Search

Purpose. The purpose of our article is to research and forecast prices for agricultural products using the example of potato prices based on the most effective models using data science techniques. Methodology / approach. Various forecasting models are explored, starting from baseline models like decomposition and exponential smoothing models to more advanced techniques such as ARIMA, SARIMA, as well as deep learning models including neural network. The data is split into training and testing sets, and models are validated using cross-validation techniques and optimised through hyperparameter tuning. Model performance is evaluated using metrics such as MAE, MSE, RMSE, and MAPE. The selected model is then used to generate future price forecasts, with uncertainty quantified through confidence intervals. Results. The study successfully applied advanced data science techniques to forecast potato prices, leveraging a range of effective models. By analysing historical price data and using various forecasting methods, the research identified the most accurate models for predicting future price trends. The results demonstrate that the selected models can provide reliable forecasts. In particular, the results showed that the model could achieve good forecast results when applied to real problems and, thus, can be effectively used for forecasting tasks especially considering seasonality. In addition, it should be noted that the model has a higher prediction accuracy at the time intervals closest to the original data. The obtained results support using both models simultaneously for forecasting, which can compensate for the shortcomings of each of them. The models can be used separately, to more accurately predict the values for the required period, or a combination of them is also possible. Originality / scientific novelty. The study’s originality lies in development of methods for effectively accounting for seasonality in agricultural price data, such as using seasonal decomposition techniques or more advanced techniques that combine statistical and data science approaches. The novelty implies the implementation of real-time data processing and forecasting system allows for the timely prediction of price changes, enabling stakeholders to make more informed decisions. Practical value / implications. Forecasting potato prices holds significant practical value for various stakeholders. For farmers, accurate forecasts enable informed decisions on the optimal times to plant, harvest, and sell their crops, thereby optimising their profits. In the supply chain, distributors and retailers can use these forecasts to manage inventory more effectively and plan contracts, reducing waste and avoiding shortages. Policymakers benefit from forecasts by anticipating market fluctuations and stabilising prices, which supports both consumers and producers. For consumers, stable pricing ensures better budgeting and helps avoid sudden price spikes, making essential foods more affordable. Overall, accurate price forecasting enhances market efficiency by reducing uncertainty and aiding investors in managing risk.

The mounting impacts of climate change on infrastructure demand proactive adaptation strategies to ensure long-term resilience. This study investigates the effects of predicted future global warming on asphalt binder performance grade (PG) selection in the United States using a time series method. Leveraging Long-Term Pavement Performance (LTPP) data and Superpave protocol model, the research forecasts temperature changes for the period up to 2060 and calculates the corresponding PG values for different states. The results reveal significant temperature increases across the majority of states, necessitating adjustments in PG selection to accommodate changing climate conditions. The findings indicate significant increases in average 7-day maximum temperatures across the United States by 2060, with 38 out of 50 states likely to experience rising trends. Oregon, Utah, and Idaho are anticipated to face the largest temperature increases. Concurrently, the low air temperature has risen in 33 states, with notable increases in Maine, North Carolina, and Virginia. The widening gap predicted between required high and low PG poses challenges, as some necessary binders cannot be produced or substituted with other grades. The study highlights the challenge of meeting future PG requirements with available binders, emphasizing the need to consider energy consumption and CO2 emissions when using modifiers to achieve the desired PG properties. [ABSTRACT FROM AUTHOR]

Copyright of Econder International Academic Journal is the property of Econder International Academic Journal and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Daily data on COVID-19 infections and deaths tend to possess weekly oscillations. The purpose of this work is to forecast COVID-19 data with partially cyclical fluctuations. A partially periodic oscillating ARIMA model is suggested to enhance the predictive performance. The model, optimized for improved prediction, characterizes and forecasts COVID-19 time series data marked by weekly oscillations. Parameter estimation and out-of-sample forecasting are carried out with data on daily COVID-19 infections and deaths between January 2021 and October 2022 in the USA, Germany, and Brazil, in which the COVID-19 data exhibit the strongest weekly cycle behaviors. Prediction accuracy measures, such as RMSE, MAE, and HMAE, are evaluated, and 95% prediction intervals are constructed. It was found that predictions of daily COVID-19 data can be improved considerably: a maximum of 55–65% in RMSE, 58–70% in MAE, and 46–60% in HMAE, compared to the existing models. This study provides a useful predictive model for the COVID-19 pandemic, and can help institutions manage their healthcare systems with more accurate statistical information. [ABSTRACT FROM AUTHOR]

Abstract This study focuses on forecasting German generation-based CO2 emission factors to develop accurate prediction models, which help to shift flexible loads in time with low emissions. While most existing research relies on point forecasts to predict CO2 emission factors, the presented methods are utilized to perform interval forecasts. In addition, compared to other studies, recent data that extends over a long period is used. The study describes the used data and discusses the concept of walk-forward validation. Further, various models are employed and tuned to forecast the emission factors, including benchmark, parametric (e.g., SARIMAX), and non-parametric (bagging, random forest, gradient boosting, CNN, LSTM, MLP) models. The study reveals that all applied parametric and non-parametric models yield better results than the benchmark models, while the gradient boosting model has the lowest mean absolute error with 40.66 gCO2/kWh, the lowest mean absolute percentage error 8.17%, and the random forest has the lowest root mean square error with 57.61 gCO2/kWh. However, the potential of the deep learning models was not fully exploited. In a live application, the implementation effort should be evaluated against the benefit of better prediction.

Daily data on COVID-19 infections and deaths tend to possess weekly oscillations. The purpose of this work is to forecast COVID-19 data with partially cyclical fluctuations. A partially periodic oscillating ARIMA model is suggested to enhance the predictive performance. The model, optimized for improved prediction, characterizes and forecasts COVID-19 time series data marked by weekly oscillations. Parameter estimation and out-of-sample forecasting are carried out with data on daily COVID-19 infections and deaths between January 2021 and October 2022 in the USA, Germany, and Brazil, in which the COVID-19 data exhibit the strongest weekly cycle behaviors. Prediction accuracy measures, such as RMSE, MAE, and HMAE, are evaluated, and 95% prediction intervals are constructed. It was found that predictions of daily COVID-19 data can be improved considerably: a maximum of 55–65% in RMSE, 58–70% in MAE, and 46–60% in HMAE, compared to the existing models. This study provides a useful predictive model for the COVID-19 pandemic, and can help institutions manage their healthcare systems with more accurate statistical information.

Objective To explore the risk factors of supplementary injection after foam sclerotherapy for varicose veins of lower extremities and its impact on blood coagulation function. Methods A total of 185 patients with varicose veins of lower limbs diagnosed in the First People' s Hospital of Zunyi from January 2018 to December 2021 were selected. The corresponding pathological data were collected, and the D-dimer, thrombin time, and fibrinogen level of patients were detected 1 d before and 1 d after the surgery. The postoperative video phone follow-up lasted until 6 months after the surgery. The patients were divided into single treatment group and supplementary treatment group according to whether supplementary injection of foam sclerosing agent was needed during the follow-up. Propensity matching on the data between the two groups was conducted, and the correlation between disease course data, coagulation factors, and the occurrence of supplementary injection was analyzed. A time series model for the incidence of supplementary injection was established, and the therapeutic effect and complications were observed. Results After propensity matching, there was still significant difference in the degree of lesion between the two groups (P < 0.05). On the first day after surgery, there was significant difference in the D-dimer and fibrinogen groups between the two groups (P < 0.05 ), and but no significant difference in thrombin time (P > 0.05). The occurrence of supplementary injection was significantly correlated with D-dimer, fibrinogen, thrombin time, and first-time injection dose (P < 0.05), and the incidence of supplementary injection was higher in patients who received first-time injection in January, August, September, and December. Both groups achieved successful treatment 6 months after surgery, and there was no significant difference in the incidence of complications. Conclusion Patients with lower limb varicose veins of C3/C4 are more likely to require supplementary injection compared to patients with other levels. The level of D-dimer and fibrinogen at 1 d after surgery is positively correlated with the occurrence of supplementary injection, while the dose of the first injection is negatively correlated with the occurrence of supplementary injection. [ABSTRACT FROM AUTHOR]

In recent years, under the influence of changes in natural conditions and human social activities, the issue of global warming has become increasingly prominent. So it is crucial to effectively predict the future trend of temperature changes. In this regard, from the perspective of statistical models, this paper studies a new combination model, namely the new GM-ARIMA model, based on linear combination of weight calculation. Furthermore, it also analyzes the prediction effect through comparative experiments and uses multiple performance evaluation indicators, so as to prove the scientificity and effectiveness of the proposed combination model in this paper. Finally, according to the experimental results, it can be clearly found that among the four methods for calculating the weights of linear combination, namely the equal weight method, the variance reciprocal method, the residual reciprocal method and the standard deviation method, the combination model using the standard deviation method for calculation has the highest prediction accuracy, so it is finally decided to use this method to build the combination model (namely S-GM-ARIMA). In addition, the experimental results show that the S-GM-ARIMA model achieves the best prediction results compared to other existing prediction models. Among them, the MAE of S-GM-ARIMA decreases by 10.38% and 16.22% compared to the GM(1,1) model and ARIMA model, respectively. The RMSE of S-GM-ARIMA decreases by 4.52% and 10.03% compared to the GM(1,1) model and ARIMA model, respectively. And the MAPE of S-GM-ARIMA decreases by 10.34% and 16.17% compared to the GM(1,1) model and ARIMA model, respectively. Therefore, the new GM-ARIMA combination model studied in this paper has relatively higher prediction accuracy when making predictions, and can be used to make more effective and accurate predictions of global average temperature. This study can also provide reference for countries in making decisions to address global warming issues. [ABSTRACT FROM AUTHOR]

Ozone has a significant impact on the environment. Atmospheric ozone concentration in coastal tourist areas now gains greater importance because tourists' skin is directly exposed to sunlight. The current research provides the best prediction model to improve the prediction accuracy of ozone level for the coastal area of Bangladesh. The functional time series analysis (FTSA) is a direct extension of function-to-function regression model dealing with continuous curves. The proposed functional time series–based model was applied to the hourly ozone series observed over 92 days starting from March 2019 to May 2019 in the coastal area of Bangladesh. Descriptive measures were used to estimate the overall temporal patterns, and the functional principal component regression model (FPCR) was used to predict first day of monsoon season. In addition, functional autoregressive model (FAR(1)) was used to measure the impact of 1-h differences on next day's ozone levels. Results of functional principal component regression reveal complex dynamic patterns of the ozone levels over hours and days. The first principal component primarily models afternoon-hour ozone levels, and the second principal component models the complex difference pattern between midnight to early morning, and the rest of the hourly ozone concentration. In addition, from FAR(1) model, our results confirm the moderate effect of ozone series of current day on the next day when the 1-h difference is observed (more specifically around office hours: 8 am to 17 pm). Finally, the highest peak was observed for forecasted series at 11 am. Intriguingly, we discovered that anticipated values perfectly fit observed values, resulting in the smallest forecasting error. [ABSTRACT FROM AUTHOR]

This study focuses on forecasting German generation-based CO2 emission factors to develop accurate prediction models, which help to shift flexible loads in time with low emissions. While most existing research relies on point forecasts to predict CO2 emission factors, the presented methods are utilized to perform interval forecasts. In addition, compared to other studies, recent data that extends over a long period is used. The study describes the used data and discusses the concept of walk-forward validation. Further, various models are employed and tuned to forecast the emission factors, including benchmark, parametric (e.g., SARIMAX), and non-parametric (bagging, random forest, gradient boosting, CNN, LSTM, MLP) models. The study reveals that all applied parametric and non-parametric models yield better results than the benchmark models, while the gradient boosting model has the lowest mean absolute error with 40.66 gCO2/kWh, the lowest mean absolute percentage error 8.17%, and the random forest has the lowest root mean square error with 57.61 gCO2/kWh. However, the potential of the deep learning models was not fully exploited. In a live application, the implementation effort should be evaluated against the benefit of better prediction. [ABSTRACT FROM AUTHOR]

Dropout rates are a key indicator of educational quality, making it imperative for educational institutions to design strategies to reduce them, thereby contributing to improved student retention and the achievement of academic objectives. While dropout research has primarily focused on machine learning methods applied to in-person education datasets, this article introduces a novel approach based on time series models for dropout rates analysis at the National Open and Distance University (UNAD). Methodologically, an adaptation of the CRISP-DM methodology was undertaken in four phases, namely: F1. Business and data understanding, F2. Data preparation, F3. Model building and evaluation, and F4. Model deployment. In terms of results, an open dataset on UNAD dropout, obtained from the SPADIES system between 1999 and 2021, was employed. Using Python libraries statsmodels and pandas, an ARIMA model was implemented, displaying optimal error metrics. This ARIMA model was utilized to forecast future dropout rates at UNAD, projecting a future dropout rate fluctuating around 23%. In conclusion, the ARIMA model developed for UNAD stands as an innovative and essential tool in the educational realm, capable of accurately anticipating dropout rates for upcoming semesters. This provides UNAD with a unique advantage in strategic decision-making. [ABSTRACT FROM AUTHOR]

Flash flood is the most hazardous type of flooding, mainly caused by extensive rainfall. It also can cause significant harm to a community's economy, ecology, and society without warning at an irrational pace. Therefore, this study was conducted to detect the time series element within the rainfall data, select the optimal model, and make predictions about the volume of rainfall in Selangor. A variety of univariate time series models were utilized, including the naïve model, decomposition model, Autoregressive Integrated Moving Average (ARIMA) model, exponential models, and combined models. Historical monthly rainfall data collected from Petaling station and Subang station from 2018 to 2022 were used to estimate the parameters of the models, and the model was evaluated for the smallest error of measurements. Previous research mostly focused on complex methodologies for forecasting rainfall. However, this research aimed to identify a simple tool for fast prediction of rainfall. The results showed that the combination of the ARIMA (2,0,3) model from Petaling Station and the ARIMA (4,0,4) model from Subang station were able to capture the trends and seasons in the time series with the lowest error of measurement on short-term predictions of rainfall volume. Furthermore, the study delves into the concept of combined time series models, which are blended using weighted performance measures to enhance prediction accuracy further. The research acknowledges certain limitations of univariate time series models, notably their inability to account for intricate interactions among environmental variables and potential long-term trends, such as those stemming from climate change. Overall, the study explores the potential of combining models to refine predictions for forecasting rainfall volume in Klang Valley. [ABSTRACT FROM AUTHOR]

Introduction: Rabies, a deadly zoonotic viral disease, accounts for over 50,000 fatalities globally each year. This disease predominantly plagues developing nations, with Thailand being no exception. In the current global landscape, concerted eorts are being mobilized to curb human mortalities attributed to animal-transmitted rabies. For strategic allocation and optimization of resources, sophisticated and accurate forecasting of rabies incidents is imperative. This research aims to determine temporal patterns, and seasonal fluctuations, and project the incidence of canine rabies throughout Thailand, using various time series techniques. Methods: Monthly total laboratory-confirmed rabies cases data from January 2013 to December 2022 (full dataset) were split into the training dataset (January 2013 to December 2021) and the test dataset (January to December 2022). Time series models including Seasonal Autoregressive Integrated Moving Average (SARIMA), Neural Network Autoregression (NNAR), Error Trend Seasonality (ETS), the Trigonometric Exponential Smoothing State-Space Model with Box-Cox transformation, ARMA errors, Trend and Seasonal components (TBATS), and Seasonal and Trend Decomposition using Loess (STL) were used to analyze the training dataset and the full dataset. The forecast values obtained from the time series models applied to the training dataset were compared with the actual values from the test dataset to determine their predictive performance. Furthermore, the forecast projections from January 2023 to December 2025 were generated from models applied to the full dataset. Results: The findings revealed a total of 4,678 confirmed canine rabies cases during the study duration, with apparent seasonality in the data. Among the models tested with the test dataset, TBATS exhibited superior predictive accuracy, closely trailed by the SARIMA model. Based on the full dataset, TBATS projections suggest an annual average of approximately 285 canine rabies cases for the years 2023 to 2025, translating to a monthly average of 23 cases (range: 18–30). In contrast, SARIMA projections averaged 277 cases annually (range: 208–214) Discussion: This research oers a new perspective on disease forecasting through advanced time series methodologies. The results should be taken into consideration when planning and conducting rabies surveillance, prevention, and control activities. [ABSTRACT FROM AUTHOR]

Recently, the development and application of artificial intelligence have received widespread research attentions, and one of important applications is accident prevention. Since most accidents on construction sites are caused by construction works' unsafe behaviors, unsafe behavior detection is desired. Unlike traditional detection model which focuses only on accuracy of detection and ignore efficiency of detection, a deep neural network-based edge computing framework is proposed for detecting unsafe behavior not only efficiently but also precisely. To address efficiency issue, an object detection model and a posture estimation model are established on edge device for extracting feature from surveillance camera streaming, a time series classification model is developed on server for detecting unsafe behavior according to the features extracted from edge devices. Finally, a comprehensive experimental study based on three datasets collected from three real construction sites is conducted. The results showed that the models proposed in this study can achieve 87% in terms of accuracy and 1.5 s in terms of latency. The improve rate of the proposed DeepSafety is higher than 25% in terms of accuracy and 80% in terms of latency. Accordingly, the proposed edge-computing based framework is shown to deliver excellent performance. [ABSTRACT FROM AUTHOR]

Copyright of Coal Science & Technology (0253-2336) is the property of Coal Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The emergence of new suppliers and energy resources has reshaped the energy market in terms of contractual structures and pricing systems. The market shifts were accelerated in response to the latest Russian-Ukraine crisis, impacting natural gas supply chains from financing projects to contracting volumes. The increased demand for liquified natural gas volumes intensified the need to switch from long-term oil-indexed contracts to short-term gas-indexed contracts. Those shifts were anticipated to influence the selling strategies for the expected added 49 MTPA of Qatari LNG, wherein increasing the share of spot selling would be reflected in higher economic performance. This study used forecasted prices to investigate potential Qatari LNG selling strategies. Initially, projections of the most dominant pricing systems used for pricing Qatari LNG (i.e., brent, Henry Hub, Title Transfer Facility, and Japan Korea Marker) were estimated between 2023 and 2040. While Qatar has been relying on long-term oil-indexed contracts, the second step estimated annual LNG revenues under different combinations of selling strategies (i.e., long-term and spot sales). Finally, the influence of varying brent slopes on the estimated revenues was measured. Due to data limitations and non-stationarity, the double exponential smoothing model was selected among the different tested models. Considering current market dynamics, forecasts of the double exponential smoothing model showed an upward price trend until 2040. An annual average increase of 1.24% for the studied pricing systems was reported. Reducing the share of long-term brent-indexed contracts to 70% and dedicating the remaining 30% of volumes to spot sales yielded the highest premiums for revenue estimates. An average annual revenue of $62 bn was reported for the 70/30 strategy, around 6% higher than the 100% brent-indexed contracts strategy. The findings revealed that diversifying the selling approach and introducing spot sales can enhance revenues. From the buyers’ perspective, the outcomes support policymakers in understanding the implications of escalated prices driven by a lack of liquidity investments.

In recent times, many investigators have delved into plastic waste (PW) research, both locally and internationally. Many of these studies have focused on problems related to land-based and marine-based PW management with its attendant impact on public health and the ecosystem. Hitherto, there have been little or no studies on forecasting PW quantities in developing countries (DCs). The key objective of this study is to provide a forecast on PW generation in the city of Johannesburg (CoJ), South Africa over the next three decades. The data used for the forecasting were historical data obtained from Statistics South Africa (StatsSA). For effective prediction and comparison, three-time series models were employed in this study. They include exponential smoothing (ETS), Artificial Neural Network (ANN), and the Gaussian Process Regression (GPR). The exponential kernel GPR model performed best on the overall plastic prediction with a determination coefficient (R2) of 0.96, however, on individual PW estimation, ANN was better with an overall R2 of 0.93. From the result, it is predicted that between 2021 and 2050, the total PW generated in CoJ is forecasted to be around 6.7 megatonnes with an average of 0.22 megatonnes/year. In addition, the estimated plastic composition is 17,910 tonnes PS per year; 13,433 tonnes PP per year; 59,440 tonnes HDPE per year; 4478 tonnes PVC per year; 85,074 tonnes PET per year; 34,590 tonnes LDPE per year and 8955 tonnes other PWs per year.

【Objective】 Accurate prediction of water quality is of great importance for protecting water ecological environment and improving water resource management, but difficult due to the combined influence of various factors including human activities, rainfall, temperature and hydrodynamic conditions which are complex and uncertain. In this paper we compare three models, the SARIMA model, Holt-Winters model and LSTM neural network model, for predicting water quality of reservoir. 【Method】 Electric conductivity of water was used as a proxy for water quality. Data measured monthly from 2012—2018 from Mishan Reservoir was used for model training, and the data measured in 2019 was used to test the models. 【Result】 The SARIMA and Holt-Winters models are comparatively simple, but because they only consider time series of water quality data, their accuracy is low. In contrast, the LSTM neural network model considers factors that affect water quality and implicitly represents the nonlinearity of the factors in their impact on water quality, it is more accurate than other two models. 【Conclusion】 In general, the LSTM neural network model is reliably, giving rise to large error only when there were sudden changes in the conductivity. Overall, it is reliable and accurate for predicting change in water quality induced by variations in the environment.

The mounting impacts of climate change on infrastructure demand proactive adaptation strategies to ensure long-term resilience. This study investigates the effects of predicted future global warming on asphalt binder performance grade (PG) selection in the United States using a time series method. Leveraging Long-Term Pavement Performance (LTPP) data and Superpave protocol model, the research forecasts temperature changes for the period up to 2060 and calculates the corresponding PG values for different states. The results reveal significant temperature increases across the majority of states, necessitating adjustments in PG selection to accommodate changing climate conditions. The findings indicate significant increases in average 7-day maximum temperatures across the United States by 2060, with 38 out of 50 states likely to experience rising trends. Oregon, Utah, and Idaho are anticipated to face the largest temperature increases. Concurrently, the low air temperature has risen in 33 states, with notable increases in Maine, North Carolina, and Virginia. The widening gap predicted between required high and low PG poses challenges, as some necessary binders cannot be produced or substituted with other grades. The study highlights the challenge of meeting future PG requirements with available binders, emphasizing the need to consider energy consumption and CO2 emissions when using modifiers to achieve the desired PG properties.

The article proposes a time series model to explore the influencing factors of the cobalt industry chain trade competition network pattern. By analyzing the current situation of the evolution of the cobalt industry chain trade network, the relevant variables are selected. The data are described based on the overview of the relevant algorithmic research of the time series model. Finally, the model based on the time series data is empirically tested. The unit root is verified to be in an unsteady state by first-order differencing, and the p-values all have a probability of accepting the original hypothesis greater than 0. After the second-order differencing ADF test, all the series are smooth and all of them are second-order monotonic. After the cointegration test, it was found that the residual series is smooth at the 5% critical level, and there is a cointegration relationship.

Copyright of Journal of Irrigation & Drainage is the property of Journal of Irrigation & Drainage Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Vaccines are the primary weapon used to stop the outbreak, especially amid the COVID-19 pandemic. Thus, supplying vaccines to control the COVID-19 pandemic is essential, especially in minimizing the incidence and achieving herd immunity to break the chain of COVID-19. West Kalimantan has taken firm anticipatory steps to prevent COVID-19 in the form of a vaccination program in Indonesia. The highest vaccination achievement occurs in Pontianak City, the province’s capital. The research analyzed data on vaccine participants in Pontianak using time series analysis. In addition, the residuals from the time series model were used as observations in constructing the control chart. The research also analyzes the accuracy of the time series model using the Individual Moving Range (IMR) control chart. The results show that the ARIMA model (5,0,2) is the best because it fulfills the assumption of white noise. However, the ARIMA (5,0,2) model is inaccurate in making predictions because the residuals from the ARIMA (5,0,2) model are out of control (based on the IMR control chart). Hence, it is necessary to evaluate in determining the time series model. It can be analyzed using a control chart. Therefore, measuring the model’s accuracy on the best model is essential in predicting several subsequent periods.

IntroductionRabies, a deadly zoonotic viral disease, accounts for over 50,000 fatalities globally each year. This disease predominantly plagues developing nations, with Thailand being no exception. In the current global landscape, concerted efforts are being mobilized to curb human mortalities attributed to animal-transmitted rabies. For strategic allocation and optimization of resources, sophisticated and accurate forecasting of rabies incidents is imperative. This research aims to determine temporal patterns, and seasonal fluctuations, and project the incidence of canine rabies throughout Thailand, using various time series techniques.MethodsMonthly total laboratory-confirmed rabies cases data from January 2013 to December 2022 (full dataset) were split into the training dataset (January 2013 to December 2021) and the test dataset (January to December 2022). Time series models including Seasonal Autoregressive Integrated Moving Average (SARIMA), Neural Network Autoregression (NNAR), Error Trend Seasonality (ETS), the Trigonometric Exponential Smoothing State-Space Model with Box-Cox transformation, ARMA errors, Trend and Seasonal components (TBATS), and Seasonal and Trend Decomposition using Loess (STL) were used to analyze the training dataset and the full dataset. The forecast values obtained from the time series models applied to the training dataset were compared with the actual values from the test dataset to determine their predictive performance. Furthermore, the forecast projections from January 2023 to December 2025 were generated from models applied to the full dataset.ResultsThe findings revealed a total of 4,678 confirmed canine rabies cases during the study duration, with apparent seasonality in the data. Among the models tested with the test dataset, TBATS exhibited superior predictive accuracy, closely trailed by the SARIMA model. Based on the full dataset, TBATS projections suggest an annual average of approximately 285 canine rabies cases for the years 2023 to 2025, translating to a monthly average of 23 cases (range: 18–30). In contrast, SARIMA projections averaged 277 cases annually (range: 208–214).DiscussionThis research offers a new perspective on disease forecasting through advanced time series methodologies. The results should be taken into consideration when planning and conducting rabies surveillance, prevention, and control activities.

BackgroundSince March 2020, the coronavirus disease 2019 (COVID-19) pandemic has been a major shock to health systems across the world. We examined national usage patterns for selected basic, essential health services, before and during the COVID-19 pandemic in Uganda and Bangladesh, to determine whether COVID-19 affected reporting of service utilization and the use of health services in each country.MethodsWe used routine health information system data since January 2017 to analyze reporting and service utilization patterns for a variety of health services. Using time series models to replicate pre-COVID-19 trajectories over time we estimated what levels would have been observed if COVID-19 had not occurred during the pandemic months, starting in March 2020. The difference between the observed and predicted levels is the COVID-19 effect on health services.ResultsThe time trend models for Uganda and Bangladesh closely replicated the levels and trajectories of service utilization during the 38 months prior to the COVID-19 pandemic. Our results indicate that COVID-19 had severe effects across all services, particularly during the first months of the pandemic, but COVID-19 impacts on health services and subsequent recovery varied by service type. In general, recovery to expected levels was slow and incomplete across the most affected services.ConclusionOur analytical approach based on national information system data could be very useful as a form of surveillance for health services disruptions from any cause leading to rapid responses from health service managers and policymakers.

Large-span spatial lattice structures generally have characteristics such as incomplete modal information, high modal density, and high degrees of freedom. To address the problem of misjudgment in the damage detection of large-span spatial structures caused by these characteristics, this paper proposed a damage identification method based on time series models. Firstly, the order of the autoregressive moving average (ARMA) model was selected based on the Akaike information criterion (AIC). Then, the long autoregressive method was used to estimate the parameters of the ARMA model and extract the residual sequence of the autocorrelation part of the model. Furthermore, principal component analysis (PCA) was introduced to reduce the dimensionality of the model while retaining the characteristic values. Finally, the Mahalanobis distance (MD) was used to construct the damage sensitive feature (DSF). The dome of Taiyuan Botanical Garden in China is one of the largest non-triangular timber lattice shells worldwide. Relying on the structural health monitoring (SHM) project of this structure, this paper verified the effectiveness of the damage identification model through numerical simulation and determined the damage degree of the dome structure through SHM measurement data. The results demonstrated that the proposed damage identification method can effectively identify the damage of large-span timber lattice structures, locate the damage position, and estimate the degree of damage. The constructed DSF had relatively strong robustness to small damage and environmental noise and has practical application value for SHM in engineering. [ABSTRACT FROM AUTHOR]

Sometimes classification tasks have to be based on multivariate time series data collected for each class. In these situations the data for each class might exhibit non-stationary behaviour together with complex dependence structures. We propose a vine copula-based approach to capture these features in each class before applying a Bayesian classifier. Vine copulas have been very successful in modelling asymmetric tail dependence among variables and are coupled with non-stationary univariate time series to model the multivariate time series data for each class. We illustrate this classification approach using data from a neural activity experiment using electroencephalography, where we want to classify the eye state. The level of neural activity was collected over time for multiple locations on the scalp. Our approach is able to identify relevant locations and allows for a model-based interpretation of the data generating process. A cross-validation study with comparison to competitor classifiers for this data set shows good performance of the proposed classifier. [ABSTRACT FROM AUTHOR]

Crop diversity has always been a way to reduce agricultural risk. This study seeks to explore the long-term impact of crop diversity on reducing agricultural income risk in the province of Zanjan. In this study, first the crop diversity was evaluated through the herfindhal index in the timeframe of 1997 to 2018. Next, the income risk was estimated via hodrick-prescott filter. Finally using the Vector Error Correction Model (VECM), the long-term impact of crop diversity on reduced income risk was measured. Given the results of the long-term model it is clear that in the long-run there is a reduction in income fluctuations as crop diversity increases. The result was statistically meaningful by 1%. Meanwhile, based on the results if in the short-run a shock impacts agricultural income fluctuations in the province of Zanjan, in the long-run about 4 cycles are needed to totally balance the impact of the shock out. In other words, the impact of the shock is modified by 25% in each cycle. Thus, it is on the policymakers to first establish supportive policies to diversify cultivation patterns and prevent income shocks. They also need to develop reparative policies such as insurance means in a four-year period to balance the shock once it strikes. [ABSTRACT FROM AUTHOR]

Aiming at the problems of low accuracy of network attack prediction and long response time of attack detection, bidirectional long short-term memory (BiLSTM) was used to predict network attacks. However, BiLSTM has the problems of difficulty in parameter setting and low accuracy of the prediction model. This paper first proposes the Improved Grey Wolf algorithm (IGWO) to optimize the BiLSTM (IGWO-BiLSTM). First, IGWO uses Dimension Learning Hunting (DLH) strategy to construct the wolf neighborhood. In the established wolf neighborhood, the BiLSTM parameters are iteratively optimized to obtain a prediction model with fast convergence speed and small reconstruction error. Secondly, the dataset is preprocessed, and the IP packet statistical signature (IPDCF) is defined according to the characteristics of denial of service (DOS) and distributed denial of service (DDOS) attacks. IPDCF was used to establish the time series model and network traffic time series data were input into IGWO-BiLSTM to get the prediction results. Finally, the DOS and DDOS network packets were input into the trained prediction model to obtain the prediction results of attack data. By comparing the predicted values of IGWO-BiLSTM normal network packets and attack packets, a reasonable threshold is set to provide the basis for the subsequent attack prediction. Experiments show that the IGWO-BiLSTM can reach 99.05% of the fitting degree and accurately distinguish network attacks from normal network demand increases. [ABSTRACT FROM AUTHOR]

Copyright of China Tropical Medicine is the property of China Tropical Medicine Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Technology in agriculture has been widely and massively applied. One of them is automation technology and the use of big data through the Internet of Things (IoT). The use of IoT allows a process to run automatically without human intervention. Extreme weather changes and narrow land use are one of the main problems in agriculture. The development of IoT devices has been widely developed regarding this subject. One of them is a soil moisture detection system. This study aims to build an IoT soil moisture detection system. The system will use a sensor as input which is then processed in a microcontroller device and the prediction results are sent to the IoT cloud platform. Prediction results are obtained using a time series model and then its performance is evaluated using RMSE. This model was chosen because the structure of the observed soil moisture data is based on time. The results of this study indicate that the soil moisture IoT system can work well. This is supported by the results of the prediction evaluation value of the RMSE = 1.175682x10-5 model which is very small.

Необходимость обнаружения аномалий имеет особую актуальность в задачах геофизического мониторинга, требует обеспечения точности и оперативности метода. В работе предлагается подход на основе нейронных сетей NARX для задачи моделирования данных foF2 и обнаружения в них аномалий. Известно, что нейронные сети трудно моделируют сильно зашумленные и существенно нестационарные временные ряды. Поэтому оптимизация процесса моделирования временных рядов сложной структуры сетью NARX выполнялась с использованием вейвлет-фильтрации. На примере обработки временных рядов параметров ионосферы показана эффективность предлагаемого подхода, приведены результаты для задачи обнаружения ионосферных аномалий. Подход может быть применен при выполнении прогноза космической погоды для прогнозирования параметров ионосферы.

Tourism is the leading source of revenue to the Kenyan Government, contributing about 8.8% to the Kenya’s Gross Domestic Product. Based on the 2019 report released by the ministry of tourism and wildlife, tourism industry contributed approximately $7.9 billion to the Kenya’s budget. This study was therefore developed to predict the future numbers of tourists that will visit Kenya between 2023 and 2025. The Seasonal Autoregressive Integrated Moving Average time series model was applied for the prediction. The study used secondary data collected from the Ministry of Tourism and Wildlife. The data covered a period of 11 years from 2011 to 2022. The model was fitted to the real tourists’ data using the time series algorithm implemented in R statistical software. Based on the Akaike Information Criterion, the ARIMA(2,1,1)(0,1,0)12 was identified as the perfect model with minimum errors. The model passed the diagnostic test performed. Importantly, 95% confidence level prediction done for 3 years (2023-2025) using the model showed that the number of tourists expected to visit Kenya will increase significantly. Therefore, the study recommended that recreational facilities and accommodations should be maintained to cater for the high projected numbers of tourists. The study also recommended that the government of Kenya should strategize on how to beef up security to curb terrorism attacks and tribal conflicts which might discourage tourists.