Blockchain market and eco-friendly financial assets: Dynamic price correlation, connectedness and spillovers with portfolio implications

Since the emergence of blockchain technology, several digital assets such as cryptocurrencies, DeFi, and NFTs have gained considerable attention from investors and policymakers. However, the blockchain market has significant negative ramifications for the environment that may transmit shocks towards eco-friendly financial assets. We use the rolling window wavelet correlation (RWWC) model and the quantile-based time-varying (QVAR) connectedness framework to analyze the dynamic price correlation and connectedness between the blockchain market and green (eco-friendly) financial assets. As a representative of the blockchain market, we use the price returns of four cryptocurrencies, DeFi, and NFTs. For green equities, we use the MSCI Global Environment Price Index and the S&P Green Bond Price Index. We find a low correlation between the blockchain market and green financial assets before the outbreak of COVID-19 and a strong correlation during the COVID-19 and the Russia-Ukraine war. The quantile VAR results show symmetric connectedness of the examined and identical spillovers between extremely positive and strongly negative returns. Green bonds and stocks are the system's major shock receivers. The transmission network results imply major shock transmissions are driven by short-term frequency, whereas there is a lower transmission in the long-term. © 2023 Elsevier Inc.

Effective multi-step ahead container throughput forecasting under the complex context

Accurate and effective container throughput forecasting plays an essential role in economic dispatch and port operations, especially in the complex and uncertain context of the global Covid-19 pandemic. In light of this, this research proposes an effective multi-step ahead forecasting model called EWT-TCN-KMSE. Specifically, we initially use the empirical wavelet transform (EWT) to decompose the original container throughput series into multiple components with varying frequencies. Subsequently, the state-of-the-art temporal convolutional network is utilized to predict the decomposed components individually, during which an improved loss function that combines mean square error (MSE) and kernel trick is employed. Eventually, the deduced prediction results can be obtained by integrating the predicted values of each component. In particular, this research introduces the MIMO (multi-input and multi-output) strategy to conduct multi-step ahead container throughput forecasting. Based on the experiments in Shanghai port and Ningbo-Zhoushan port, it can be found that the proposed model shows its superiority over benchmark models in terms of accuracy, stability, and significance in container throughput forecasting. Therefore, our proposed model can assist port operators in their daily management and decision making. © 2023 John Wiley & Sons Ltd.

A Novel Framework to Forecast COVID-19 Incidence Based on Google Trends Search Data

The global outbreak of coronavirus disease 2019 (COVID-19) has spread to more than 200 countries worldwide, leading to severe health and socioeconomic consequences. As such, the topic of monitoring and predicting epidemics has been attracting a lot of interest. Previous work reported search volumes from Google Trends are beneficial in decoding influenza dynamics, implying its potential for COVID-19 prediction. Therefore, a predictive model using the Wiener methods was built based on epidemic-related search queries from Google Trends, along with climate variables, aiming to forecast the dynamics of the weekly COVID-19 incidence in Washington, DC, USA. The Wiener model, which shares the merits of interpretability, low computation costs, and adaptation to nonlinear fluctuations, was used in this study. Models with multiple sets of features were constructed and further optimized by the highest weight selecting strategy. Furthermore, comparisons to the other two commonly used prediction models based on the autoregressive integrated moving average (ARIMA) and long short-term memory (LSTM) were also performed. Our results showed the predicted COVID-19 trends significantly correlated with the actual (rho <inline-formula> <tex-math notation="LaTeX">$=$</tex-math> </inline-formula> 0.88, <inline-formula> <tex-math notation="LaTeX">$p $</tex-math> </inline-formula> <inline-formula> <tex-math notation="LaTeX">$<$</tex-math> </inline-formula> 0.0001), outperforming those with ARIMA and LSTM approaches, indicating Google Trends data as a useful tool in terms of COVID-19 prediction. Also, the model using 20 search queries with the highest weighting outperformed all other models, supporting the highest weight feature selection as a feasible criterion. Google Trends search query data can be used to forecast the outbreak of COVID-19, which might assist health policymakers to allocate health care resources and taking preventive strategies. IEEE

Wavelet and modified VGG-16 deep learning to identify COVID-19 based on X-ray images

COVID-19 is caused by the SARS coronavirus 2 family (SARS-CoV-2). A quick antibody or antigen test can detect the presence of COVID-19, but further testing is needed to confirm a positive result. Radiologists use chest X-rays to diagnose chest diseases early. The proposed system integrates discrete wavelet transformation and deep learning to help radiologists categorise conditions. Wavelets break down images into multiple spatial resolutions depending on a high pass and low pass frequency components and efficiently extract characteristics from lung X-rays. Here, we use a hybrid wavelet-CNN model to diagnose lung X-rays. The proposed CNN model is trained and verified on different source COVID 19 chest X-ray images for binary and three classes. The proposed studies suggest significant improvement in outcomes, with the best parameters achieving 99.42% accuracy and 96.43% accuracy for binary and three classes. The depiction of feature maps shows that our suggested network collected features from the corona virus-affected lung properly. Results suggest that the proposed model is successful enough for COVID 19 diagnosis. © 2022 IEEE.

A study on fractional COVID-19 disease model by using Hermite wavelets.

The preeminent target of present study is to reveal the speed characteristic of ongoing outbreak COVID-19 due to novel coronavirus. On January 2020, the novel coronavirus infection (COVID-19) detected in India, and the total statistic of cases continuously increased to 7 128 268 cases including 109 285 deceases to October 2020, where 860 601 cases are active in India. In this study, we use the Hermite wavelets basis in order to solve the COVID-19 model with time- arbitrary Caputo derivative. The discussed framework is based upon Hermite wavelets. The operational matrix incorporated with the collocation scheme is used in order to transform arbitrary-order problem into algebraic equations. The corrector scheme is also used for solving the COVID-19 model for distinct value of arbitrary order. Also, authors have investigated the various behaviors of the arbitrary-order COVID-19 system and procured developments are matched with exiting developments by various techniques. The various illustrations of susceptible, exposed, infected, and recovered individuals are given for its behaviors at the various value of fractional order. In addition, the proposed model has been also supported by some numerical simulations and wavelet-based results.

An extended wavelet approach of the money-output link in the United States.

The paper examines the link between money and output in the U.S. by using wavelet analysis. The time span covers the period from 1960Q1 to 2021Q1. The main results evidence that money positively leads real output from the late 1960s to 1982, at medium frequency, with the interest rate playing an important role. In contrast, we reveal that real output negatively leads money, at the same medium frequency, but from the late 1990s to 2021. The COVID-19 pandemic generates significant co-movements in the short and medium frequencies, over the period from 2020 to 2021, with output negatively leading money. We underline that Federal Reserve monetary policy operating procedures play an essential role in explaining these findings. The results support using the federal funds rate operating procedure as countercyclical monetary policy measures and implementing unconventional monetary policy tools in times of the effective lower bound. Finally, no relationship between money and output is observed in the long term, while the short term (i.e. high frequency) reveals rather chaotic co-movements. The results remain robust to alternative wavelet tools, higher-frequency datasets, and a Hodrick-Prescott filtered quarterly sample. Supplementary Information: The online version contains supplementary material available at 10.1007/s00181-022-02294-6.

NON-LINEAR OPERATOR APPROXIMATIONS FOR INITIAL VALUE PROBLEMS

Time-evolution of partial differential equations is fundamental for modeling several complex dynamical processes and events forecasting, but the operators associated with such problems are non-linear. We propose a Padé approximation based exponential neural operator scheme for efficiently learning the map between a given initial condition and the activities at a later time. The multiwavelets bases are used for space discretization. By explicitly embedding the exponential operators in the model, we reduce the training parameters and make it more data-efficient which is essential in dealing with scarce and noisy real-world datasets. The Padé exponential operator uses a recurrent structure with shared parameters to model the non-linearity compared to recent neural operators that rely on using multiple linear operator layers in succession. We show theoretically that the gradients associated with the recurrent Padé network are bounded across the recurrent horizon. We perform experiments on non-linear systems such as Korteweg-de Vries (KdV) and Kuramoto-Sivashinsky (KS) equations to show that the proposed approach achieves the best performance and at the same time is data-efficient. We also show that urgent real-world problems like epidemic forecasting (for example, COVID-19) can be formulated as a 2D time-varying operator problem. The proposed Padé exponential operators yield better prediction results (53% (52%) better MAE than best neural operator (non-neural operator deep learning model)) compared to state-of-the-art forecasting models. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

Pass-through Effects of Oil Prices on LATAM Emerging Stocks before and during COVID-19: An Evidence from a Wavelet-VAR Analysis

Vector Auto regression model (VAR) a time-varying parameter is applied to study the effect of oil price shocks on the returns of stocks in the LATAM (Latin American) markets. Coherent Wavelet analysis highlights possibilities of connectedness of the oil price and LATAM stock markets through the presence of different patterns in a time series. The structural demand shocks standard deviations during the COVID-19 era remain high and the pass-through effects on stock returns due to oil prices differ for different time frames. The fundamental linkages are demonstrated due to oil market specific demand. The main motive of the research work is to identify the influence of oil price on stocks and identify the fundamental source of contagion.A random effects model is applied to the panel data of LATAM markets with the Global stock market index, MSCI (Morgan Stanley Capital International World Index), domestic money market rates and currency exchange rates during the period of study, 15 March 2019 to 31 July 2021 with 684 observations of controlled non-observed characteristics from individual country. The findings of this research recommend the pass-through effect of the oil prices on the stock market returns are based on time frequency. The contribution of this paper helps the policy makers to restore the confidence amongst the investors in the stock markets and strategies to be adopted by the investors to mitigate the risk by ideal portfolio management. © 2023, Econjournals. All rights reserved.

EVALUATION OF AIR TRAFFIC IN THE CONTEXT OF THE COVID-19 PANDEMIC

The Covid-19 pandemic unexpectedly shook the entire global economy, causing it to destabilize over a long period of time. One of the sectors that was particularly hit hard was air traffic, and the changes that have taken place in it have been unmatched by any other crisis in history. The purpose of this article was to identify the time series describing the number of airline flights in Poland in the context of the Covid-19 pandemic. The article first presents selected statistics and indicators showing the situation of the global and domestic aviation market during the pandemic. Then, based on the data on the number of flights in Poland, the identification of the time series describing the number of flights by airlines was made. The discrete wavelet transformation (DWT) was used to determine the trend, while for periodicity verification, first statistical tests (Kruskal-Wallis test and Friedman test) and then spectral analysis were used. The confirmation of the existence of weekly seasonality allowed for the identification of the studied series as the sum of the previously determined trend and the seasonal component, as the mean value from the observations on a given day of the week. The proposed model was compared with the 7-order moving average model, as one of the most popular in the literature. As the obtained results showed, the model developed by the authors was better at identifying the studied series than the moving average. The errors were significantly lower, which made the presented solution more effective. This confirmed the validity of using wavelet analysis in the case of irregular behaviour of time series, and also showed that both spectral analysis and statistical tests (Kruskal-Walis and Fridman) proved successful in identifying the seasonal factor in the time series. The method used allowed for a satisfactory identification of the model for empirical data, however, it should be emphasized that the aviation services market is influenced by many variables and the forecasts and scenarios created should be updated and modified on an ongoing basis. © 2022 Warsaw University of Technology. All rights reserved.

Does the source of uncertainty matter? The impact of financial, newspaper and Twitter-based measures on U.S. banks

This study examines if the source of uncertainty (newspaper, Twitter, financial market) matters in its impact on bank stock returns in the United States. By applying discrete wavelet transformation, we model directional spillovers and Granger causality between uncertainty and bank returns for different time horizons. Our results demonstrate that this distinction between time horizons is crucial. Although newspaper and Twitter-based measures are correlated, they capture a different source of investor perception. Twitter-based uncertainty adversely affects bank stocks in the short run, while newspaper-based policy uncertainty is relevant in the medium run. Financial-based uncertainty, VIX, is the most important factor. Moreover, we find that the impact of uncertainty on bank returns is stronger during the COVID-19 pandemic and for banks with a high ratio of loans to total assets and large off-balance-sheet activities. © 2023 Elsevier B.V.

A wavelet multifractal model for quality of life index measuring during pandemics and crises

In the present article, we investigate the impact of the timescale factor on the quality of life index behaviour on specific time intervals characterized by the presence of socio-economic, political, and/or health severe movements such as pandemics and crises. We essentially aim to show that effectively the quality of life evaluation based on a single index as in the existing studies may be described more adequately by a variable index due to the social, political, economic, and also healthy environment. The variability discovered is expressed by the existence and the estimation of a multi-index instead of a single one with relatively too many factors. Our focus is mainly on the effect of the COVID-19 pandemic and crises or crashes on the quality of life. It turns out that the first essays of empirical treatments of such a series bring out a fractal/multifractal aspect. This motivates our main idea reposing on the fractal/multifractal structure of the data to construct a quantitative model based on wavelets combined with change-point analysis. Our model is applied empirically on a sample corresponding to Saudi Arabia as a case of study during the period from January 1990 to December 2021. The end of this period is strongly affected by the COVID-19 pandemic. The sample is based on social media conversations and texts discussing and describing the satisfaction with the quality of life. The study confirms effectively that the role of the timescale factor is more described when considering a multi-index rather than measurement on the whole time interval. Besides, this multi-index is clearly illustrated by means of the multifractal spectra of the data used. © 2023 John Wiley & Sons Ltd.

Does climate impact the relationship between the energy price and the stock market? The Colombian case

Climate change imposes increased stress on the relationship between energy and financial markets. Countries with energy matrices that depend on water sources influenced by climatic phenomena must identify and control their impact on energy prices and financial markets. This research analyses if the El Niño Southern Oscillation phenomenon affects the relationship between electricity prices and financial markets. To that end, we apply wavelet analysis for bivariate time series and contagion tests to examine the correlations and evaluate the presence of contagion. The cross-wavelet power spectrum coherence coefficients suggest two periods where energy prices and the stock market are closely related: The strong El Niño phase in 2015, which confirms our conjecture, and the first stages of the 2020 Covid Pandemic. For the el Niño phase, the energy price leads the stock market in scales from three to eight months, while for the pandemic period, the unexpected disruption produces changing patterns for the same scales. There is also a robust long-term coherence for longer scales beginning in 2012. Moreover, the contagion tests confirm the contagion between markets during extreme climate events. Thus, our alternative method to uncover market relationships beyond traditional econometric contagion approaches contributes to theoretical discussions.

Lung disease detection using Self-Attention Generative Adversarial Capsule network optimized with sun flower Optimization Algorithm

Lung cancer is the uncontrolled growth of abnormal cells in one or both lungs. This is one of the dangerous diseases. A lot of feature extraction with classification methods were discussed previously regarding this disease, but none of the methods give sufficient results, not only that, those methods have high over fitting problem, as a result, the detection accuracy was minimizing. Therefore, to overcome these issues, a Lung Disease Detection using Self-Attention Generative Adversarial Capsule Network optimized with Sun flower Optimization Algorithm (SA-Caps GAN-SFOA-LDC) is proposed in this manuscript. Initially, NIH chest X-ray image dataset is gathered through Kaggle repository to diagnose the lung disease. Then, the chests X-ray images are pre-processed by using the contrast limited adaptive histogram equalization (CLAHE) filtering method to eliminate the noise and to enhance the image quality. These pre-processed outputs are fed to feature extraction process. In the feature extraction process, the empirical wavelet transform method is used. These extracted features are given into Self-Attention based Generative Adversarial Capsule classifier for detecting the lung disease. The hyper parameters of SA-Caps GAN classifier is optimized using Sun flower Optimization Algorithm. The simulation is implemented in MATLAB. The proposed SA-Caps GAN-SFOA-LDC method attains higher accuracy 21.05%, 33.28%, 30.27%, 29.68%, 32.57% and 44.28%, Higher Precision 30.24%, 35.68%, 32.08%, 41.27%, 28.57% and 34.20%, Higher F-Score 32.05%, 31.05%, 36.24%, 30.27%, 37.59% and 22.05% analyzed with the existing methods, SVM-SMO-LDC, CNN-MOSHO-LDC, XGboost-PSO-LDC respectively. © 2022 Elsevier Ltd

COVID-19 X-Ray Images Classification using Support Vector Machine and K-Nearest Neighbor

COVID-19 has significantly influenced living in recent years. Almost all countries have carried out all limitations to reduce its spread. Detection is highly required for further handling of COVID-19. In this study, the detection was performed using classification on 1,184 X-ray images, specifically 404 X-ray images of COVID-19 positive people, 390 X-ray images of normal people and 390 X-ray images of pneumonia positive people. The image data were extracted with the Haar wavelet algorithm and classified using the Support Vector Machine (SVM) and K-Nearest Neighbor (KNN);each had three classification models. The Quadratic SVM model obtained the best result with an accuracy of 79.8%. © 2022 IEEE.

Dynamic connectedness of China's green bonds and asset classes

This paper quantifies the co-movement and time-varying integration between China's green bonds and other asset classes across different time domains using the wavelet coherence and time-frequency connectedness model based on the time-varying parameter VAR (TVP-VAR). First, we predominantly detect a strong positive co-movement of green and conventional bonds, especially in the medium and long term. Second, strong bidirectional spillovers exist between green bonds and treasury, corporate, and financial bonds regardless of the time horizon. Lastly, cross-market spillovers between the green bonds and the stock, energy, low-carbon stock market were quite limited in the short-run but strengthened towards the long-term except during the 2015 China stock market crash and the COVID-19 recession when short-term integration rose sharply. The results document some practical enlightenment for investors and policymakers with various time horizons. © 2022 Elsevier Inc.

A Modified PINN Approach for Identifiable Compartmental Models in Epidemiology with Application to COVID-19.

Many approaches using compartmental models have been used to study the COVID-19 pandemic, with machine learning methods applied to these models having particularly notable success. We consider the Susceptible-Infected-Confirmed-Recovered-Deceased (SICRD) compartmental model, with the goal of estimating the unknown infected compartment I, and several unknown parameters. We apply a variation of a "Physics Informed Neural Network" (PINN), which uses knowledge of the system to aid learning. First, we ensure estimation is possible by verifying the model's identifiability. Then, we propose a wavelet transform to process data for the network training. Finally, our central result is a novel modification of the PINN's loss function to reduce the number of simultaneously considered unknowns. We find that our modified network is capable of stable, efficient, and accurate estimation, while the unmodified network consistently yields incorrect values. The modified network is also shown to be efficient enough to be applied to a model with time-varying parameters. We present an application of our model results for ranking states by their estimated relative testing efficiency. Our findings suggest the effectiveness of our modified PINN network, especially in the case of multiple unknown variables.

Bunker fuel, commodity prices and shipping market indices following the COVID-19 pandemic. A time-frequency analysis

This paper deals with the analysis of the evolution of international trade after COVID-19, examining commodity prices, the shipping industry, and the influence of the cost of bunker fuel. To this end, we use techniques based on fractional integration, fractional cointegration VAR (FCVAR) and wavelet analysis. Monthly data relating to heavy fuel oil prices and the shipping market from October 2011 to September 2021 are used. Using fractional integration in the post-break period, a lack of mean reversion is observed in all cases, which means that, for the commodity prices and shipping market indices, a change in trend will be permanent after COVID-19 unless strong measures are carried out by the authorities. Using wavelet analysis, we conclude that the demand shock represented in the indices mentioned above has led the price of fuel oil since the beginning of the pandemic, and bunker fuel is not relevant in determining the cost of maritime transport.

Detection of COVID-19 using Wavelet Transform, Machine Learning and Deep Learning Models

Since December 2019, the world is fighting against the newly found virus named COVID-19 whose symptoms are closer to pneumonia. Being highly contagious, it has spread all over the world, and hence the World Health Organization has declared this as a global pandemic. Some patients infected with this virus have severe symptoms which are fatal. Hence the early discovery of COVID-19 infected patients is necessary to avoid further community spread. The available tests such as RTPCR and Rapid Antigen Tests are not 100% accurate and do not give quick results either. Therefore, it is the need of the hour to explore identification methodologies that are quick, accurate, and easily scalable. This work intends to do so using different machine learning and deep learning models. First, the step involves feature extraction using Gray Level Co-occurrence Matrix (GLCM) and classification with LightGBM classifier which gives an accuracy of 92.78%. This is then further improved to 95.79% using wavelets. Further, the CNN architectures with max-pooling and DWT layers are compared and it's found that CNN architecture with max-pooling layer gives better accuracy of 95.72%. Thus, this work presents a comparative analysis of Machine Learning Algorithms and CNN architectures for better accuracy and time. © 2022 IEEE.

Combination of wavelet transform and LSTM to detect low functional respiration

Automatic and long-term monitoring of respiratory is in great demand for lung diseases. It gets required greater in these years due to COVID-19 pandemic to reduce medical staff fatigue for checking patient conditions frequently for long time. Kobayashi et al., in our team, developed a device measuring respiratory condition by quantizing the displacement between the 6th and 8th ribs. We introduce long short-term memory (LSTM) neural network to classify patient respiratory signals into the two states of normal and low-functional respirations. The signals were checked by a medical doctor manually for classified into the two states. In the process, they were transformed to frequency-domain spectra with complex-valued wavelet transform, and then quantized the respiratory wavelet spectra due to the large number of spectra patterns. After that, the LSTM learned and classified the processed respiratory signals. The experimental results showed the feasibility to detect the two states. © 2021, Japan Soc. of Med. Electronics and Biol. Engineering. All rights reserved.

Analysis of the Spatio-Temporal Dynamics of COVID-19 in Massachusetts Via Spectral Graph Wavelet Theory

The rapid spread of COVID-19 disease has had a significant impact on the world. In this paper, we study COVID-19 data interpretation and visualization using open-data sources for 351 cities and towns in Massachusetts from December 6, 2020 to September 25, 2021. Because cities are embedded in rather complex transportation networks, we construct the spatio-temporal dynamic graph model, in which the graph attention neural network is utilized as a deep learning method to learn the pandemic transition probability among major cities in Massachusetts. Using the spectral graph wavelet transform (SGWT), we process the COVID-19 data on the dynamic graph, which enables us to design effective tools to analyze and detect spatio-temporal patterns in the pandemic spreading. We design a new node classification method, which effectively identifies the anomaly cities based on spectral graph wavelet coefficients. It can assist administrations or public health organizations in monitoring the spread of the pandemic and developing preventive measures. Unlike most work focusing on the evolution of confirmed cases over time, we focus on the spatio-temporal patterns of pandemic evolution among cities. Through the data analysis and visualization, a better understanding of the epidemiological development at the city level is obtained and can be helpful with city-specific surveillance. IEEE