Exponential Smoothing Model Research Articles

Exponential Smoothing Models, Support for Analysis of the Mountain Regions Livestock: Evidence from Romania

Exponential Smoothing Models, Support for Analysis of the Mountain Regions Livestock: Evidence from Romania

Formulasi Model Perencanaan Penjualan Produk PD.Tataka Sumber Sentosa Berdasarkan Metode Peramalan

This study aims to formulate a product sales planning model at Pd. Tataka Sumber Sentosa uses the right forecasting method. Forecasting method is the key in confirming. In this study an analysis of the products was carried out, namely buis concrete and u-ditch. Data analysis is used as a basis for analyzing using forecasting methods such as the Moving Average, Exponential Smoothing, and Linear Trend Line Models of product sales planning formulation results. It can be concluded from the three forecasting models that the best is forecasting a 40 cm concrete bus with the Linear Trend Line Model results the error value of the 40 cm concrete buis with the Linear Trend Line Model is the value of MAD = 1.19, MSE = 2.048, MAPE = 2.412, and it can be concluded that the next forecast = 52 then the forecasting model chosen to determine forecasts for the next 6 months using the Linear Trend Line Model. Because the results of the analysis show that historical sales data and analyzing market demand trends are important steps in selecting the appropriate forecasting model.

Identification of stock market manipulation using a hybrid ensemble approach

Anomaly detection in time series data is a complex data mining issue with many useful, real-world applications. Anomalies in datasets represent deviations in the expected behaviour of a system and can indicate rare but significant events that require intervention. Market manipulation is a serious issue in financial jurisdictions worldwide, with financial regulators such as the SEC constantly trying to prevent it and prosecute those guilty of it. This paper makes use of state-of-the-art deep learning techniques as well as more classical statistical techniques in order to detect anomalies in five real-world datasets. The predictions of these models are then aggregated in two different ensemble models. The results of the individual models as well as the ensemble models, are evaluated, and F1-Score measures performance. Nine individual models, consisting of three models based on LSTM with Dynamic Thresholding, three ARIMA models and three Exponential Smoothing models, were used to generate predictions of anomalies based on daily trading volumes. The individual predictions of these models were then aggregated, with two different ensemble methods being used, namely the majority voting ensemble method and the ensemble averaging aggregation method. While both performed well, the majority voting ensemble method was seen to be the superior method in this study, with an average F1Score of 0.494, compared to an F1Score of 0.414 for the ensemble averaging aggregation method.

Forecasting Trends of Safety Performance Indicators in Aviation

The article concerns the issues of forecasting trends of safety performance indicators (SPIs)in civil aviation. The main objective was to present a proposal for the method of forecasting trends in air traffic safety performance indicators in the future. For this purpose, a SPI forecasting method based on Holt's exponential smoothing model was proposed. To confirm the correctness of the proposed method, a selected, sample safety performance indicator for Airspace Infringement occurrences was forecasted. An analysis of the obtained results was carried out, as well as the directions of further research in this area were presented. The article discusses also the issues of forecasting development trends of selected safety performance indicators and their variability over time for the Polish airspace.

Comparison of SARIMA model, Holt-winters model and ETS model in predicting the incidence of foodborne disease

BackgroundAccording to the World Health Organization, foodborne disease is a significant public health issue. We will choose the best model to predict foodborne disease by comparison, to provide evidence for government policies to prevent foodborne illness.MethodsThe foodborne disease monthly incidence data from June 2017 to April 2022 were obtained from the Chongqing Nan’an District Center for Disease Prevention and Control. Data from June 2017 to June 2021 were used to train the model, and the last 10 months of incidence were used for prediction and validation The incidence was fitted using the seasonal autoregressive integrated moving average (SARIMA) model, Holt-Winters model and Exponential Smoothing (ETS) model. Besides, we used MSE, MAE, RMSE to determine which model fits better.ResultsDuring June 2017 to April 2022, the incidence of foodborne disease showed seasonal changes, the months with the highest incidence are June to November. The optimal model of SARIMA is SARIMA (1,0,0) (1,1,0)12. The MSE, MAE, RMSE of the Holt-Winters model are 8.78, 2.33 and 2.96 respectively, which less than those of the SARIMA and ETS model, and its prediction curve is closer to the true value. The optimal model has good predictive performance.ConclusionBased on the results, Holt-Winters model produces better prediction accuracy of the model.

Forecasting a museum visit post pandemic using exponential smoothing model

This paper aims to evaluate the performance of a machine learning model for predicting the number of visitors to a museum after the COVID-19 pandemic. The easing of policies that began to be implemented by the Palembang city government after the end of the pandemic at the end of 2022 became a momentum in predicting the number of visits to the SMBII museum. During the pandemic the museum experienced a very drastic decline due to closures and restrictions on activities at the museum and had an impact on achieving the museum's targets in the fields of tourism and education. Museum managers need to establish a strategy as an effort to achieve the targets set during the post-pandemic period. This study predicts the number of visits to the SMBII museum in post-pandemic years by applying the double exponential smoothing (ESM) model. The dataset used is SMBII museum visit data which is divided into three categories of visitors, namely students, local and foreign. The evaluation results show that the double ESM model has the best performance with MSE = 3.8 and a = 0.9. The phenomena that occurred in the student visitor category affected ESM's performance in predicting visits where MSE in the post-pandemic period had a 200% higher value than before the pandemic which was influenced by the implementation of post-pandemic policies in museums. With the forecasting results in this study, it is hoped that it can become information in developing strategies and improving the performance of post-pandemic museums

Forecasting performance of machine learning, time series, and hybrid methods for low‐ and high‐frequency time series

One of the main objectives of the time series analysis is forecasting, so both Machine Learning methods and statistical methods have been proposed in the literature. In this study, we compare the forecasting performance of some of these approaches. In addition to traditional forecasting methods, which are the Naive and Seasonal Naive Methods, S/ARIMA, Exponential Smoothing, TBATS, Bayesian Exponential Smoothing Models with Trend Modifications and STL Decomposition, the forecasts are also obtained using seven different machine learning methods, which are Random Forest, Support Vector Regression, XGBoosting, BNN, RNN, LSTM, and FFNN, and the hybridization of both statistical time series and machine learning methods. The data set is selected proportionally from various time domains in M4 Competition data set. Thereby, we aim to create a forecasting guide by considering different preprocessing approaches, methods, and data sets having various time domains. After the experiment, the performance and impact of all methods are discussed. Therefore, most of the best models are mainly selected from machine learning methods for forecasting. Moreover, the forecasting performance of the model is affected by both the time frequency and forecast horizon. Lastly, the study suggests that the hybrid approach is not always the best model for forecasting. Hence, this study provides guidelines to understand which method will perform better at different time series frequencies.

Forecasting Georgia Economic Growth 2020-2030

Firms, households, government agencies, and non-government organizations rely on forecasts when making decisions regarding the allocation of scarce resources. This paper develops evidence-based forecasts for key macroeconomic variables for the Republic of Georgia. Sources of data include the International Monetary Fund’s World Economic Outlook, The World Bank, and others. We use, primarily, exponential smoothing models generated by the statistical application Forecast Pro 100 to generate forecasts with 95 percent confidence limits. Finally, recognizing the high degree of uncertainty associated with long-term forecasting, we include scenarios to generate high, middle, and low values for the key variables. Our analysis shows population, a key economic resource, to be declining, along with the labor force participation rate, after a considerable rise. Gross fixed capital formation appears to be rising, while total reserves (including gold) is holding steady. With real GDP rising at an average rate of about five percent over the past decade, our forecast shows GDP continuing to increase over the next decade, along with GDP per capita, indicating a rising level of general wellbeing. Georgia’s inflation rate is low, and there is no credible evidence that the rate of inflation will accelerate in the coming years. We develop three scenarios for economic growth for Georgia for the period 2020-2030. All three scenarios – low, medium, and high–show continued healthy growth.

Forecasting multicycle hollow fiber ultrafiltration fouling using time series analysis

This study proposes the application of time series analysis and exponential smoothing (ETS) to predict multicycle membrane fouling with high accuracy and great interpretability. First, lab-scale filtration tests were performed with foulant surrogates to assess the potential of ETS models in predicting multicycle membrane fouling. Two models, ETS (A,A,A) and ETS (A,A,M), were found to be most suitable for describing the variation of transmembrane pressure. The ETS (A,A,A) model showed a slight edge over the ETS (A,A,M) model when reversible fouling was dominant. In contrast, the ETS (A,A,M) performed better when irreversible fouling was prevalent. Then, the effectiveness of ETS models in multicycle forecasting during the filtration of natural water resources was evaluated. Residual mean squared errors between 0.02 bar and 0.15 bar were obtained for horizons going from 2 up to 10 filtration cycles. Finally, ETS models were applied to predict the variation in permeability of drinking water treatment plant membrane skid. A three-month dataset was utilized to predict the next 41 days of permeability variation, yielding an average error of 3.2 %. Along with that, a web application designed to assist membrane users in utilizing ETS was developed and presented at the end. The web application can be accessed through the following link: https://fouling-ets.shinyapps.io/shiny-ets-forecasting/.

Monthly Runoff Prediction by Combined Models Based on Secondary Decomposition at the Wulong Hydrological Station in the Yangtze River Basin

Accurate runoff prediction plays a pivotal role in facilitating effective watershed management and the rational allocation of water resources. Given the inherent challenges posed by the nonlinear and nonstationary nature of runoff sequences, this study introduces a novel coupled model, combining complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), variational mode decomposition (VMD), long short-term memory (LSTM), and Informer techniques for monthly runoff prediction at the Wulong hydrological station of the Yangtze River Basin from 1973 to 2022. In addition, by comparing the prediction results of the traditional statistical model, which is the seasonal exponential smoothing model, with those of the machine learning model, the prediction accuracy of the machine learning model was found to be much higher than that of the traditional statistical mode. And the coupled model of secondary decomposition and secondary prediction was compared with other types of coupled models, such as one decomposition and one prediction. The CEEMDAN-VMD-LSTM-Informer model exhibited superior performance, as evidenced by an NSE value of 0.997, MAE of 1.327 × 108 m3, MAPE of 2.57%, and RMSE of 2.266 × 108 m3. The combined model proposed in this paper has the highest prediction accuracy, rendering it suitable for long-time series prediction. Accurate runoff prediction plays a pivotal role in facilitating effective watershed management and the rational allocation of water resources.

Teaching design of Chinese contemporary stylized watercolor based on quadratic exponential smoothing model

Abstract This paper is based on the exponential smoothing model to enhance the abilities of watercolor students and achieve their stylized watercolor creation. Firstly, the system is structured from the predicted value of the smoothing index. The sum of weights is calculated for each coefficient, and the quadratic, exponential smoothing model is modified. The design of the watercolor teaching system based on the quadratic, exponential model was completed after analyzing the components of the teaching model. Finally, a comparison experiment was conducted to verify that the overall performance of students was improved, and the final test score of painting reached 69%, which was significantly improved relative to that of the control class. The students in the experimental class were also tested for their T-values, and the test results were all below the significance level. It indicates that after the systematic teaching designed in this paper, the watercolor students' watercolor skill ability, personal stylization, and watercolor creation ability have a positive enhancement effect.

Hybrid analytic network process (ANP)-Entropy model, time series analysis for predicting nitrate and fluoride in groundwater and cumulative health risk assessment

The study focused on groundwater evaluation of the trans-Himalayan region using a novel concept of Hybrid Analytic Network Process (ANP) - entropy and Holt's exponential smoothing model for short-term prediction of groundwater quality. Hierarchy cluster analysis of groundwater was performed to identify the sources and spatial distribution of water quality. The PCA coupled with multivariate analysis dictated a high correlation of various ions i.e., NO3−, K+, F−, Cl−, SO42−, PO42−, and Na+ with the lithology of the area and helped in identification of various polluting sources i.e., excessive use of fertilizers, wastewater discharges and agrochemicals. The hybrid ANP-entropy technique offered a holistic approach to provide a more accurate and complete understanding of groundwater quality and revealed that groundwater quality in 21.43% (in winter) and 42.86% (in summer) of the locations fall into the poor category. The non-carcinogenic health risk analysis revealed that fluoride poses a major potential health risk followed by nitrate, primarily via the oral pathway while it was negligible through the dermal pathway. The total hazard index was observed highest in children (1.99) followed by infants (1.64). 95th percentile of the probable risk obtained through Monte Carlo simulation also dictated highest risk to infants than child. The predicted values of the Holt's exponential smoothing model for the year 2021 and 2022 was varied within ±5 % of the observed values. The proposed model effectively treats uncertainties in groundwater quality assessment and considers average and incremental increase both hence, can be used for short-term prediction and trend analysis of groundwater quality.

Research of Combined ES-BP Model in Predicting Syphilis Incidence 1982-2020 in Mainland China.

Syphilis remains a major public health concern in China. We aimed to construct an optimum model to forecast syphilis epidemic trends and provide effective precautionary measures for prevention and control. Data on the incidence of syphilis between 1982 and 2020 were obtained from the China Health Statistics Yearbook. An exponential smoothing model (ES model) and a BP neural network model were constructed, and on this basis, the ES-BP combination model was created. The prediction performance was assessed to compare the MAE (Mean Absolute Error), MSE (Mean Squared Error), MAPE (Mean Absolute Percentage Error), and RMSE (Root Mean Square Error). The optimum ES model was Brown's linear trend model, which had the lowest MAE and MAPE values, and its residual was a white noise sequence (P=0.359). The optimum BP neural network model had three layers with the number of nodes in the input, hidden, and output layers set to 5, 11, and 1, and the mean values of MAE, MSE, and RMSE by five-fold cross-validation were 1.519, 6.894, and 1.969, respectively. The ES-BP combination model had three layers, with model nodes 1, 4, and 1. The lowest mean values of MAE, MSE, and RMSE obtained by five-fold cross-validation were 1.265, 5.739, and 2.105, respectively. The ES, BP neural network, and ES-BP combination models can be used to predict syphilis incidence, but the prediction performance of the ES-BP combination model is better than that of a basic ES model and a basic BP neural network model.

Consumption–Production Profile Categorization in Energy Communities

Energy Transition is changing the renewable energy participation in new distributed generation systems like the Local Energy Markets. Due to its inherent intermittent and variable nature, forecasting production and consumption load profiles will be more challenging and demand more complex predictive models. This paper analyzes the production, consumption load profile, and storage headroom% of the Cornwall Local Energy Market, using advanced statistical time series methods to optimize the opportunity market the storage units provide. These models also help the Energy Community storage reserves to meet contract conditions with the Distribution Network Operator. With this more accurate and detailed knowledge, all sites from this Local Energy Market will benefit more from their installation by optimizing their energy consumption, production, and storage. This better accuracy will make the Local Energy Market more fluid and safer, creating a flexible system that will guarantee the technical quality of the product for the whole community. The training of several SARIMAX, Exponential Smoothing, and Temporal Causal models improved the fitness of consumption, production, and headroom% time series. These models properly decomposed the time series in trend, seasonality, and stochastic dynamic components that help us to understand how the Local Energy Market consumes, produces, and stores energy. The model design used all power flows and battery energy storage system state-of-charge site characteristics at daily and hourly granularity levels. All model building follows an analytical methodology detailed step by step. A benchmark between these sequence models and the incumbent forecasting models utilized by the Energy Community shows a better performance measured with model error reduction. The best models present mean squared error reduction between 88.89% and 99.93%, while the mean absolute error reduction goes from 65.73% to 97.08%. These predictive models built at different prediction scales will help the Energy Communities better contribute to the Network Management and optimize their energy and power management performance. In conclusion, the expected outcome of these implementations is a cost-optimal management of the Local Energy Market and its contribution to the needed new Flexibility Electricity System Scheme, extending the adoption of renewable energies.

Construction of a screening and evaluation system for anti-hepatitis B virus drugs based on quadratic exponential smoothing model

Abstract Exploring the construction of an anti-hepatitis B virus drug screening and evaluation system is to better develop anti-HBV virus drugs. In this paper, we analyzed the types of hepatitis B virus present in different hepatocytes, starting from the hepatitis B cell line model. Based on the quadratic, exponential smoothing model, a QES-LSTM viral gene detection model was constructed by introducing a long and short term memory neural network, and experimental analysis of the sensitivity and specificity of viral gene detection was conducted for this model. From the sensitivity experiments, the sensitivity of HBV DNA, DHBV DNA and DHBV cccDNA were 60 copies/ml, 60 copies/ml and 10 copies/ml, respectively. From the specificity experiments, the mean values of specificity of HBV DNA, DHBV DNA, and DHBV cccDNA were 0.489, 0.481, 0.429, respectively, 0.429, which showed positive amplification compared to other types. This indicates that effective discrimination of HBV viral genes is needed in the construction of an anti-HBV virus drug screening and evaluation system, which in turn allows targeted screening of drugs for the treatment of the HBV virus.

FORECASTING QUARTERLY RICE AND CORN PRODUCTION IN THE PHILIPPINES: A COMPARATIVE STUDY OF SEASONAL ARIMA AND HOLT-WINTERS MODELS

Rice and corn are essential crops for the Philippines, playing a critical role in the nation’s economy and food security. However, the agricultural sector faces challenges, including climate variability, land constraints, and the need for imports to meet growing demand. Accurate forecasting of rice and corn production is crucial for informed decision-making and resource allocation. This research applied Seasonal Autoregressive Integrated Moving Average (SARIMA) and Holt-Winters exponential smoothing models to forecast rice and corn production. The study used quarterly production data from 1987 to 2023 obtained from the Philippine Statistics Authority. The Holt-Winters model with additive seasonality outperformed the SARIMA model for both rice and corn production, achieving lower Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) values. The findings have significant implications for policymakers, agricultural stakeholders, and commodity traders, guiding them in making informed decisions regarding import requirements. The volatility of global food prices and exchange rates can significantly impact the cost of imports, putting a strain on the country’s financial resources. Accurate forecasting models are essential for ensuring food sufficiency and making informed decisions on the amount of imports required. By adopting the Holt-Winters model and continuously improving forecasting methodologies, the Philippines can enhance food sufficiency and promote rural economic growth. The study highlighted the importance of accurate forecasting models in ensuring stable and sufficient rice and corn supplies to meet the nation’s growing demands, contributing to sustainable agricultural development and food security. Continuous research in agricultural forecasting methodologies is necessary to address the challenges posed by evolving agricultural dynamics and further enhance predictive accuracy.

Trends in deaths following drug use in England before, during, and after the COVID-19 lockdowns.

This research aimed to describe how the characteristics of deaths following drug use changed during the COVID-19 pandemic in England, and how this can inform future strategy to support the health and social care of people who use drugs in future emergency scenarios. All deaths reported to the National Programme on Substance Abuse Deaths which occurred between January 2018 and December 2021 inclusive were extracted for analysis. Exponential smoothing models were constructed to determine any differences between forecasted vs. actual trends. Following the first lockdown period in England there were significant increases in the proportion of people who died at home beyond the 95% confidence bounds of the exponential smoothing model and concurrent decreases in the proportion of people who died in hospital. Whilst the overall proportion of deaths attributable to opioids did not significantly deviate from the forecasted trend, there were significant increases in methadone-related deaths and decreases in heroin/morphine-related death beyond the 95% confidence bounds. The proportion of deaths concluded as suicide increased, as did those implicating antidepressant use. There were no changes in the proportion of deaths following use of other drug classes, alcohol use in combination with psychoactive drugs, or on decedent demographics (gender, age, and drug user status). A small number of deaths due to drug use had COVID-19 infection itself listed as a cause of death (n = 23). For people who use drugs, the impact of the restrictions due to the COVID-19 pandemic was greater than that of infection from the virus itself. The health and social care strategy for these people needs to be pre-emptively adapted to mitigate against the specific risk factors for fatal drug overdose associated with future emergency scenarios.

A Bayesian estimation approach of random switching exponential smoothing with application to credit forecast

We introduce an efficient Markov Chain Monte Carlo sampler in precision-based algorithms for the estimation of the Random Switching Exponential Smoothing model, a versatile forecasting mechanism for time series data characterized with changing trends. Through a series of simulation experiments, RC-MCMC exhibits superior parameter estimation accuracy, particularly for datasets featuring low persistence trends. Furthermore, an empirical evaluation using the Bank for International Settlements’ quarterly time series data on the non-financial sector’s total credit relative to GDP validates the findings. The out-of-sample results indicate that the proposed approach outperforms its counterparts in estimating and forecasting accuracy for trending time series data.

Forecast of the Temperature Variation of an Elastohydrodynamic Contact by the Simple Exponential Smoothing Model (SES)

Forecast of the Temperature Variation of an Elastohydrodynamic Contact by the Simple Exponential Smoothing Model (SES)

Forecasting of Resin Yield and Number of Blazes of Naturally Regenerated Chir Pine (Pinus roxburghii Sargent) in Himachal Pradesh by Using Single Exponential Smoothing Method

The present investigation entitled “Forecasting of resin yield and number of blazes of naturally regenerated chir pine (Pinus roxburghii Sargent) in Himachal Pradesh by using single exponential smoothing method” was carried out during the year 2020-2022. The secondary information was collected regarding the resin yield and number of resin blazes w.e.f. 2005 to 2022 from Himachal Pradesh State Forest Department. Exponential smoothing is a particular moving average technique applied to time series data and to produce smoothed data to make forecast. In exponential smoothing, one or more smoothing parameters are to be determined explicitly and those choices determine the weights assigned to the observations. Forecasting with the help of various linear and non-linear models is on the assumption that the series is stationary. Often time series is found to be non-stationary which means they are integrated and can be made stationary by differencing the time series. To check the stationarity of the number of blazes and resin yield, Augmented Dickey Fuller test was used. The results indicated that data was not approaching stationarity even after taking third difference. So, the prerequisite condition of ARIMA model is that the data should be stationary and if the time series data does not contain trend and seasonal components, Single Exponential Smoothing model was used. The Single Exponential Smoothing model was found to be best fit for the prediction of number of blazes and resin yield as per the high value of , low value of MAPE and Normalized BIC.