Predicting the frequency of positive laboratory submissions for porcine reproductive and respiratory syndrome in Ontario, Canada, using autoregressive integrated moving average, exponential smoothing, random forest, and recurrent neural network.

Porcine Reproductive and Respiratory Syndrome Virus (PRRSV) is endemic in many pig-producing countries and poses significant health and economic challenges. Enhanced surveillance strategies are essential for effective disease management. This study aimed to evaluate and compare the performance of different time-series modeling techniques to predict weekly PRRSV-positive laboratory submissions in Ontario, Canada. Ten years of PRRSV diagnostic data were obtained from the Animal Health Laboratory at the University of Guelph and were processed into a weekly time series. The dataset was analyzed with autoregressive integrated moving average (ARIMA), exponential smoothing (ETS), random forest (RF), and recurrent neural network (RNN) models. Two validation strategies were employed: a traditional train-test split and a simulated prospective rolling forecast. Model accuracy was evaluated using common predictive error metrics. Descriptive analysis indicated a gradual increase in PRRSV positive submissions over time, with no consistent seasonal pattern. ARIMA and ETS models generally overpredict case counts, while RF and RNN tended to underpredict them. Among the evaluated models, the RF regression model most accurately captured the underlying time-series dynamics and produced the lowest prediction errors across both validation approaches. Despite outperforming other models, the RF model’s high relative prediction errors limit its suitability for accurate forecasting of PRRSV-positive submissions in Ontario’s routine surveillance system. Further data refinement and algorithm improvements are warranted.

This study aimed to explore the epidemiological characteristics of breast cancer and establish an Exponential Smoothing (ETS) and Autoregressive Integrated Moving Average (ARIMA) models to predict the development of incidence in Shantou. This study has a large sample size, strong representativeness, and wide‐ranging and comprehensive medical insurance information, which can fill the gaps in basic epidemiological research on breast cancer in Shantou. Successful completion of this study is a helpful tool to understand the epidemiology of Guangdong Province and Southern China. This study also provides data and scientific references for the government and future research on breast cancer prevention and control. This retrospective study was conducted to describe the epidemic intensity, epidemic distribution, and epidemic trend of breast cancer in Shantou, Guangdong Province, from 2006 to 2017, gathered from the Shantou's Medical Security Bureau covers the whole districts of Shantou. ETS and ARIMA models were used to describe the regional distribution, time distribution, and population distribution of breast cancer in Shantou. Moreover, based on the ARIMA model and ETS model, the incidence trend of breast cancer was predicted during 2018–2022. This study included 5,681 breast cancer patients, majority of whom were aged 50–59 years. The male‐to‐female ratio of the breast cancer patients was about 1:107 (the same ratio of the insured population was 1:1). Female patients accounted for 98.61% of the total insured population. The incidence and mortality rates of female breast cancer were 16.42/100,000 and 0.66/100,000, respectively. Based on the ARIMA model or ARIMA and ETS model, a gradually decreasing trend in the incidence of breast cancer is expected in the future. Comparing the performances of the ARIMA model and ETS model, ARIMA (4, 0, 1) (0, 1, 0) model had a lower the root mean squared error and the mean absolute percentage error than ETS (M, N) model. This population‐based retrospective study showed that the high‐risk age for the age‐specific incidence of female breast cancer was 50–55 years. It is recommended that healthcare administration should strengthen program awareness and education regarding breast cancer prevention and control. It is also possible that feasibility of extrapolating the current methodology to other future studies or broader populations in which the cancer registry data are not available.

This study conducts a comparative evaluation of the Autoregressive Integrated Moving Average (ARIMA) and Exponential Smoothing (ETS) models for forecasting China's monthly inflation rate, based on Consumer Price Index (CPI) data from December 2022 to November 2025. Within a univariate forecasting framework, both models are estimated and assessed using out-of-sample accuracy measures, including the Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Scaled Error (MASE). The empirical results consistently show that the ARIMA model, specifically the ARIMA (1,0,0) specification, outperforms the ETS model across all evaluation metrics. This advantage reflects ARIMA's effectiveness in capturing short-term persistence and lag dependence in the inflation series, rather than increased structural complexity. In contrast, the automatically selected ETS (A, N, N) model produces smoother forecast trajectories by emphasizing level-based smoothing, which provides a stable representation of underlying inflation behavior but reduces responsiveness to short-lived fluctuations. Overall, the findings highlight the importance of aligning model selection with data characteristics and forecasting objectives. While ARIMA models are better suited for short-term inflation monitoring under low-volatility conditions, ETS models may remain informative for medium- to long-term trend analysis. Limitations related to the short sample period and the univariate framework suggest avenues for future research using extended datasets and multivariate models.

In this study, based on the characteristics of the ARIMA models and ETS models, respectively, that the former focuses more on autocorrelation between data, while the latter focuses more on trends and seasonality of data sets. These two forms of models are used to forecast the USD/CNY exchange rate. This study used the monthly average USD/CNY exchange rate from January 2010 to June 2023, which taken from the website of the China Foreign Exchange Trade System (CFETS) , which data is provided by People's Bank of China, and used computer software to forecast and test the results using each model. Ultimately, it was found that the forecasts using the Autoregressive Integrated Moving Average (ARIMA) and Exponential Smoothing (ETS) models, were close to each other, with both showing a flattening trend over the long term. In the short term, ETS(M, Ad, N) forecasts an upward trend in the USD/CNY exchange rate while ARIMA(0,1,2) forecasts an almost flat trend. ARIMA (0,1,2) forecasts that the USD/CNY exchange rate shown the shape that finally stabilized at around 6.85, while ETS (M, Ad, N) forecasts around 7.6, and comparatively ARIMA model gives more reliable forecasts on the test set, and fit the training set better. This study compares the accuracy of the ETS model and the ARIMA model in fitting and subsequently forecasting the USD/CNY exchange rate for the period 2010-2023. Future research could build on this by discussing the impact of particular specific events and policies on the forecasts at this stage and experimenting with optimization.

Short-term forecast of pertussis incidence is helpful for advanced warning and planning resource needs for future epidemics. By utilizing the Auto-Regressive Integrated Moving Average (ARIMA) model and Exponential Smoothing (ETS) model as alterative models with R software, this paper analyzed data from Chinese Center for Disease Control and Prevention (China CDC) between January 2005 and June 2016. The ARIMA (0,1,0)(1,1,1)12 model (AICc = 1342.2 BIC = 1350.3) was selected as the best performing ARIMA model and the ETS (M,N,M) model (AICc = 1678.6, BIC = 1715.4) was selected as the best performing ETS model, and the ETS (M,N,M) model with the minimum RMSE was finally selected for in-sample-simulation and out-of-sample forecasting. Descriptive statistics showed that the reported number of pertussis cases by China CDC increased by 66.20% from 2005 (4058 cases) to 2015 (6744 cases). According to Hodrick-Prescott filter, there was an apparent cyclicity and seasonality in the pertussis reports. In out of sample forecasting, the model forecasted a relatively high incidence cases in 2016, which predicates an increasing risk of ongoing pertussis resurgence in the near future. In this regard, the ETS model would be a useful tool in simulating and forecasting the incidence of pertussis, and helping decision makers to take efficient decisions based on the advanced warning of disease incidence.

Background: COVID-19 has claimed the lives of millions of people in Nigeria and around the world during the last two years. It is a recognized global health crisis of our day, as well as a persistent threat to the earth. The goal of this study was to examine the trend and fit an Error Trend and Seasonal (ETS) exponential smoothing and Autoregressive Integrated Moving Average (ARIMA) model to Nigeria's COVID-19 daily fatalities.Methods: A dataset of daily COVID-19 confirmed fatality cases was used in the investigation. Data was acquired from the Nigerian Centre for Disease Control (NCDC) web database between the 10th of July 2020 and the 2nd of December 2021. The ARIMA model and twelve (12) ETS exponential smoothing techniques were investigated using a dataset of COVID-19 pandemic deaths in Nigeria. The ARIMA and ETS exponential smoothing algorithms were evaluated using the Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), Hannan Quinn Information Criterion (HQC), and Average Mean Squared Error (AMSE) selection criteria.Result: The ARIMA (0,1,0) model was the best time series modeling for the coronavirus (COVID-19) epidemic in Nigeria since it had the lowest AIC=2863.51, BIC=2866.90, HQ = 2866.90, and AMSE = 0.55471 values.Conclusion: The ARIMA (0,1,0) model is preferred above the other thirteen (13) competing models based on daily confirmed COVID-19 deaths in Nigeria. This research would assist the Nigerian government in better understanding the pestilence's evolution pattern and providing adequate provisions, prompt mediation, and treatment to prevent additional deaths caused by the virus.

Porcine reproductive and respiratory syndrome virus (PRRSV) is a prevalent pathogen that impacts the health of swine and is costly to the swine industry. This study utilized PRRSV test results from the University of Guelph's Animal Health Laboratory database to develop interactive, real-time dashboards and to monitor and investigate PRRSV data. The test results from Ontario swine herd samples submitted from January 2014 to July 2023 were processed in R v.4.1.1. The final optimized, aggregated, and anonymized datasets were exported to the Tableau server and were used to design dynamic real-time visualizations with Tableau Desktop v.2021.4. Constructed dashboards were: (1) monthly number of submissions and positive submissions over the last 10 years; (2) number of submissions and positive submissions over the last 3 years, interactively displayed at weekly, monthly, quarterly and yearly intervals; (3) monthly number of PRRSV restriction fragment length polymorphism pattern (RFLP) types at the submission level over the last 5 years; (4) weekly number of tested farms and positive farms over the last 6 Years; (5) monthly number of tested farms and positive farms over the last 6 Years; (6) indicators of the epidemiological data quality in each month; and (7) contextual information. Eighty different PRRSV RFLP patterns were identified with the predominant patterns being 1-8-4, 1-1-1, 1-4-2, and 2-5-2. Most farms contributed one submission per week or per month for PRRSV testing (median: 1 submission per week; IQR: 0; max: 13; median: 1 submission per month; IQR: 1, max: 31). Epidemiological data quality showed considerable improvements over the 9 years of investigation. Apparent changes in trends of submissions were visually observed when time series were stratified by reasons for submission and production class.

Porcine reproductive and respiratory syndrome (PRRS) was first recognized in 1987 in the United States and shortly thereafter in Europe [12, 35]. The disease has since continued to plague nearly all pig-producing countries, causing severe economic losses in the global swine industry [1, 26]. The etiological agent of PRRS, the PRRS virus (PRRSV), was isolated almost simultaneously in Europe and North America in the early 1990s [3, 6, 36]. PRRSV is a member of the family Arteriviridae including equine arteritis virus (EAV), lactate dehydrogenase-elevating virus of mice, and simian hemorrhagic fever virus, which forms the order Nidovirales along with the Coronaviridae family [5, 19, 31]. Since the emergence, PRRSV has evolved divergently on the two continents and consequently, consists of two major genotypes, European (type 1) and North American (type 2) [9, 10, 23, 28]. The two genotypes exhibits antigenic and genetic variations, sharing only about 60% sequence identity at the genome level [24, 18]. PRRSV is a small enveloped virus with a singlestranded, positive-sense RNA genome of ~15 kb in size. The PRRSV genome possesses the 5' cap structure and 3' polyadenylated tail and constitutes the 5' untranslated region (UTR), ten open reading frames (ORF1a, ORF1b, ORF2a, ORF2b, and ORFs 3 through 7 including ORF5a), and the 3' UTR [8, 11, 22, 30, 36]. The two large ORF1a and 1b occupying the 5' two-third of the genome encode the ORF1a and ORF1ab polyproteins by a ribosome frameshifting mechanism that are translated directly from the genomic RNA. The polyproteins are then autocleaved into 14 protease and replicase-associated nonstructural proteins In this study, a DNA-launched reverse genetics system was developed from a type 2 porcine reproductive and respiratory syndrome virus (PRRSV) strain, KNU-12. The complete genome of 15,412 nucleotides was assembled as a single cDNA clone and placed under the eukaryotic CMV promoter. Upon transfection of BHK-tailless pCD163 cells with a full-length cDNA clone, viable and infectious type 2 progeny PRRSV were rescued. The reconstituted virus was found to maintain growth properties similar to those of the parental virus in porcine alveolar macrophage (PAM) cells. With the availability of this type 2 PRRSV infectious clone, we first explored the biological relevance of ORF5a in the PRRSV replication cycle. Therefore, we used a PRRSV reverse genetics system to generate an ORF5a knockout mutant clone by changing the ORF5a translation start codon and introducing a stop codon at the 7 codon of ORF5a. The ORF5a knockout mutant was found to exhibit a lack of infectivity in both BHK-tailless pCD163 and PAM-pCD163 cells, suggesting that inactivation of ORF5a expression is lethal for infectious virus production. In order to restore the ORF5a gene-deleted PRRSV, complementing cell lines were established to stably express the ORF5a protein of PRRSV. ORF5a-expressing cells were capable of supporting the production of the replicationdefective virus, indicating complementation of the impaired ORF5a gene function of PRRSV in trans.

Porcine reproductive and respiratory syndrome (PRRS) is an endemic viral disease in most pig-producing countries, including Denmark. In 2022, Denmark launched a control program to reduce PRRS prevalence, with legislative changes in 2023 making testing and status reporting mandatory. The program also enforces the loss of PRRS-free status for farms that purchase pigs from non-PRRS-free sources and implements region-specific control measures to coordinate PRRS elimination within herds. However, the effectiveness of these interventions remains uncertain and requires thorough evaluation through transmission modelling and analysis of data before and after legislation changes. To understand PRRS transmission prior to legislative changes in 2023 and predict the impact of control measures, we developed a between-herd stochastic compartmental model. This model includes compartments for susceptible (S), highly infectious (Ih), lowly infectious (Il) and detected (D) pig herds, using data from 2020 to 2021. The model (i) quantifies the relative contributions of pig movements and local transmission to the spread of PRRS; (ii) generate herd-level maps of the basic reproduction (R0); and (iii) assess the effectiveness of targeted interventions for eradicating PRRS in Denmark. Model results indicated that more than 50 % of herds had an R0 greater than 1, suggesting a potential for sustained transmission if no interventions had been implemented after 2022. Both local spread and movement-mediated transmission play important roles, but local transmission drives the spatial heterogeneity in observed PRRS prevalence across Denmark. Although only 17 % of infectious herds remain undetected under current surveillance, they are responsible for 60 % of total transmission. Local control via depopulation and repopulation, is the fastest measure to reduce the observed prevalence of PRRS, but it has a lower effect on true transmission due to the hidden infections. Therefore, achieving eradication may require a combination of more frequent testing, targeted within-herd PRRS elimination and stricter risk-based trading. This study identifies PRRS hotspots and transmission routes, offering evidence-based recommendations for control.

The study embarks on an insightful journey into the world of stock indices through the deeper understanding of time series analysis application, especially during the special period of oil price volatility. The goal of this paper is to utilize sophisticated statistical models, including Autoregressive Integrated Moving Average (ARIMA) and Exponential Smoothing (ETS), to extract meaningful information from historical stock index data of S&P500 by Yahoo Finance, enhancing predictive accuracy and operating forecasts to inform strategic decision-making. In addition to the prediction results, the study also compares the forecasts of the two models through some values, and concludes that the prediction effect of the ARIMA model is better than that of the ETS model. The reason behind this result has a lot to do with the processing of the data itself and the fit of the models. For S&P500 during the period of the study, the ARIMA model’s prediction result is better. The insights derived from this analysis are expected to empower investors, researchers, and market analysts with a deeper understanding of the stock index’s past behavior and its implications for future performance.

Forecasting multicycle hollow fiber ultrafiltration fouling using time series analysis

At the onset of an infectious disease, such as the monkeypox virus (MPXV), surveillance data is crucial in keeping track of the outbreak’s progression. The surveillance data for MPXV received considerable attention after multiple European countries recorded cases. Historical data obtained from May 9, 2022, to August 10, 2022, were used to model the cumulative case trajectories of MPXV in five countries. Our study employed autoregressive integrated moving averages (ARIMA), neural network autoregression (NNETAR), exponential smoothing (ETS), and seasonal naïve regression (SNAÏVE) for training and evaluation. The paper makes the following contributions: (1) enhanced model stability with the Box-Cox transformation as a preprocessing step, (2) experimentation with both linear and non-linear models, and (3) simulation of the top five countries during the impulsive rise in cases of MPXV. The results were evaluated using three metrics: root mean square error (RMSE), mean square error (MAE), and mean absolute percentage error (MAPE). The ARIMA (0,1,3) (1,0,0)[7] model yielded the lowest percentage error of 5.16 in the holdout set for MAPE in France observations. The ETS (A, A, A) model, the lowest percentage error in the holdout set for MAE was 7.35 in Germany. Regarding the NNETAR (1,1,2) [7] model, the lowest percentage error in the holdout observations for RMSE was 8.33 in Spain, 2.75 in the United Kingdom (UK), and 8.05 in the United States of America (USA) in that order. Based on these findings, we can conclude that while the transformation proved crucial for model performance, it was not necessary for all experiments, as ARIMA remained dominant in France and the ETS model in Germany. At the same time, NNETAR model outperformed in cumulative case counts in Spain, the UK, and the USA. Our experimentation allows for early identification and contributes to a better understanding of forecasting MPXV cases using combinations of both linear and nonlinear models.

The purpose of this study is to demonstrate how to make air quality forecasting to predict the Nitrogen Dioxide quality index in the future. In this paper, we demonstrate exploratory data analysis and compare the performance of the Autoregressive Integrated Moving Average and Exponential Smoothing Model. We used R Language and R Studio to integrate all the datasets, exploratory data analysis, data preparation, performing Autoregressive Integrated Moving Average and Exponential Smoothing methods, model evaluation, and visualization. This study used data from the automatic remote air quality-monitoring station located in an urban area in Madrid, Spain. The dataset in the period from 1 January 2001 to 31 December 2017. The dataset recorded six pollutants such as Nitrogen Dioxide, Particulate Matter 10 micrometres, Sulphur Dioxide, Carbon Monoxide, Ozone and Particulate Matter 2.5 micrometres. In this study, we focus only on Nitrogen Dioxide pollutants. From our model, we saw that exponential smoothing has better accuracy compared to the Autoregressive Integrated Moving Average. We also exposed that Nitrogen Dioxide pollutant shows unhealthy for sensitive group’s level in November to March and has the lowest level in June and July.

In this paper, the consumption of wood -based panels in Iran are forecasted up to the year 2014 using statistical time series exponential smoothing and ARIMA models. The models performance was calculated in term of RMSE. ADF test was applied to investigate the stationary character of the data. The results indicated that the Holt-winters exponential smoothing model with the smallest RMSE can be selected as the best forecasting model for particleboard and plywood. The ARIMA (2,1,1) model provided the smallest RMSE and it was selected as the best forecasting model for veneer. Forecasting accuracy of the Holt-Winters model is more than the double exponential smoothing model, especially in the case of plywood. It was projected that consumption levels particleboard, veneer and plywood to increase and then decrease from 2010 to 2014 respectively. The most significant increase is forecasted in the consumption of veneer and particleboard. The average annual rates of increase are calculated as 5.1% and 1.17% for veneer and particleboard respectively. For plywood, the average annual rate of decrease is 3%. Particleboard. The consumption quantity of particleboard and veneer will increase from 684790 and 115880638 m2 in 2009 to 749428 and 206424496 in 2014 respectively. For plywood, the consumption quantity will be reduced from 32000 in 2009 to 23035 m3 in 2014.

Nowadays the new universal disease of the coronavirus that is called the epidemic COVID-19 is spread as geometric progression among the people around the world, so, such pathogen considered the most dangerous threat facing humanity. This study aimed to derive the best forecasting models for the close future cases of infected, recovered, and deaths in the four provinces of Kurdistan Region-Iraq to avoid more loss of human lives by applying more health care in certain province. Two forecasting methods were used including Exponential Smoothing and ARIMA models. The results indicate that both ARIMA and Exponential Smoothing models were close to each other for predicting the infected cases of COVID-19 in Kurdistan Region provinces, and the predicting models show that the pandemic might not be under control unless the people apply the government instructions for health care and keep social distances.