Development of artificial intelligence approach to forecasting oyster norovirus outbreaks along Gulf of Mexico coast

A Hybrid Prediction Model Based on Decomposition-Integration for Foodborne Disease Risks

Foodborne diseases (FBDs) are contagious, explosive, clustered diseases caused by the ingestion of contaminated foods, which represent huge economic and health burdens globally. Reliably predicting the risk trend of FBDs has become a major challenge in the field of public health. This study aimed to design a risk prediction model suitable for predicting FBD risks by using the decomposition-integration technique. A total of 28,646 FBD cases from FBD surveillance data reported by all sentinel hospitals in Wuxi from 2019 to 2023 were included in the study. The obtained FBD risk data were decomposed into multiple intrinsic mode functions (IMFs) using complete ensemble empirical mode decomposition with adaptive noise, which were then reconstructed by calculating the sample entropy. Finally, the time dependence of the reconstructed IMFs was explored using a temporal convolution network-long short-term memory (TCN-LSTM) model to obtain the prediction results of each component, which were then linearly added to obtain the final prediction results. Compared with other models, our proposed prediction model significantly improved the prediction accuracy of FBD risks, with a best average root mean square error of 5.349 and mean absolute error of 3.819, demonstrating at least a 40% improvement in accuracy over standalone LSTM. The FBD risk prediction results obtained by the method proposed in this study can provide data support for food safety management and policy making and enable more accurate early warning of FBDs.

A hybrid approach to study and forecast climate-sensitive norovirus infections in the USA

Norovirus, responsible for acute gastroenteritis and foodborne diseases in the United States, is influenced significantly by environmental factors. This study employs a hybrid approach to develop a foodborne disease model that incorporates indirect incidence to examine the correlation between norovirus outbreaks and environmental conditions, specifically focusing on the impact of temperature and humidity on virus transmission. By analyzing weekly average climate data and confirmed case data from four United States regions (Southern, Northeastern, Midwestern, and Western), we assess the mortality rates and estimate transmission rates using the inverse method. Our numerical results confirm that norovirus outbreaks predominantly occur in colder months. However, higher temperatures or increased humidity during warmer months appear to mitigate the spread of the virus. Utilizing climate data, this study also forecasts transmission rates and infection cases up to eight weeks in advance using a generalized boosting machine learning model.

Comprehensive analysis of predominant pathogenic bacteria and viruses in seafood products

Given the growing global demand for seafood, it is imperative to conduct a comprehensive study on the prevalence and persistence patterns of pathogenic bacteria and viruses associated with specific seafood varieties. This assessment thoroughly examines the safety of seafood products, considering the diverse processing methods employed in the industry. The importance of understanding the behavior of foodborne pathogens, such as Salmonella typhimurium, Vibrio parahaemolyticus, Clostridium botulinum, Listeria monocytogenes, human norovirus, and hepatitis A virus, is emphasized by recent cases of gastroenteritis outbreaks linked to contaminated seafood. This analysis examines outbreaks linked to seafood in the United States and globally, with a particular emphasis on the health concerns posed by pathogenic bacteria and viruses to consumers. Ensuring the safety of seafood is crucial since it directly relates to consumer preferences on sustainability, food safety, provenance, and availability. The review focuses on assessing the frequency, growth, and durability of infections that arise during the processing of seafood. It utilizes next-generation sequencing to identify the bacteria responsible for these illnesses. Additionally, it analyzes methods for preventing and intervening of infections while also considering the forthcoming challenges in ensuring the microbiological safety of seafood products. This evaluation emphasizes the significance of the seafood processing industry in promptly responding to evolving consumer preferences by offering current information on seafood hazards and future consumption patterns. To ensure the continuous safety and sustainable future of seafood products, it is crucial to identify and address possible threats.

Prediction of Foodborne Norovirus Outbreaks in Coastal Areas in China in 2008-2018

Foodborne norovirus outbreak usually poses high risks in coastal areas in China. Owing to the influence of multiple climatic factors, it demonstrates typical seasonality and the hotspots gradually expanded northwards from 2008 to 2018. However, the complex mechanism of the onset of outbreaks makes accurate prediction difficult. Thus, it is in necessity to construct a predictive model for foodborne norovirus outbreaks in coastal areas based on environmental and geographical variables. A novel predictive nonlinear autoregressive model with exogenous inputs model was developed using 11 years of environmental and foodborne norovirus outbreak data collected from coastal areas in China. Five input variables (temperature, precipitation, elevation, latitude, and longitude) were screened through stepwise regression analysis. The predicted model developed in this study was able to reproduce 88.53% of outbreaks reported to the National Public Health Emergency Event Surveillance System (PHEESS) in the model development and 100% of outbreaks reported in the independent cross-validation since the system was first launched in China. In particular, foodborne norovirus outbreaks might occur when the probability is >0.6. The findings of this study suggest that foodborne norovirus outbreaks could be accurately predicted in coastal areas in China using the developed predictive model on a daily basis. The model output is most sensitive to temperature, followed by precipitation, and locations. The application of this predictive model is promising to improve local hygiene management levels, prevent foodborne norovirus outbreaks, and reduce the disease and economic costs in coastal areas in China.

A machine learning-based universal outbreak risk prediction tool

In order to prevent and control the increasing number of serious epidemics, the ability to predict the risk caused by emerging outbreaks is essential. However, most current risk prediction tools, except EPIRISK, are limited by being designed for targeting only one specific disease and one country. Differences between countries and diseases (e.g., different economic conditions, different modes of transmission, etc.) pose challenges for building models with cross-country and cross-disease prediction capabilities. The limitation of universality affects domestic and international efforts to control and prevent pandemic outbreaks. To address this problem, we used outbreak data from 43 diseases in 206 countries to develop a universal risk prediction system that can be used across countries and diseases. This system used five machine learning models (including Neural Network XGBoost, Logistic Boost, Random Forest and Kernel SVM) to predict and vote together to make ensemble predictions. It can make predictions with around 80%-90 % accuracy from economic, cultural, social, and epidemiological factors. Three different datasets were designed to test the performance of ML models under different realistic situations. This prediction system has strong predictive ability, adaptability, and generality. It can give universal outbreak risk assessment that are not limited by border or disease type, facilitate rapid response to pandemic outbreaks, government decision-making and international cooperation.

Prediction of Xe/Kr Separation in Metal-Organic Frameworks by a Precursor-Based Neural Network Synergistic with a Polarizable Adsorbate Model

Adsorption and separation of Xe/Kr are significant for making high-density nuclear energy environmentally friendly and for meeting the requirements of the gas industry. Enhancing the accuracy of the adsorbate model for describing the adsorption behaviors of Xe and Kr in MOFs and the efficiency of the model for predicting the separation potential (SP) value of Xe/Kr separation in MOFs helps in searching for promising MOFs for Xe/Kr adsorption and separation within a short time and at a low cost. In this work, polarizable and transferable models for mimic Xe and Kr adsorption behaviors in MOFs were constructed. Using these models, SP values of 38 MOFs at various temperatures and pressures were calculated. An optimal neural network model called BPNN-SP was designed to predict SP value based on physical parameters of metal center (electronegativity and radius) and organic linker (three-dimensional size and polarizability) combined with temperature and pressure. The regression coefficient value of the BPNN-SP model for each data set is higher than 0.995. MAE, MBE, and RMSE of BPNN-SP are only 0.331, -0.002, and 0.505 mmol/g, respectively. Finally, BPNN-SP was validated by experiment data from six MOFs. The transferable adsorbate model combined with the BPNN-SP model would highly improve the efficiency for designing MOFs with high performance for Xe/Kr adsorption and separation.

A Social Network Analysis Approach to Evaluate the Relationship Between the Mobility Network Metrics and the COVID-19 Outbreak

The emergence of the new coronavirus in late 2019 further highlighted the human need for solutions to explore various aspects of deadly pandemics. Providing these solutions will enable humans to be more prepared for dealing with possible future pandemics. In addition, it helps governments implement strategies to tackle and control infectious diseases similar to COVID-19 faster than ever before. In this article, we used the social network analysis (SNA) method to identify high-risk areas of the new coronavirus in Iran. First, we developed the mobility network through the transfer of passengers (edges) between the provinces (nodes) of Iran and then evaluated the in-degree and page rank centralities of the network. Next, we developed 2 Poisson regression (PR) models to predict high-risk areas of the disease in different populations (moderator) using the mobility network centralities (independent variables) and the number of patients (dependent variable). The P-value of .001 for both prediction models confirmed a meaningful interaction between our variables. Besides, the PR models revealed that in higher populations, with the increase of network centralities, the number of patients increases at a higher rate than in lower populations, and vice versa. In conclusion, our method helps governments impose more restrictions on high-risk areas to handle the COVID-19 outbreak and provides a viable solution for accelerating operations against future pandemics similar to the coronavirus.

Multi-region machine learning-based novel ensemble approaches for predicting COVID-19 pandemic in Africa

Coronavirus disease 2019 (COVID-19) has produced a global pandemic, which has devastating effects on health, economy and social interactions. Despite the less contraction and spread of COVID-19 in Africa compared to some other continents in the world, Africa remains amongst the most vulnerable regions due to less technology and unequipped or poor health system. Recent happenings showed that COVID-19 may stay for years owing to the discoveries of new variants (such as Omicron) and new wave of infections in several countries. Therefore, accurate prediction of new cases is vital to make informed decisions and in evaluating the measures that should be implemented. Studies on COVID-19 prediction are limited in Africa despite the risks and dangers that the virus possessed. Hence, this study was performed to predict daily COVID-19 cases in 10 African countries spread across the north, south, east, west and central Africa considering countries with few and large number of daily COVID-19 cases. Machine learning (ML) models due to their nonlinearity and accurate prediction capabilities were employed for this purpose, including artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), support vector machine (SVM) and conventional multiple linear regression (MLR) models. As any other natural process, the COVID-19 pandemic may contain both linear and nonlinear aspects. In such circumstances, neither nonlinear (ML) nor linear (MLR) models could be sufficient; hence, combining both ML and MLR models may produce better accuracy. Consequently, to improve the prediction efficiency of the ML models, novel ensemble approaches including ANN-E and SVM-E were employed. The advantage of using ensemble approaches is that they provide collective benefits of all the standalone models, thereby reducing their weaknesses and enhancing their prediction capabilities. The obtained results showed that ANFIS led to better prediction performance with MAD = 0.0106, MSE = 0.0003, RMSE = 0.0185 and R2 = 0.9059 in the validation step. The results of the proposed ensemble approaches demonstrated very high improvements in predicting the COVID-19 pandemic in Africa with MAD = 0.0073, MSE = 0.0002, RMSE = 0.0155 and R2 = 0.9616. The ANN-E improved the standalone models performance in the validation step up to 10%, 14%, 42%, 6%, 83%, 11%, 7%, 5%, 7% and 31% for Morocco, Sudan, Namibia, South Africa, Uganda, Rwanda, Nigeria, Senegal, Gabon and Cameroon, respectively. This study results offer a solid foundation in the application of ensemble approaches for predicting COVID-19 pandemic across all regions and countries in the world.

Deep learning-based ensemble modeling of Vibrio parahaemolyticus concentration in marine environment

Vibrio parahaemolyticus (V.p) is a marine pathogenic bacterium that poses a high risk to human health and shellfish industry, yet an effective regional-scale nowcasting model for managing the risk remains lacking. This study presents the first regional-scale model for nowcasting the level of V.p in oysters in the marine environment by developing an ensemble modeling approach. The ensemble modeling approach involves the integration of genetic programming (GP) and deep artificial neural networks (DNN)-based modeling. The new approach was demonstrated by developing three GP-DNN ensemble models for predicting the V.p level in North Carolina, New Hampshire, and the combined region. Specifically, GP was employed to establish nonlinear functions between the V.p level and antecedent conditions of environmental variables. The nonlinear GP functions and current conditions of individual environmental variables were then utilized as inputs into a DNN model, forming a GP-DNN ensemble model. Modeling results indicated that the GP-DNN ensemble models were capable of predicting the V.p level with the correlation coefficient of 0.91, 0.90, and 0.80 for North Carolina, New Hampshire, and the combined region, respectively, demonstrating the impact of distinct environmental conditions in the local areas on accuracy of the combined regional-scale model. Sensitivity analysis results showed that sea surface temperature and sea surface salinity are the two most important environmental predictors for the abundance of V.p in oysters, followed by water level, pH, chlorophyll-a, and turbidity. The findings suggested that the GP-DNN ensemble models could be utilized as effective predictive tools for mitigating the V.p risk.

Early detection of norovirus outbreak using machine learning methods in South Korea

BACKGROUND

The norovirus is a major cause of acute gastroenteritis at all ages but particularly has a high chance of affecting children under the age of five. Given that the outbreak of norovirus in Korea is seasonal, it is important to try and predict the start and end of norovirus outbreaks.

METHODS

We predicted weekly norovirus warnings using six machine learning algorithms using test data from 2017 to 2018 and training data from 2009 to 2016. In addition, we proposed a novel method for the early detection of norovirus using a calculated norovirus risk index. Further, feature importance was calculated to evaluate the contribution of the estimated weekly norovirus warnings.

RESULTS

The long short-term memory machine learning (LSTM) algorithm proved to be the best algorithm for predicting weekly norovirus warnings, with 97.2% and 92.5% accuracy in the training and test data, respectively. The LSTM algorithm predicted the observed start and end weeks of the early detection of norovirus within a 3-week range.

CONCLUSIONS

The results of this study show that early detection can provide important insights for the preparation and control of norovirus outbreaks by the government. Our method provides indicators of high-risk weeks. In particular, last norovirus detection rate, minimum temperature, and day length, play critical roles in estimating weekly norovirus warnings.

Evaluation of prediction models for the malaria incidence in Marodijeh Region, Somaliland

Malaria is a major public health concern in tropics and subtropics. Accurate malaria prediction is critical for reporting ongoing incidences of infection and its control. Hence, the purpose of this investigation was to evaluate the performances of different models of predicting malaria incidence in Marodijeh region, Somaliland. The study used monthly historical data from January 2011 to December 2020. Five deterministic and stochastic models, i.e. Seasonal Autoregressive Moving Average (SARIMA), Holt-Winters' Exponential Smoothing, Harmonic Model, Seasonal and Trend Decomposition using Loess (STL) and Artificial Neural Networks (ANN), were fitted to the malaria incidence data. The study employed Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Scaled Error (MASE) to measure the accuracy of each model. The results indicated that the artificial neural network (ANN) model outperformed other models in terms of the lowest values of RMSE (39.4044), MAE (29.1615), MAPE (31.3611) and MASE (0.6618). The study also incorporated three meteorological variables (Humidity, Rainfall and Temperature) into the ANN model. The incorporation of these variables into the model enhanced the prediction of malaria incidence in terms of achieving better prediction accuracy measures (RMSE = 8.6565, MAE = 6.1029, MAPE = 7.4526 and MASE = 0.1385). The 2-year generated forecasts based on the ANN model implied a significant increasing trend. The study recommends the ANN model for forecasting malaria cases and for taking the steps to reduce malaria incidence during the times of year when high incidence is reported in the Marodijeh region.

Empirical Study on Classifiers for Earlier Prediction of COVID-19 Infection Cure and Death Rate in the Indian States

Machine Learning methods can play a key role in predicting the spread of respiratory infection with the help of predictive analytics. Machine Learning techniques help mine data to better estimate and predict the COVID-19 infection status. A Fine-tuned Ensemble Classification approach for predicting the death and cure rates of patients from infection using Machine Learning techniques has been proposed for different states of India. The proposed classification model is applied to the recent COVID-19 dataset for India, and a performance evaluation of various state-of-the-art classifiers to the proposed model is performed. The classifiers forecasted the patients’ infection status in different regions to better plan resources and response care systems. The appropriate classification of the output class based on the extracted input features is essential to achieve accurate results of classifiers. The experimental outcome exhibits that the proposed Hybrid Model reached a maximum F1-score of 94% compared to Ensembles and other classifiers like Support Vector Machine, Decision Trees, and Gaussian Naïve Bayes on a dataset of 5004 instances through 10-fold cross-validation for predicting the right class. The feasibility of automated prediction for COVID-19 infection cure and death rates in the Indian states was demonstrated.

Short-Term Impacts of Meteorology, Air Pollution, and Internet Search Data on Viral Diarrhea Infection among Children in Jilin Province, China

The influence of natural environmental factors and social factors on children’s viral diarrhea remains inconclusive. This study aimed to evaluate the short-term effects of temperature, precipitation, air quality, and social attention on children’s viral diarrhea in temperate regions of China by using the distribution lag nonlinear model (DLNM). We found that low temperature affected the increase in children’s viral diarrhea infection for about 1 week, while high temperature and heavy precipitation affected the increase in children’s viral diarrhea infection risk for at least 3 weeks. As the increase of the air pollution index may change the daily life of the public, the infection of children’s viral diarrhea can be restrained within 10 days, but the risk of infection will increase after 2 weeks. The extreme network search may reflect the local outbreak of viral diarrhea, which will significantly improve the infection risk. The above factors can help the departments of epidemic prevention and control create early warnings of high-risk outbreaks in time and assist the public to deal with the outbreak of children’s viral diarrhea.

Understanding the spatiotemporal pollution dynamics of highly fragile montane watersheds of Kashmir Himalaya, India

Pollution of riverine ecosystems through the multidimensional impact of human footprints around the world poses a serious challenge. Research studies that communicate potential repercussions of landscape structure metrics on snowmelt riverine water quality particularly, in climatically fragile Himalayan watersheds are very scarce. Though, worldwide, grasping the influence of land-use practices on water quality (WQ) has received renewed attention yet, the relevance of spatial scale linked to landscape pattern is still elusive due to its heterogenic nature across diverse geomorphic regions. In this work, therefore, we tried to capture the insights on landscape-aquascape interface by juxtapositioning the impacts of landscape structure pattern on snowmelt stream WQ of the whole Jhelum River Basin (JRB) under three varying spatial scales viz., watershed scale, riparian corridor (1000 m wide) and reach buffer (500 m wide). The percentage of landscape pattern composition and configuration metrics in the JRB were computed in GIS utilizing Landsat-8 OLI/TIRS satellite image having 30 m resolution. To better explicate the influence of land-use metrics on riverine WQ with space and time, we used Redundancy analysis (RDA) and multilinear regression (MLR) modeling. MLR selected land-use structure metrics revealed the varied response of WQ parameters to multi-scale factors except for total faecal coliform bacteria (TC) which showed perpetual presence. The reach-scale explained slightly better (76%) variations in WQ than riparian (75%) and watershed (70%) scales. Likewise, across seasonal scale, autumn (75%), winter (83%), and summer (77%) captured the most WQ variation at catchment, riparian, and reach scales respectively. We observed impairing WQ linkages with agriculture, built-up and barren rocky areas across watersheds, besides, pastures in riparian buffer areas, and fragmentation of landscape patches at the reach scale. Due to little appearance of spatial scale differences, a multi scale perspective landscape planning is emphasized to ensure future sustainability of Kashmir Himalayan water resources.

Coastal management – working towards the UN’s Decade of Ocean Science for Sustainable Development (2021–2030)

The UN declared 2021-2030 as the Decade of Ocean Science and identified research and technology priority areas to achieve the 2030 Sustainable Development Goals. We reviewed the current status of scientific support for coastal management in South Africa within the context of these priorities and found promising development. However, challenges for the next decade remain, such as rolling out pilot projects into sustainable, national-scale programmes, facilitating greater collaboration and coordination among scientific role players, and achieving long-term commitment and political will for dedicated financial support. Through our lens as natural scientists we focused on the ecological system and coupling with the social system; however scientific support on better characterisation and understanding of the dynamics within the social system is also critical as sustainable development relies heavily on the willingness of the social system to embrace and execute related policies.

Hybrid modeling and prediction of oyster norovirus outbreaks

This paper presents a hybrid model for predicting oyster norovirus outbreaks by combining the Artificial Neural Networks (ANNs) and Principal Component Analysis (PCA) methods and using the Moderate Resolution Imaging Spectroradiometer (MODIS) satellite remote-sensing data. Specifically, 10 years (2007-2016) of cloud-free MODIS Aqua data for water leaving reflectance and environmental data were extracted from the center of each oyster harvest area. Then, the PCA was utilized to compress the size of the MODIS Aqua data. An ANN model was trained using the first 4 years of the data from 2007 to 2010 and validated using the additional 6 years of independent datasets collected from 2011 to 2016. Results indicated that the hybrid PCA-ANN model was capable of reproducing the 10 years of historical oyster norovirus outbreaks along the Northern Gulf of Mexico coast with a sensitivity of 72.7% and specificity of 99.9%, respectively, demonstrating the efficacy of the hybrid model.

Modeling and Forecasting Vibrio Parahaemolyticus Concentrations in Oysters

Vibrio parahaemolyticus (V.p) is an epidemiologically significant pathogen that thrives in coastal waters where oysters are harvested, posing high risks to human health and shellfish industry and requiring effective forecasting models for emergency preparedness and interventions. This study sought to develop forecasting models with differing lead times, which are able to predict the level of V.p in oysters in advance to mitigate the health risk to the general public and the economic loss to the shellfish industry. The Random Forest method along with 227 sampling datasets from two different geographic locations were utilized to: (1) Identify the most critical environmental predictors controlling the level of V.p in oysters, (2) Select the most important time lags for the environmental predictors as model input variables, and (3) Develop four forecasting models (RF-1Day, RF-2Day, RF-3Day, and RF-4Day) with the lead time of one to four days. The uncertainty involved in model predictions was quantified using the bootstrapping method. Results showed that V.p abundance in oysters is controlled by antecedent environmental conditions 1-11 days before. The antecedent environmental conditions can be described using time-lagged Sea Surface Temperature (SST) and salinity. The V.p abundance can well be forecasted 1 - 4 days in advance using the four models. The performance of the models decreases with increasing lead time. The RF-3Day and RF-4Day models can be employed primarily for emergency preparedness due to their relatively long lead time while the RF-1Day and RF-2Day models can be used primarily for management interventions due to their relatively high predictive performance.

COVID-19: A Review on the Novel Coronavirus Disease Evolution, Transmission, Detection, Control and Prevention

Three major outbreaks of the coronavirus, a zoonotic virus known to cause respiratory disease, have been reported since 2002, including SARS-CoV, MERS-CoV and the most recent 2019-nCoV, or more recently known as SARS-CoV-2. Bats are known to be the primary animal reservoir for coronaviruses. However, in the past few decades, the virus has been able to mutate and adapt to infect humans, resulting in an animal-to-human species barrier jump. The emergence of a novel coronavirus poses a serious global public health threat and possibly carries the potential of causing a major pandemic outbreak in the naïve human population. The recent outbreak of COVID-19, the disease caused by SARS-CoV-2, in Wuhan, Hubei Province, China has infected over 36.5 million individuals and claimed over one million lives worldwide, as of 8 October 2020. The novel virus is rapidly spreading across China and has been transmitted to 213 other countries/territories across the globe. Researchers have reported that the virus is constantly evolving and spreading through asymptomatic carriers, further suggesting a high global health threat. To this end, current up-to-date information on the coronavirus evolution and SARS-CoV-2 modes of transmission, detection techniques and current control and prevention strategies are summarized in this review.

COVID-19: A Review on the Novel Coronavirus Disease Evolution, Transmission, Detection, Control and Prevention

Three major outbreaks of the coronavirus, a zoonotic virus known to cause respiratory disease, have been reported since 2002, including SARS-CoV, MERS-CoV and the most recent 2019-nCoV, or more recently known as SARS-CoV-2. Bats are known to be the primary animal reservoir for coronaviruses. However, in the past few decades, the virus has been able to mutate and adapt to infect humans, resulting in an animal-to-human species barrier jump. The emergence of a novel coronavirus poses a serious global public health threat and possibly carries the potential of causing a major pandemic outbreak in the naïve human population. The recent outbreak of COVID-19, the disease caused by SARS-CoV-2, in Wuhan, Hubei Province, China has infected over 36.5 million individuals and claimed over one million lives worldwide, as of 8 October 2020. The novel virus is rapidly spreading across China and has been transmitted to 213 other countries/territories across the globe. Researchers have reported that the virus is constantly evolving and spreading through asymptomatic carriers, further suggesting a high global health threat. To this end, current up-to-date information on the coronavirus evolution and SARS-CoV-2 modes of transmission, detection techniques and current control and prevention strategies are summarized in this review.

COVID-19 Outbreak Prediction with Machine Learning

Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and these models are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models need to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak as an alternative to susceptible–infected–recovered (SIR) and susceptible-exposed-infectious-removed (SEIR) models. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP; and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior across nations, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research. This paper further suggests that a genuine novelty in outbreak prediction can be realized by integrating machine learning and SEIR models.

Determinants of the infection rate of the COVID-19 in the U.S. using ANFIS and virus optimization algorithm (VOA)

Recently, anovel coronavirus disease (COVID-19) has become a serious concern for global public health. Infectious disease outbreaks such as COVID-19 can also significantly affect the sustainable development of urban areas. Several factors such as population density and climatology parameters could potentially affect the spread of the COVID-19. In this study, a combination of the virus optimization algorithm (VOA) and adaptive network-based fuzzy inference system (ANFIS) was used to investigate the effects of various climate-related factors and population density on the spread of the COVID-19. For this purpose, data on the climate-related factors and the confirmed infected cases by the COVID-19 across the U.S counties was used. The results show that the variable defined for the population density had the most significant impact on the performance of the developed models, which is an indication of the importance of social distancing in reducing the infection rate and spread rate of the COVID-19. Among the climatology parameters, an increase in the maximum temperature was found to slightly reduce the infection rate. Average temperature, minimum temperature, precipitation, and average wind speed were not found to significantly affect the spread of the COVID-19 while an increase in the relative humidity was found to slightly increase the infection rate. The findings of this research show that it could be expected to have slightly reduced infection rate over the summer season. However, it should be noted that the models developed in this study were based on limited one-month data. Future investigation can benefit from using more comprehensive data covering a wider range for the input variables.

Enhanced Gaussian process regression-based forecasting model for COVID-19 outbreak and significance of IoT for its detection

Virus based epidemic is one of the speedy and widely spread infectious disease which can affect the economy of the country as well as it is life-threatening too. So, there is a need to forecast the epidemic lifespan, which can help us in taking preventive measures and remedial action on time. These preventive measures and corrective action may consist of closing schools, closing malls, closing theaters, sealing of borders, suspension of public services, and suspension of traveling. Resuming such restrictions is depends upon the outbreak momentum and its decay rate. The accurate forecasting of the epidemic lifespan is one of the enormously essential and challenging tasks. It is a challenging task because the lack of knowledge about the novel virus-based diseases and its consequences with complicated societal-governmental factors can influence the widespread of this newly born disease. At this stage, any forecasting can play a vital role, and it will be reliable too. As we know, the novel virus-based diseases are in a growing phase, and we also do not have real-time data samples. Thus, the biggest challenge is to find out the machine learning-based best forecasting model, which could offer better forecasting with the limited training samples. In this paper, the Multi-Task Gaussian Process (MTGP) regression model with enhanced predictions of novel coronavirus (COVID-19) outbreak is proposed. The purpose of the proposed MTGP regression model is to predict the COVID-19 outbreak worldwide. It will help the countries in planning their preventive measures to reduce the overall impact of the speedy and widely spread infectious disease. The result of the proposed model has been compared with the other prediction model to find out its suitability and correctness. In subsequent analysis, the significance of IoT based devices in COVID-19 detection and prevention has been discussed.

Spatiotemporal variability and key influencing factors of river fecal coliform within a typical complex watershed

Fecal coliform bacteria are a key indicator of human health risks; however, the spatiotemporal variability and key influencing factors of river fecal coliform have yet to be explored in a rural-suburban-urban watershed with multiple land uses. In this study, the fecal coliform concentrations in 21 river sections were monitored for 20 months, and 441 samples were analyzed. Multivariable regressions were used to evaluate the spatiotemporal dynamics of fecal coliform. The results showed that spatial differences were mainly dominated by urbanization level, and environmental factors could explain the temporal dynamics of fecal coliform in different urban patterns except in areas with high urbanization levels. Reducing suspended solids is a direct way to manage fecal coliform in the Beiyun River when the natural factors are difficulty to change, such as temperature and solar radiation. The export of fecal coliform from urban areas showed a quick and sensitive response to rainfall events and increased dozens of times in the short term. Landscape patterns, such as the fragmentation of impervious surfaces and the overall landscape, were identified as key factors influencing urban non-point source bacteria. The results obtained from this study will provide insight into the management of river fecal pollution.

COVID-19 Pandemic Prediction for Hungary; A Hybrid Machine Learning Approach

Several epidemiological models are being used around the world to project the number of infected individuals and the mortality rates of the COVID-19 outbreak. Advancing accurate prediction models is of utmost importance to take proper actions. Due to the lack of essential data and uncertainty, the epidemiological models have been challenged regarding the delivery of higher accuracy for long-term prediction. As an alternative to the susceptible-infected-resistant (SIR)-based models, this study proposes a hybrid machine learning approach to predict the COVID-19, and we exemplify its potential using data from Hungary. The hybrid machine learning methods of adaptive network-based fuzzy inference system (ANFIS) and multi-layered perceptron-imperialist competitive algorithm (MLP-ICA) are proposed to predict time series of infected individuals and mortality rate. The models predict that by late May, the outbreak and the total morality will drop substantially. The validation is performed for 9 days with promising results, which confirms the model accuracy. It is expected that the model maintains its accuracy as long as no significant interruption occurs. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research.

A novel model for malaria prediction based on ensemble algorithms

BACKGROUND AND OBJECTIVE

Most previous studies adopted single traditional time series models to predict incidences of malaria. A single model cannot effectively capture all the properties of the data structure. However, a stacking architecture can solve this problem by combining distinct algorithms and models. This study compares the performance of traditional time series models and deep learning algorithms in malaria case prediction and explores the application value of stacking methods in the field of infectious disease prediction.

METHODS

The ARIMA, STL+ARIMA, BP-ANN and LSTM network models were separately applied in simulations using malaria data and meteorological data in Yunnan Province from 2011 to 2017. We compared the predictive performance of each model through evaluation measures: RMSE, MASE, MAD. In addition, gradient-boosting regression trees (GBRTs) were used to combine the above four models. We also determined whether stacking structure improved the model prediction performance.

RESULTS

The root mean square errors (RMSEs) of the four sub-models were 13.176, 14.543, 9.571 and 7.208; the mean absolute scaled errors (MASEs) were 0.469, 0.472, 0.296 and 0.266 and the mean absolute deviation (MAD) were 6.403, 7.658, 5.871 and 5.691. After using the stacking architecture combined with the above four models, the RMSE, MASE and MAD values of the ensemble model decreased to 6.810, 0.224 and 4.625, respectively.

CONCLUSIONS

A novel ensemble model based on the robustness of structured prediction and model combination through stacking was developed. The findings suggest that the predictive performance of the final model is superior to that of the other four sub-models, indicating that stacking architecture may have significant implications in infectious disease prediction.

Presence and Distribution of Histo-Blood Group Antigens in Pacific Oysters and the Effects of Exposure to Noroviruses GI.3 and GII.4 on Their Expression

Noroviruses (NoVs) are one of the most important foodborne viral pathogens worldwide. Oysters are common carriers of NoVs and are responsible for their transmission. NoVs recognize human histo-blood group antigens (HBGAs) as receptors. Recent studies indicate that HBGA-like molecules also exist in oyster tissues and that they may play a key role in the binding of NoVs. However, the mechanism by which different genotypes of NoV accumulate in different oyster tissues is unknown. In this study, the presence and distribution of different types of HBGA-like molecules were evaluated in 240 oysters collected from the Shandong Peninsula of People's Republic of China for 1 year. The HBGA-like molecules were detected at various rates and expressed at different levels in different tissues. Immunohistochemistry confirmed the diversity of HBGA-like molecules in four oyster tissues. Eight types of HBGA-like molecules (types A, B, H1, Lewis x, Lewis y, Lewis a, Lewis b, and precursor) were assessed in different tissues. Of these, the type A HBGA-like molecule was consistently expressed in the gills, digestive tissue, and mantle, while types H1 and Lewis b HBGA-like molecules were expressed in the digestive tissues. The expression of HBGA-like molecules in response to the NoV challenge was investigated. The levels of types A, H1, and Lewis x increased significantly in specific oyster tissues after exposure to genogroup II, genotype 4 (GII.4) or genogroup I, genotype 3 (GI.3) NoV. The real-time reverse transcription PCR assays indicated that GI.3 NoV mainly accumulated in the digestive tissues of oysters, whereas GII.4 NoV accumulated in the gills, mantle, and digestive tissues. These results provide new insights into the mechanism of NoV bioaccumulation in oysters and suggest that NoV accumulation in oysters may be related to the expression of HBGA-like molecules.