Autoregressive Moving Average Research Articles

Forecasting cryptocurrency returns using classical statistical and deep learning techniques

The emergence of cryptocurrencies has generated enthusiasm and concern in the modern global economy. However, their high volatility, erratic price fluctuations, and tendency to exhibit price bubbles have made investors cautious about investing in them. Consequently, it is essential to develop methods and models to forecast cryptocurrency returns to benefit investors, traders, and the scientific community. Despite the considerable volume of research on Bitcoin price forecasting, other cryptocurrencies have received little attention in academic literature. Additionally, the current body of literature on predicting cryptocurrency prices or returns emphasizes the use of in-sample methodologies. However, this method is susceptible to overfitting. To address these gaps in the literature, this study employs autoregressive moving average (ARMA), generalized autoregressive conditional heteroskedasticity (GARCH), exponential generalized autoregressive conditional heteroskedasticity (EGARCH), and long short-term memory (LSTM) deep learning neural networks to forecast returns for the ten most actively traded digital currencies: Bitcoin, Ethereum, Ripple, Chainlink, Litecoin, Cardano, Ethereum Classic, Bitcoin Cash, Tether, and Binance Coin. To assess the accuracy of the two models, this study utilizes an out-of-sample method with data gathered sequentially from November 9, 2017, to September 18, 2022. The results indicate that all models exhibit high accuracy, as evidenced by their low root mean square error (RMSE), mean absolute error (MAE), and mean squared error (MSE) values. Meanwhile, the hybrid EGARCH-LSTM or GARCH-LSTM models demonstrate slightly better accuracy compared with the other models. The findings are valuable for investors, traders, and researchers involved in cryptocurrency forecasting.

Some Estimation Methods for a Random Coefficient in the Gegenbauer Autoregressive Moving-Average Model

The Gegenbauer autoregressive moving-average (GARMA) model is pivotal for addressing non-additivity, non-normality, and heteroscedasticity in real-world time-series data. While primarily recognized for its efficacy in various domains, including the health sector for forecasting COVID-19 cases, this study aims to assess its performance using yearly sunspot data. We evaluate the GARMA model’s goodness of fit and parameter estimation specifically within the domain of sunspots. To achieve this, we introduce the random coefficient generalized autoregressive moving-average (RCGARMA) model and develop methodologies utilizing conditional least squares (CLS) and conditional weighted least squares (CWLS) estimators. Employing the ratio of mean squared errors (RMSE) criterion, we compare the efficiency of these methods using simulation data. Notably, our findings highlight the superiority of the conditional weighted least squares method over the conditional least squares method. Finally, we provide an illustrative application using two real data examples, emphasizing the significance of the GARMA model in sunspot research.

Long Memory Time-series Model (ARFIMA) Based Modelling of Jute Prices in the Samsi Market of Malda District, West Bengal

The objective of this paper is modeling and forecasting the weekly jute prices of Samsi market in the Malda district of West Bengal in the presence of long memory process. The long memory behavior of series is investigated by the ACF plot and Hurst R/S analysis. A fractionally integrated autoregressive moving-average (ARssFIMA) model is fitted using 668 weekly data (January 2009-November 2022). This study shows the efficiencies of the Hurst exponent, GPH, Smoothed periodogram, Local Whittle, and Wavelet methods used to estimate the fractional difference parameter in the ARFIMA model. Furthermore, we compared the forecasting abilities of the ARFIMA and ARIMA models. The results show that long memory is present in the jute price series. The models selected according to each method are ARFIMA (3,0.348,0), ARFIMA (3,0.291,1), ARFIMA (2,0.487,0), ARFIMA (3,0.461,0), ARFIMA (2,0.311,0), and ARIMA (2,1,1) on the basis of minimum AIC and BIC using 534 in-sample data. Finally, the wavelet method based ARFIMA (2,0.311,0) model is found to be the best optimal model in terms of MAE, RMSE, and MAPE criteria using 134 out-of-sample data. A comparative study indicates that the forecasting performance of the ARFIMA model is strongly better than that of the ARIMA model in this regard.

Time-Varying Zero-Adjusted Poisson Distribution for Modeling Count Time Series

Many studies have used extensions of ARMA models for the analysis of non-Gaussian time series. One of them is the Generalized Autoregressive Moving Average, GARMA, enabling the modeling of count time series with distributions such as Poisson. The GARMA class is being expanded to accommodate other distributions, aiming to capture the typical characteristics of count data, including under or overdispersion and excess zeros. This study aims to propose an approach based on the GARMA class in order to analyze count time series with excess zeros, assuming a time-varying zero-adjusted Poisson distribution. This approach allows for capturing serial correlation, forecasting the future values, and estimating the future probability of zeros. For inference, a Bayesian analysis was adopted using the Hamiltonian Monte Carlo (HMC) algorithm for sampling from the joint posterior distribution. We conducted a simulation study and presented an application to influenza mortality reported in Brazil. Our findings demonstrated the usefulness of the model in estimating the probability of non-occurrence and the number of counts in future periods.

Multi-step carbon emissions forecasting model for industrial process based on a new strategy and machine learning methods

The rising industrial sector capacity increases carbon emissions, necessitating a low-carbon transformation for global sustainability. Accurate multi-step forecasting of industrial carbon emissions is crucial for optimizing production, reducing energy consumption, improving efficiency, and achieving decarbonization. However, current forecasting faces challenges like model uncertainty and low accuracy with multi forecasting steps. To address these issues, this study proposed a multi-step carbon emissions forecasting model for industrial processes. Firstly, a new multi-step forecasting strategy framework was proposed. Secondly, SHapley Additive exPlanations (SHAP) and lagged autocorrelation analysis were used to extract key features affecting industrial carbon emissions. On this basis, the grey model, autoregressive moving average (ARMA) model, and least squares support vector machine (LSSVM) method were used to build forecasting models separately. The weights of the three models were solved using the induced ordered weighted average operator and the Monte Carlo search tree (MCST) method. The final forecasting results were obtained by using the weighted summation method. The data collected from the real industry were used to validate the proposed model. The results showed that the proposed model could accurately forecast industrial carbon emissions within 12 steps and its MAPE is less than 10%. The proposed multi-step industrial carbon emissions forecasting model can provide data support for industrial energy saving, carbon reduction, and green and sustainable development.

Enhancing Tire Condition Monitoring through Weightless Neural Networks Using MEMS-Based Vibration Signals

Tire pressure monitoring system (TPMS) has a critical role in safeguarding vehicle safety by monitoring tire pressure levels. Keeping the accurate tire pressure is necessary for confirming comfortable driving and safety, and improving fuel consumption. Tire problems can result from various factors, such as road surface conditions, weather changes, and driving activities, emphasizing the importance of systematic tire checks. This study presents a novel method for tire condition monitoring using weightless neural networks (WNN), which mimic neural processes using random-access memory (RAM) components, supporting fast and precise training. Wilkes, Stonham, and Aleksander Recognition Device (WiSARD), a type of WNN, stands out for its capability in classification and pattern recognition, gaining from its ability to avoid repetitive training and residual formation. For vibration data acquisition from tires, cost-effective micro-electro-mechanical system (MEMS) sensors are employed, offering a more economical solution than piezoelectric sensors. This approach yields a variety of features, such as autoregressive moving average (ARMA), statistical and histogram features. The J48 decision tree algorithm plays a critical role in selecting essential features for classification, which are subsequently divided into training and testing sets, crucial for assessing the WiSARD classifier’s efficacy. Hyperparameter optimization of the WNN leads to improved classification accuracy and shorter computation times. In practical tests, the WiSARD classifier, when optimally configured, achieved an impressive 97.92% accuracy with histogram features in only 0.008 seconds, showcasing the capability of WNN to enhance tire technology and the accuracy and efficiency of tire monitoring and maintenance.

Wind speed prediction

With the help of wind farms, wind energy is a vital renewable energy source that contributes significantly to the worlds energy balance. The lifespan and maintenance costs of wind turbines will be reduced with an accurate wind speed prediction. On the other hand, wind speed is highly volatile and unpredictable. Thus, it is essential to do research into creating complex models and algorithms for precise wind speed prediction. So far, some of the most promising models include Support Vector Machine (SVM), Artificial Neural Networks (ANN), and Autoregressive Moving Average (ARMA). Python, as an advanced and versatile programming language, is exceptionally suited for scripting the algorithms of these sophisticated models. This paper will use the data from Austin Texas and apply a Support Vector Machine (SVM) for wind speed prediction involves several stages, including data collection, data preprocessing, model selection, model training, parameter optimization, model validation, and prediction. Wind energy resource optimisation, maintenance cost reduction, and total wind farm efficiency can all be significantly improved by incorporating these models into predictive analytics and continuously improving them against changing data.

An Empirical Study on Stock Returns of Chemical Industry Based on ARMA-GARCH Model--The Case of NIKKE Chemicals

This paper uses the ARMA-GARCH model to make predictions on the volatility of stock returns in China, selects the time series of daily returns of the representative enterprise of the chemical industry, NIKKE CHEMICAL, as the object of study, analyzes the stock returns of the enterprise over the past 6 years, and uses the ARMA model to make predictions of stock returns, and at the same time, joins the effect of volatility, and models the risk rate by using the GARCH model, and empirical evidence The results show that the chosen ARMA-GARCH model has a good fit to the time series of daily returns. This paper examines stock prices and analyses them by constructing a theoretical model that can provide advice for investment decisions in the stock market.

ARMA time series prediction model for fault detection of launch vehicle

Spaceflight is a high-risk activity, especially for launch vehicles, and the losses caused by launch failures are considerable. Real-time fault detection is a prerequisite to ensure that future launch vehicles can detect and isolate faults in a timely manner, and ultimately reduce the hazard of fault. In this article, a time series prediction model of axial overload and three-axis angular rate is established using ARMA (Auto Regressive Moving Average) time series prediction model, and the residuals of the prediction model are analyzed and combined with the fault determination decision strategy to determine whether the system has a fault, and a fault tree can be built to further locate the fault location.

Sparse linear parameter-varying autoregressive moving average modelling of non-stationary gearbox vibration signals

Gearboxes frequently operate under variable speed conditions, leading to the non-stationarity of collected monitoring signals. This paper proposes a sparse linear parameter-varying autoregressive moving average (Spa LPV-ARMA) model for fault detection of gearboxes under variable speed conditions. The Spa LPV-ARMA model integrates the advantages of LPV concepts, sparse models, and ARMA models. The proposed model has a more compact structure compared to the reported Spa LPV-AR model, which results in a lower ratio of parameter number to data amount, and the compact model structure also allows the Spa LPV-ARMA model to have higher computational efficiency during the testing phase. A simulation study was conducted to validate the performance of the proposed method. The results demonstrate that the Spa LPV-ARMA model exhibits superior modeling accuracy compared to the reported Spa LPV-AR model. Additionally, the fault detection method based on the Spa LPV-ARMA model achieves a higher fault detection rate when contrasted with a model that solely considers the autoregressive component.

Testing the Forecasting Power of Statistical Models for Intercity Rail Passenger Flows in Turkey

While going through a major rail transformation, it is important to develop reliable estimation models for rail passenger flows (RPFs) in Turkey. There are two main approaches in RPF estimation, regressions and autoregressive integrated moving-average (ARIMA) models, both of which were in this study developed using the daily RPF data for the period 2011–2015. The ARIMA models (with some variations) were used to forecast first the daily flows in 2016, during which travel restrictions for summer resulted in reduced volumes, successfully captured in the updated ARIMA model. The regression models predicted the expected demand during the restrictions, enabling evaluation of the impact of restrictions, which also showed the models’ power over the longer term. The forecasts were extended to 2017, 2018, and 2019 data. The regression results produced more reliable forecasts over the long term, whereas more accurate predictions were obtained by ARIMA-Sliding (FA-Sld) for short-term planning purposes.

Sex Ratio at Birth after Concurrent Events of Earthquakes and the COVID-19 Pandemic in Croatia.

The sex ratio at birth (ratio of males to females) has been known to be affected by exogenous shocks such as wars, pollution, natural catastrophes, economic crises, and others. Among these stressful events, both earthquakes and the COVID-19 pandemic have been reported to lower the sex ratio at birth. In this article, a rather unusual situation of two episodes of simultaneous events of COVID-19 lockdown and earthquakes approximately nine months apart (March and December of 2020) is investigated to assess whether they were associated with a bias in sex ratio at birth 3-5 months later (in utero loss) and 9 months later (loss at conception) in Croatia. The monthly time series of sex ratio at birth, total number of births, and total number of both male and female births from January 2010 to December 2021 were analyzed. Seasonally adjusted autoregressive moving-average models were used to estimate the functional form of the time series from January 2010 to February 2020. These results were used to predict the future values of the series until December 2021 and to compare them with the actual values. For all series used, there was no indication of deviation from the values predicted by the models, neither for 3-5 months nor for 9 months after the COVID-19 lockdown and earthquake events. The possible mechanisms of the absence of bias, such as the threshold of the stressful events and its localized reach, as well as the statistical methods employed, are discussed.

A time series analysis of monthly issuance of plant import permits in Nigeria

An import permit is issued by the National Plant Protection Organization of each country, known in Nigeria as the Nigeria Agricultural Quarantine Service (NAQS), to allow the importation of pest-free plants and prevent the introduction of quarantine pests or check the entry of regulated non-quarantine pests of imported plant commodities. Issuance of import permits at the Post-Entry Quarantine, Surveillance and Diagnostic Station (PEQDS), Ibadan is mostly for germplasm materials mainly used for cultivation, which poses a high risk of pest introduction. Thus, this study investigated the statistical components of the issuance of import permits at the PEQDS using the Time Series approach to determine the peak period of collection essential for planning phytosanitary activities to mitigate the introduction of foreign pests. The dataset of the monthly issuance of import permits from January 2012 to July 2022 was analysed. From the preliminary study, we observed that the series exhibit seasonal and stationary components with no definite trend pattern, hence we modelled the series using a Seasonal Autoregressive Moving Average (SARIMA) model. Several models were estimated and the best model (SAR(12)) for forecasting the future import permit collectionwas selected based on the forecast accuracy measures. The forecasted values indicated the highest issuance of import permits in May and September, each year and showed a fluctuating movement over time in the future. To further prevent pest incursion and facilitate trade, NAQS needs to operate round-the-clock surveillance, keep its staff on high alert and adequate facilities operational for more effective activities. Other factors responsible for low and fluctuating issuance of import permits should also be investigated.

Risk Modeling, Return Forecasting, and Optimal Portfolio Selection

The main objective of this research is to form an optimal investment portfolio consisting of a number of stocks selected according to specific criteria in Amman Stock Exchange and to test the ability of a various economic models to predict the performance of this portfolio in the foreseeable future. A time series for the return of the selected portfolio and for the return of a market index are formed. A set of tests were conducted to reach a stationary time series return and, then, to follow the Box-Jenkins methodology in order to build predictive models (ARMA) and to examine the residuals of models and to model them using ARCH and GARCH models to reach the best prediction of the performance of the portfolio and the market index in the forecasted periods. The data were tracked on a daily basis for the study sample and the market index simultaneously for a period of three years. Twenty-one companies were selected in the investment portfolio distributed among several sectors. The study concluded that the formed portfolio achieved a good diversification and gave a high return in relation to the lowest possible risk according to the Sharpe scale. Also, it is concluded that the model ARMA (1,1) is the most suitable for estimating market portfolio returns and forecasting risks for the market index return, and ARMA (2,1) and the model ARMA - GARCH are the most capable one of achieving good results that can be relied upon in tracking the performance of the studied investment portfolio.

Comparative study of the effectiveness of time series and arima modeling x RNA approach in a Multi Layer Perceptron (MLP) model in predicting fouled in petroleum pre-processing heat exchangers

This work presents a comparison between two approaches based on Artificial Intelligence techniques to predict critical deposition in the battery of shell and tube heat exchangers, used in petroleum pre-processing. Deposition or incrustation, which occurs on the thermal exchange surfaces of heat exchangers, during operation, can reduce the efficiency of this equipment and generate an increase in the cost of refining for the petrochemical plant due to the modification of ideal operating parameters and changes. process variables, such as flow, pressure and temperature, input and output of heat exchangers, as well as thermodynamic parameters, such as fouling resistance coefficient and global heat transfer coefficient. The proposed methods for comparing results used the analysis and prediction of time series based mainly on integrated autoregressive moving average (ARIMA) and Deep Learning models and, on the other hand, an artificial neural network (ANN) model based on the Multi Layer architecture. Perceptron (MLP) with the Backpropagation error backpropagation algorithm. The data was collected in exchangers of a petroleum preheating battery in the years 2014 to 2021. The general objective of this work is to present the results of both approaches and compare, since they aim to predict the deposition in the heat exchanger of the shell and tube type, thus helping to minimize maintenance costs and increase the energy efficiency of the petrochemical plant, making operations safer and more efficient, bringing significant benefits to the petroleum industry.

Deep learning approach for one-hour ahead forecasting of solar radiation in different climate regions

ABSTRACT The accurate prediction of hourly global solar radiation is critical to solar energy conversion systems selecting appropriate provinces, and even future investment policies. With this viewpoint, the aim of this study is to predict one hour ahead the global solar radiation of six provinces that have different climate regions in Turkey. A deep learning technique based on the LSTM neural network is used for this purpose. To see the success of this proposed model, the deep learning technique GRU, a machine-learning approach ANFIS with FCM, and standard statistical models ARMA, ARIMA, and, SARIMA are also applied. Forecasting models developed to estimate the future values of hourly global solar radiation are based on past time series data. The study discusses four different statistical metrics (MAE, RMSE, NSE, and, R) to determine the success of these algorithms. The results indicate that the R, MAE, NSE, and, RMSE values of the two approaches range from 0.9352 to 0.9806, from 29.0737 to 59.4840 Wh/m2, from 0.6445 to 0.9686 and from 57.4492 to 94.3287 Wh/m2, respectively. The results revealed that the methods used in the study performed satisfactorily in terms of hourly solar radiation estimation, but the LSTM method performed better.

A hybrid model enhancing streamflow forecasts in paddy land use-dominated catchments with numerical weather prediction model-based meteorological forcings

The development of a streamflow forecasting tool becomes a challenging task due to the sophisticated nonlinear catchment response, varying crop management practices, and limited in situ data availability. For real-time streamflow forecasting with up to 10-days lead-time, this study investigates the potential of SWAT-pothole (PSWAT) module forced with bias-corrected Global Forecasting System (GFS) meteorological variables; wherein the error-updating is carried out for the streamflow forecasts simulated by PSWAT. The error is updated by hierarchical data-driven sub-models, such as AutoRegressive (AR), AutoRegressive Moving Average with eXogenous inputs (ARMAX), Wavelet-based Neural Network (WNN), Wavelet-based Non-linear AutoRegressive with eXogenous inputs (WNARX), Long-Short Term Memory (LSTM), and a novel Wavelet-based Bidirectional LSTM (WBiLSTM). The efficacy of the standalone PSWAT module is tested against the hybrid models in the Brahmani-Baitarani (≈ 49,000 km2) compound River Basin in eastern India. The results revealed that the novel PSWAT-WBiLSTM hybrid model is the best for reliable streamflow forecasts up to 8-days’ and 9-days’ lead-times in the Brahmani and Baitarani River basins, respectively. Conclusively, this model can be a potential medium-range streamflow forecasting tool for paddy-dominated catchments.

The impact of COVID-19 on healthcare booking and cancellation patterns: time series analysis of private healthcare service utilisation in Finland

BackgroundCOVID-19 has had wide-reaching effects on healthcare services beyond the direct treatment of the pandemic. Most current studies have reported changes in realised service usage, but the dynamics of how patients engage with healthcare services are less well understood. We analysed the effects of COVID-19 on healthcare bookings and cancellations for various service channels between January 2020 and July 2021.MethodsOur data includes 7.3 million bookings, 11.0 million available appointments, and 405.1 thousand cancellations by 900.6 thousand individual patients between the ages of 18 and 65 years. The data were collected from electronic health record data, including laboratory and imaging services as well as inpatient stays, between January 2017 and July 2021. The patients were Finnish private and occupational healthcare customers in the capital region of Finland. We fitted an autoregressive moving average (ARIMA) model on data between 2017 and 2019 to predict the expected numbers of bookings, available appointments, and cancellations, which were compared to observed time series data between 2020 and 2021.ResultsUtilisation of physical, in-person primary care physician appointments decreased by up to 50% during the first 18 months of the pandemic. At the same time, digital care channels experienced a rapid, multi-fold increase in service usage. Simultaneously, the number of bookings for laboratory and imaging services decreased by 50% below the pre-pandemic projections. The number of specialist and hospital service bookings remained at the predicted level during the study period. Cancellations for most health services increased sharply by up to three times the pre-COVID levels during the first weeks of the pandemic but returned to the pre-pandemic levels for the rest of the study period.ConclusionsThe reduction in in-person appointments and the increase in the utilisation of digital services was likely a contributing factor in the decrease of the utilisation of diagnostic and imaging services throughout the study period. Utilisation of specialist care and hospital services were not affected. Cancellations contributed to the changes in service utilisation only during the first weeks of the pandemic.

Long-term solar radiation forecasting based on LSTM and attention mechanism: a case study in Algeria

The growing adoption of photovoltaic (PV) energy in urban areas underscores its capability to meet energy demands effectively. The accurate forecasting of meteorological parameters, particularly global solar radiation, is paramount for the efficient management and utilization of solar energy resources. Solar radiation forecasting methods typically fall into two main categories: cloud imagery combined with physical approaches, and Artificial Intelligence (AI) based methods. Due to the non-stationary nature of solar radiation and the high nonlinearity of atmospheric conditions, conventional forecasting approaches often exhibit poor accuracy. Artificial intelligence based approaches, such as machine learning and deep learning algorithms, are extensively employed in global solar radiation forecasting research, demonstrating impressive accuracy. In this respect, this paper presents a novel approach for long term monthly forecasting of global solar radiation using a Bidirectional Long Short-Term Memory (LSTM) architecture augmented with an attention mechanism that includes a Squeeze and Excitation (SE) block (SE-BiLSTM). The effectiveness of this model is extensively evaluated for long-term monthly solar radiation forecasting using meteorological data collected over a 20-year period (from Jan 2001 to Dec 2020) from the National Aeronautics and Space Administration (NASA). The proposed SE-BiLSTM model is compared with well-established forecasting models including Naïve, Autoregressive Moving Average (ARMA), Multi-layer Perceptron (MLP), LSTM, and Bidirectional LSTM. Through rigorous simulation tests, our model demonstrates superior performance, achieving the lowest mean absolute percentage error (MAPE) of 4.52% and mean absolute error (MAE) of 7.89 kW/m2. This advancement holds significant promise for enhancing solar energy forecasting accuracy and its practical application in renewable energy systems.

Multi-Objective Optimization of Cell Voltage Based on a Comprehensive Index Evaluation Model in the Aluminum Electrolysis Process

In the abnormal situation of an aluminum electrolysis cell, the setting of cell voltage is mainly based on manual experience. To obtain a smaller cell voltage and optimize the operating parameters, a multi-objective optimization method for cell voltage based on a comprehensive index evaluation model is proposed. Firstly, a comprehensive judgment model of the cell state based on the energy balance, material balance, and stability of the aluminum electrolysis process is established. Secondly, a fuzzy neural network (FNN) based on the autoregressive moving average (ARMA) model is designed to establish the cell-state prediction model in order to finish the real-time monitoring of the process. Thirdly, the optimization goal of the process is summarized as having been met when the difference between the average cell voltage and the target value reaches the minimum, and the condition of the cell is excellent. And then, the optimization setting model of cell voltage is established under the constraints of the production and operation requirements. Finally, a multi-objective antlion optimization algorithm (MOALO) is used to solve the above model and find a group of optimized values of the electrolysis cell, which is used to realize the optimization control of the cell state. By using actual production data, the above method is validated to be effective. Moreover, optimized operating parameters are used to verify the prediction model of cell voltage, and the cell state is just excellent. The method is also applied to realize the optimization control of the process. It is of guiding significance for stabilizing the electrolytic aluminum production and achieving energy saving and consumption reduction.