Short-term prediction of COVID-19 spread using grey rolling model optimized by particle swarm optimization

The application of the propensity score matching method in stock prediction among stocks within the same industry

Stock price prediction is crucial in stock market research, yet existing models often overlook interdependencies among stocks in the same industry, treating them as independent entities. Recognizing and accounting for these interdependencies is essential for precise predictions. Propensity score matching (PSM), a statistical method for balancing individuals between groups and improving causal inferences, has not been extensively applied in stock interdependence investigations. Our study addresses this gap by introducing PSM to examine interdependence among pharmaceutical industry stocks for stock price prediction. Additionally, our research integrates Improved particle swarm optimization (IPSO) with long short-term memory (LSTM) networks to enhance parameter selection, improving overall predictive accuracy. The dataset includes price data for all pharmaceutical industry stocks in 2022, categorized into chemical pharmaceuticals, biopharmaceuticals, and traditional Chinese medicine. Using Stata, we identify significantly correlated stocks within each sub-industry through average treatment effect on the treated (ATT) values. Incorporating PSM, we match five target stocks per sub-industry with all stocks in their respective categories, merging target stock data with weighted data from non-target stocks for validation in the IPSO-LSTM model. Our findings demonstrate that including non-target stock data from the same sub-industry through PSM significantly improves predictive accuracy, highlighting its positive impact on stock price prediction. This study pioneers PSM's use in studying stock interdependence, conducts an in-depth exploration of effects within the pharmaceutical industry, and applies the IPSO optimization algorithm to enhance LSTM network performance, providing a fresh perspective on stock price prediction research.

IPSO-LSTM hybrid model for predicting online public opinion trends in emergencies

When emergencies are widely discussed and shared, it may lead to conflicting opinions and negative emotions among internet users. Accurately predicting sudden network public opinion events is of great importance. Therefore, this paper constructs a hybrid forecasting model to solve this problem. First, this model introduces an improved inertia weight and an adaptive variation operation to enhance the Particle Swarm Optimization (PSO) algorithm. Then, the improved PSO (IPSO) algorithm optimizes the parameters of the Long Short-Term Memory (LSTM) neural network. Finally, the IPSO-LSTM hybrid prediction model is constructed to forecast and analyze emergency public opinion dissemination trends. The experimental outcomes indicate that the IPSO-LSTM model surpasses others and has high prediction accuracy. In the four emergency predictions we select, the MAPE value of IPSO-LSTM is 74.27% better than that of BP, 33.96% better than that of LSTM, and 13.59% better than that of PSO-LSTM on average. This study aims to assist authorities in quickly identifying potential public opinion crises, developing effective strategies, and promoting sustainable and positive growth in the network environment.

Improved LSTM-based deep learning model for COVID-19 prediction using optimized approach

Individuals in any country are badly impacted both economically and physically whenever an epidemic of infectious illnesses breaks out. A novel coronavirus strain was responsible for the outbreak of the coronavirus sickness in 2019. Corona Virus Disease 2019 (COVID-19) is the name that the World Health Organization (WHO) officially gave to the pneumonia that was caused by the novel coronavirus on February 11, 2020. The use of models that are informed by machine learning is currently a major focus of study in the field of improved forecasting. By displaying annual trends, forecasting models can be of use in performing impact assessments of potential outcomes. In this paper, proposed forecast models consisting of time series models such as long short-term memory (LSTM), bidirectional long short-term memory (Bi-LSTM), generalized regression unit (GRU), and dense-LSTM have been evaluated for time series prediction of confirmed cases, deaths, and recoveries in 12 major countries that have been affected by COVID-19. Tensorflow1.0 was used for programming. Indices known as mean absolute error (MAE), root means square error (RMSE), Median Absolute Error (MEDAE) and r2 score are utilized in the process of evaluating the performance of models. We presented various ways to time-series forecasting by making use of LSTM models (LSTM, BiLSTM), and we compared these proposed methods to other machine learning models to evaluate the performance of the models. Our study suggests that LSTM based models are among the most advanced models to forecast time series data.

Two novel nonlinear multivariate grey models with kernel learning for small-sample time series prediction

For many applications, small-sample time series prediction based on grey forecasting models has become indispensable. Many algorithms have been developed recently to make them effective. Each of these methods has a specialized application depending on the properties of the time series that need to be inferred. In order to develop a generalized nonlinear multivariable grey model with higher compatibility and generalization performance, we realize the nonlinearization of traditional GM(1,N), and we call it NGM(1,N). The unidentified nonlinear function that maps the data into a better representational space is present in both the NGM(1,N) and its response function. The original optimization problem with linear equality constraints is established in terms of parameter estimation for the NGM(1,N), and two different approaches are taken to solve it. The former is the Lagrange multiplier method, which converts the optimization problem into a linear system to be solved; and the latter is the standard dualization method utilizing Lagrange multipliers, that uses a flexible estimation equation for the development coefficient. As the size of the training data increases, the estimation results of the potential development coefficient get richer and the final estimation results using the average value are more reliable. The kernel function expresses the dot product of two unidentified nonlinear functions during the solving process, greatly lowering the computational complexity of nonlinear functions. Three numerical examples show that the LDNGM(1,N) outperforms the other multivariate grey models compared in terms of generalization performance. The duality theory and framework with kernel learning are instructive for further research around multivariate grey models to follow.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s11071-023-08296-y.

Risk assessment approach for analyzing risk factors to overcome pandemic using interval-valued q-rung orthopair fuzzy decision making method

The process of developing and implementing sustainable strategies to prevent spread of COVID-19 for society typically requires integrating all social, technological, economic, governmental aspects in a systematic way. Since the clear understanding of risk factors contribute to the success of the strategies applied against COVID-19, a risk assessment procedure is applied in this study to properly evaluate risk factors cause to spread of pandemic as a multi-complex decision problem. Therefore, due to the evaluation of risk factors, which often involves uncertain information, the model is constructed based on interval-valued q-rung orthopair fuzzy-COmplex PRoportional ASsessment (IVq-ROF-COPRAS) method. While the developed framework is efficient to enhance the quality of decisions by implementing more realistic, precise, and effective application procedure under uncertain environment, it has capability to help governments for developing comprehensive strategies and responses. According to the results of the proposed risk analysis model, the top three risk factors are "The Approach that Prioritizes the Economy in Policies", "Insufficient Process Control in Normalization" and "Lack of Epidemic Management Culture in Individuals and Businesses". Lastly, to show applicability and efficiency of the model sensitivity and comparative analysis were conducted at the end of the study.

A novel deep neural network model based Xception and genetic algorithm for detection of COVID-19 from X-ray images

The coronavirus first appeared in China in 2019, and the World Health Organization (WHO) named it COVID-19. Then WHO announced this illness as a worldwide pandemic in March 2020. The number of cases, infections, and fatalities varied considerably worldwide. Because the main characteristic of COVID-19 is its rapid spread, doctors and specialists generally use PCR tests to detect the COVID-19 virus. As an alternative to PCR, X-ray images can help diagnose illness using artificial intelligence (AI). In medicine, AI is commonly employed. Convolutional neural networks (CNN) and deep learning models make it simple to extract information from images. Several options exist when creating a deep CNN. The possibilities include network depth, layer count, layer type, and parameters. In this paper, a novel Xception-based neural network is discovered using the genetic algorithm (GA). GA finds better alternative networks and parameters during iterations. The best network discovered with GA is tested on a COVID-19 X-ray image dataset. The results are compared with other networks and the results of papers in the literature. The novel network of this paper gives more successful results. The accuracy results are 0.996, 0.989, and 0.924 for two-class, three-class, and four-class datasets, respectively.

Fuzzy-SIRD model: Forecasting COVID-19 death tolls considering governments intervention

Modeling the trend of contagious diseases has particular importance for managing them and reducing the side effects on society. In this regard, researchers have proposed compartmental models for modeling the spread of diseases. However, these models suffer from a lack of adaptability to variations of parameters over time. This paper introduces a new Fuzzy Susceptible-Infectious-Recovered-Deceased (Fuzzy-SIRD) model for covering the weaknesses of the simple compartmental models. Due to the uncertainty in forecasting diseases, the proposed Fuzzy-SIRD model represents the government intervention as an interval type 2 Mamdani fuzzy logic system. Also, since society's response to government intervention is not a static reaction, the proposed model uses a first-order linear system to model its dynamics. In addition, this paper uses the Particle Swarm Optimization (PSO) algorithm for optimally selecting system parameters. The objective function of this optimization problem is the Root Mean Square Error (RMSE) of the system output for the deceased population in a specific time interval. This paper provides many simulations for modeling and predicting the death tolls caused by COVID-19 disease in seven countries and compares the results with the simple SIRD model. Based on the reported results, the proposed Fuzzy-SIRD model can reduce the root mean square error of predictions by more than 80% in the long-term scenarios, compared with the conventional SIRD model. The average reduction of RMSE for the short-term and long-term predictions are 45.83% and 72.56%, respectively. The results also show that the principle goal of the proposed modeling, i.e., creating a semantic relation between the basic reproduction number, government intervention, and society's response to interventions, has been well achieved. As the results approve, the proposed model is a suitable and adaptable alternative for conventional compartmental models.

Dual attention-based sequential auto-encoder for Covid-19 outbreak forecasting: A case study in Vietnam

For preventing the outbreaks of Covid-19 infection in different countries, many organizations and governments have extensively studied and applied different kinds of quarantine isolation policies, medical treatments as well as organized massive/fast vaccination strategy for over-18 citizens. There are several valuable lessons have been achieved in different countries this Covid-19 battle. These studies have presented the usefulness of prompt actions in testing, isolating confirmed infectious cases from community as well as social resource planning/optimization through data-driven anticipation. In recent times, many studies have demonstrated the effectiveness of short/long-term forecasting in number of new Covid-19 cases in forms of time-series data. These predictions have directly supported to effectively optimize the available healthcare resources as well as imposing suitable policies for slowing down the Covid-19 spreads, especially in high-populated cities/regions/nations. There are several progresses of deep neural architectures, such as recurrent neural network (RNN) have demonstrated significant improvements in analyzing and learning the time-series datasets for conducting better predictions. However, most of recent RNN-based techniques are considered as unable to handle chaotic/non-smooth sequential datasets. The consecutive disturbances and lagged observations from chaotic time-series dataset like as routine Covid-19 confirmed cases have led to the low performance in temporal feature learning process through recent RNN-based models. To meet this challenge, in this paper, we proposed a novel dual attention-based sequential auto-encoding architecture, called as: DAttAE. Our proposed model supports to effectively learn and predict the new Covid-19 cases in forms of chaotic and non-smooth time series dataset. Specifically, the integration between dual self-attention mechanism in a given Bi-LSTM based auto-encoder in our proposed model supports to directly focus the model on a specific time-range sequence in order to achieve better prediction. We evaluated the performance of our proposed DAttAE model by comparing with multiple traditional and state-of-the-art deep learning-based techniques for time-series prediction task upon different real-world datasets. Experimental outputs demonstrated the effectiveness of our proposed attention-based deep neural approach in comparing with state-of-the-art RNN-based architectures for time series based Covid-19 outbreak prediction task.

A novel grey model based on Susceptible Infected Recovered Model: A case study of COVD-19

The COVID-19 pandemic has lasted for nearly two years, and the global epidemic situation is still grim and growing. Therefore, it is necessary to make correct predictions about the epidemic to implement appropriate and effective epidemic prevention measures. This paper analyzes the classic Susceptible Infected Recovered Model (SIR) to understand the significance of model characteristics and parameters, and uses the differential and difference information of the grey system to put forward a grey prediction model based on SIR infectious disease model. The Laplace transform is used to calculate the model reduction formula, and finally obtain the modeling steps of the model. It is applied to large and small numerical cases to verify the validity of different orders of magnitude data. Meanwhile, data of different lengths are modeled and predicted to verify the robustness of model. Finally, the new model is compared with three classical grey prediction models. The results show that the model is significantly superior to the comparison model, indicating that the model can effectively predict the COVID-19 epidemic, and is applicable to countries with different population magnitude, can carry out stable and effective simulation and prediction for data of different lengths.

Impact of COVID-19 pandemic on the epidemiology of STDs in China: based on the GM (1,1) model

Background

COVID-19 and Sexually Transmitted Diseases (STDs) are two very important diseases. However, relevant researches about how COVID-19 pandemic has impacted on the epidemiological trend of STDs are limited in China. This study aimed to analyze the impact of COVID-19 on STDs in China and proposed relevant recommendations to be used in bettering health.

Methods

The incidence of HIV infection, syphilis and gonorrhea in China from 2008 to 2020 were collected. Grey Model (1,1) were established to predict the incidence of STDs with the incidence data of these three STDs from 2013 to 2018 considering the impact of policies in China, respectively. We then calculated the predictive incidence of each STD in 2019, 2020 and 2021 by the established Model. And we estimated the extent of the impact of COVID-19 on the epidemiological changes of STDs by analyzing the difference between the absolute percentage error (APE) of the predictive incidence and actual rate in 2019 and 2020.

Results

The incidence of HIV infection and syphilis showed a trend of increase from 2008 to 2019 in China, but that for gonorrhea was fluctuant. Of note, the incidence of these three STDs decreased significantly in 2020 compared with that in 2019. The APE of HIV infection, syphilis and gonorrhea in 2020 (20.54%, 15.45% and 60.88%) were about 7 times, 4 times and 2 times of that in 2019 (2.94%, 4.07% and 30.41%). The incidence of HIV infection, syphilis and gonorrhea would be 5.77/100,000, 39.64/100,000 and 13.19/100,000 in 2021 based on our model.

Conclusions

The epidemiological trend of STDs in China was significant influenced by COVID-19 pandemic. It is important to balance the control of COVID-19 and timely management of STDs during the COVID-19 epidemic to prevent or reduce the poor outcome among COVID-19 patients with STDs. New management strategies on STDs, such as leveraging social media, online medical care, rapid self-testing, timely diagnosis and treatment guarantee and balance of medical resources for STDs management should be adapted in the context of the long-term effects of COVID-19.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12879-022-07496-y.

A Particle Swarm Optimization Backtracking Technique Inspired by Science-Fiction Time Travel

Artificial intelligence techniques, such as particle swarm optimization, are used to solve problems throughout society. Optimization, in particular, seeks to identify the best possible decision within a search space. Problematically, particle swarm optimization will sometimes have particles that become trapped inside local minima, preventing them from identifying a global optimal solution. As a solution to this issue, this paper proposes a science-fiction inspired enhancement of particle swarm optimization where an impactful iteration is identified and the algorithm is rerun from this point, with a change made to the swarm. The proposed technique is tested using multiple variations on several different functions representing optimization problems and several standard test functions used to test various particle swarm optimization techniques.

Forecasting CO2 Emissions Using A Novel Grey Bernoulli Model: A Case of Shaanxi Province in China

Accurate predictions of CO₂ emissions have important practical significance for determining the best measures for reducing CO₂ emissions and accomplishing the target of reaching a carbon peak. Although some existing models have good modeling accuracy, the improvement of model specifications can provide a more accurate grasp of a system’s future and thus help relevant departments develop more effective targeting measures. Therefore, considering the shortcomings of the existing grey Bernoulli model, in this paper, the traditional model is optimized from the perspectives of the accumulation mode and background value optimization, and the novel grey Bernoulli model NFOGBM(1,1,α,β) is constructed. The effectiveness of the model is verified by using CO₂ emissions data from seven major industries in Shaanxi Province, China, and future trends are predicted. The conclusions are as follows. First, the new fractional opposite-directional accumulation and optimization methods for background value determination are effective and reasonable, and the prediction performance can be enhanced. Second, the prediction accuracy of the NFOGBM(1,1,α,β) is higher than that of the NGBM(1,1) and FANGBM(1,1). Third, the forecasting results show that under the current conditions, the CO₂ emissions generated by the production and supply of electricity and heat are expected to increase by 23.8% by 2030, and the CO₂ emissions of the other six examined industries will decline.

Optimization in the Context of COVID-19 Prediction and Control: A Literature Review

This paper presents an overview of some key results from a body of optimization studies that are specifically related to COVID-19, as reported in the literature during 2020-2021. As shown in this paper, optimization studies in the context of COVID-19 have been used for many aspects of the pandemic. From these studies, it is observed that since COVID-19 is a multifaceted problem, it cannot be studied from a single perspective or framework, and neither can the related optimization models. Four new and different frameworks are proposed that capture the essence of analyzing COVID-19 (or any pandemic for that matter) and the relevant optimization models. These are: (i) microscale vs. macroscale perspective; (ii) early stages vs. later stages perspective; (iii) aspects with direct vs. indirect relationship to COVID-19; and (iv) compartmentalized perspective. To limit the scope of the review, only optimization studies related to the prediction and control of COVID-19 are considered (public health focused), and which utilize formal optimization techniques or machine learning approaches. In this context and to the best of our knowledge, this survey paper is the first in the literature with a focus on the prediction and control related optimization studies. These studies include optimization of screening testing strategies, prediction, prevention and control, resource management, vaccination prioritization, and decision support tools. Upon reviewing the literature, this paper identifies current gaps and major challenges that hinder the closure of these gaps and provides some insights into future research directions.