death, recovery, depression, as a topic we can identify the topic names also, and in which phase it occurred. © 2022 IEEE.