Comparative Analysis of Supervised Learning Techniques for Forecasting PV Current in South Africa

BackgroundMore than 79.2 million confirmed COVID-19 cases and 1.7 million deaths were caused by SARS-CoV-2; the disease was named COVID-19 by the World Health Organization. Control of the COVID-19 epidemic has become a crucial issue around the globe, but there are limited studies that investigate the global trend of the COVID-19 pandemic together with each country’s policy measures.ObjectiveWe aimed to develop an online artificial intelligence (AI) system to analyze the dynamic trend of the COVID-19 pandemic, facilitate forecasting and predictive modeling, and produce a heat map visualization of policy measures in 171 countries.MethodsThe COVID-19 Pandemic AI System (CPAIS) integrated two data sets: the data set from the Oxford COVID-19 Government Response Tracker from the Blavatnik School of Government, which is maintained by the University of Oxford, and the data set from the COVID-19 Data Repository, which was established by the Johns Hopkins University Center for Systems Science and Engineering. This study utilized four statistical and deep learning techniques for forecasting: autoregressive integrated moving average (ARIMA), feedforward neural network (FNN), multilayer perceptron (MLP) neural network, and long short-term memory (LSTM). With regard to 1-year records (ie, whole time series data), records from the last 14 days served as the validation set to evaluate the performance of the forecast, whereas earlier records served as the training set.ResultsA total of 171 countries that featured in both databases were included in the online system. The CPAIS was developed to explore variations, trends, and forecasts related to the COVID-19 pandemic across several counties. For instance, the number of confirmed monthly cases in the United States reached a local peak in July 2020 and another peak of 6,368,591 in December 2020. A dynamic heat map with policy measures depicts changes in COVID-19 measures for each country. A total of 19 measures were embedded within the three sections presented on the website, and only 4 of the 19 measures were continuous measures related to financial support or investment. Deep learning models were used to enable COVID-19 forecasting; the performances of ARIMA, FNN, and the MLP neural network were not stable because their forecast accuracy was only better than LSTM for a few countries. LSTM demonstrated the best forecast accuracy for Canada, as the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) were 2272.551, 1501.248, and 0.2723075, respectively. ARIMA (RMSE=317.53169; MAPE=0.4641688) and FNN (RMSE=181.29894; MAPE=0.2708482) demonstrated better performance for South Korea.ConclusionsThe CPAIS collects and summarizes information about the COVID-19 pandemic and offers data visualization and deep learning–based prediction. It might be a useful reference for predicting a serious outbreak or epidemic. Moreover, the system undergoes daily updates and includes the latest information on vaccination, which may change the dynamics of the pandemic.

This paper proposes a novel prediction model for photovoltaic (PV) system output current. The proposed model is based on cascade-forward back propagation artificial neural network (CFNN) with two inputs and one output. The inputs are solar radiation and ambient temperature, while the output is output current. Two years of experimental data for a 1.4 kWp PV system are utilized in this research. The monitored performance is recorded every 2 s in order to consider the uncertainty of the system’s output current. A comparison between the proposed model and other empirical and statistical models is done in this paper as well. Moreover, the ability of the proposed model to predict performance with high uncertainty rate is validated. Three statistical values are used to evaluate the accuracy of the proposed model, namely, mean absolute percentage error (MAPE), mean bias error (MBE), and root mean square error (RMSE). These values are used to measure the deviation between the actual and the predicted data in order to judge the accuracy of the proposed model. A simple estimation of the deviation between the measured value and the predicted value with respect to the measured value is first given by MAPE. After that, the average deviation of the predicted values from measured data is estimated by MBE in order to indicate the amount of the overestimation/underestimation in the predicted values. Third, the ability of predicting future records is validated by RMSE, which represents the variation of the predicted data around the measured data. Eventually, the percentage of MBE and RMSE is calculated with respect to the average value of the output current so as to present better understating of model’s accuracy. The results show that the MAPE, MBE, and RMSE of the proposed model are 7.08%, −0.21 A (−4.98%), and 0.315 A (7.5%), respectively. In addition to that, the proposed model exceeds the other models in terms of prediction accuracy.

Prophesying egg production based on energy consumption using multi-layered adaptive neural fuzzy inference system approach

This study compares the performance of standalone adaptive neuro-fuzzy inference system (ANFIS) and its hybrid with particle swarm optimisation (PSO) in predicting the energy consumption from climatic factors for a multi-campus institution in South Africa. Monthly weather condition datasets (average wind speed, average maximum temperature, average minimum temperature, average dew point and average relative humidity) for 36 months were mapped with the corresponding monthly energy consumption for each campus as the model inputs and output respectively. The ANFIS and ANFIS-PSO models were trained and tested with 70% and 30% of the dataset respectively. The root mean square error (RMSE), mean absolute deviation (MAD), mean absolute percentage error (MAPE) and the computational time were used to evaluate the model for the four campuses. The ANFIS standalone model developed for campus C outperforms other standalone models for campus A, B and D with the following performance indices: RMSE = 1.27, MAD = 1.01, MAPE = 13.34, computational time = 14.61 secs. On the contrary, the ANFIS-PSO model developed for campus D outperforms both the standalone and the hybrid models for campus A, B and C with the following values of performance indices except for computational time: RMSE = 0.147, MAD = 0.125, MAPE = 2.89, computational time = 95.60 secs. This study concludes that tuning ANFIS parameters with PSO offers a better prediction accuracy, which is reliable for strategic energy planning, though at a higher computational time.

This study investigated the accurate prediction of the calorific value of municipal solid waste (MSW) using soft computing systems, namely artificial neural networks (ANN), adaptive neural fuzzy inference system (ANFIS), support vector machine (SVM), and multi-layer perceptron (MLP). Calorific value of MSW is a crucial factor that exhibits the energy content of MSW, however, determining calorific value from conventional laboratory methods is quite expensive and difficult. The research focused on proximate analysis parameters obtained from the laboratory and utilized the measured calorific value to develop predictive models. All the models demonstrated a very good correlation between input and output, with consistently strong values of the coefficient of determination (R2). ANN SVM, MLP, and ANFIS models have respective R2 values of 0.9397, 0.8195, 0.7212, and 0.9979. ANFIS showed the best correlation with exceptional predictive power. Statistical parameters were determined to compare model accuracy, with ANFIS exhibiting the top performance, followed by ANN, and then MLP, which had the lowest values of mean square error (MSE), root mean square error (RMSE), mean absolute deviation (MAD), and mean absolute percentage error (MAPE) at 8.704E-07, 0.00019, 0.00016, and 1.295E-05 respectively. However, SVM has the least capability to predict calorific values accurately compared to other models. Soft computing Models, particularly ANFIS, demonstrated remarkable accuracy in predicting the calorific value.

This paper deals with the application of a novel neural network technique, support vector machine (SVM), in financial time series forecasting. This study applies SVM to predict the paying rate index. The objective of this paper is to examine the feasibility of SVM in paying rate forecasting by comparing it with a feed-forward backpropagation (BP) neural network. We choose Gaussian function as its kernel function. The experiment shows that SVM outperforms the feed-forward BP neural network based on the criteria of mean absolute error (MAE), mean absolute percent error (MAPE), mean squared error (MSE) and root mean square error (RMSE). Analysis of the experimental results proved that it is advantageous to apply SVMs to forecast paying rate

This paper presents a new method for predicting hourly ambient temperature series for Malaysia using generalized regression neural network (GRNN). MATLAB was used to develop the GRNN using the weather records for Malaysia. The developed model has five inputs and one output. The inputs of the proposed model are hour, day, month, sunshine ratio, and relative humidity, meanwhile ambient temperature is the output. To evaluate the accuracy of the GRNN, three statistical parameters, namely, the mean absolute percentage error (MAPE), mean bias error (MBE), and root mean square error (RMSE) are considered. The GRNN results give an accurate prediction of ambient temperatures for the selected testing months with average values of MAPE, MBE, and RMSE of 2.65%, 4.05%, and 0.347%, respectively. The advantage of the proposed method is that it is able to predict ambient temperature at sites where there is no ambient temperature-measuring instrument installed.

Nowadays , nonlinear time series and artificial neural networks (ANN) models are used for forecasting in the field of business, agriculture and soon. Recent studies have shown, ANN have been successfully used for forecasting of financial and agriculture data series The classical methods used for time series prediction like Box-Jenkins or ARIMA assumes that there is a linear relationship between inputs and outputs. ANN have more advantages that can approximate to model both linear and nonlinear structures in time series, they are not able to handling both structures equally well. The autoregressive integrated moving average (ARIMA) model and two ANN models namely, Radial basis function neural networks (RBFNN), and Elman recurrent neural networks (ERNN) methods were applied to Hyderabad airport traffic data. The data obtained for 15 years from 2002–2003 to 2016–2017 about domestic and international passenger of International Airport of Hyderabad, India. In this research paper, we compared the performances of ARIMA, RBFNN and ERNN were based on three measures: mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE). The results showed that RBFNN obtained the smallest MAE, MAPE and RMSE in both the modeling and forecasting processes. The performances of the three models ranked in ascending order were: ARIMA, ERNN and the RBFNN model. Keywords: T ime series, forecasting, artificial neural networks, ARIMA models, radial basis function neural networks, and Elman recurrent neural networks Cite this Article R. Ramakrishna, Berhe Aregay, Tewodros Gebregergs. The Comparison in Time Series Forecasting of Air Traffic Data by Autoregressive Integrated Moving Average Model, Radial Basis Function and Elman Recurrent Neural Networks. Research & Reviews: Journal of Statistics . 2018; 7(3): 75–90p.

Model evaluation is essential for ensuring the reliability, transparency, and practical usefulness of simulations in energy systems, environmental modeling, and sustainability science. However, the frequent misuse, misinterpretation, and isolated application of common performance metrics particularly root mean square error (RMSE), mean absolute percentage error (MAPE), and R 2 continue to undermine model credibility and lead to misleading conclusions. This study (i) reviews and defines five widely used evaluation metrics (mean absolute error [MAE], RMSE, mean bias error [MBE], MAPE, and R 2 ), including their mathematical foundations and conceptual meaning, (ii) compares their characteristics, strengths, and limitations, and (iii) provides context‐specific guidelines for selecting appropriate indicators based on modeling objectives and data behavior. Using a combined methodology consisting of a structured literature review, a controlled illustrative dataset, and sensitivity analysis, the study demonstrates how each metric responds to outliers and zero‐observation values. Results show that RMSE and MAE increase more under outlier conditions, MAPE becomes undefined when observed values reach zero, and R 2 collapses from 0.82 to below 0.05 when data irregularities are introduced. These findings highlight critical vulnerabilities that can distort evaluation if metrics are used in isolation. The study contributes a consolidated comparative framework, practical recommendations for multimetric reporting, and guidance for improving evaluation transparency in energy, environmental, and sustainability applications. Adopting a context‐aware, multimetric strategy enhances credibility, interpretability, and policy relevance of model‐based assessments in support of sustainable development goals (SDGs).

Deep learning approaches for bias correction in WRF model outputs for enhanced solar and wind energy estimation: A case study in East and West Malaysia

Supervised learning is mainly used to optimize Adaptive Neural Fuzzy Inference System (ANFIS) controllers. In order to generate data for supervised learning, a controller is designed and optimized using Particle Swarm Optimization (PSO) or any other algorithms. This paper proposes and compares reinforcement learning based ANFIS and Approximate Reasoning Intelligent controller (ARIC) controllers. Reinforcement learning based ANFIS reduces the work flow required to train it by directly optimizing the membership functions using Proximal Policy Optimization (PPO) algorithm. ANFIS and ARIC neuro fuzzy controllers are designed for nonlinear dynamics of coffee roasting process using Schwartzberg’s model. A custom layer is designed for every membership function and fuzzy inference operations using MATLAB’s Deep Learning Toolbox. This neural connectionist model of ANFIS and ARIC is used as actor. The critic which evaluates the goodness of action taken is a two-layer neural network with sigmoidal activation function. Simulink environment is also created to represent the dynamics of coffee roasting process. The agent is trained to track roast profile for 50 episodes. The training converged at 50th iteration. After training, the Root Mean Square Error (RMSE) for ARIC architecture reduced from 0.5134 to 0.08122. Similarly, the RMSE of ANFIS improved from 0.2026 to 0.0624.

The fluctuation of meteorological data causes random changes in photovoltaic (PV) performance, which may negatively affect the stability and reliability of the electrical grid. This paper proposes a new ultra-short-term offline hybrid prediction model for PV I-V characteristic curves based on the dynamic characteristics of the meteorological data on a 15-min basis. The proposed hybrid prediction model is a combination of the random forests (RFs) prediction technique and the ant-lion optimizer (ALO). ALO is used to optimize the hyper-parameters of the RFs model, which aims to improve its performance in terms of accuracy and computational time. The performance of the proposed hybrid prediction model is compared with that of conventional RFs, RFs-iteration, generalized regression neural network (GRNN), GRNN-iteration, GRNN-ALO, a cascade-forward neural network (CFNN), CFNN-iteration, CFNN-ALO, feed-forward neural network (FFNN), FFNN-iteration, and FFNN-ALO models. The result shows that the I-V characteristic-curve prediction accuracy, in terms of the root-mean-squared error, mean bias error, and mean absolute percentage error of the proposed model are 0.0091 A, 0.0028 A, and 0.1392%, respectively, with an accuracy of 99.86%. Moreover, the optimization, training, and testing times are 162.15, 10.1919, and 0.1237 s, respectively. Therefore, the proposed model performs better than the aforementioned models and the other existing models in the literature. Accordingly, the proposed hybrid (RFs-ALO) offline model can significantly improve the accuracy of PV performance prediction, especially in grid-connected PV system applications.

The flame retardancy of polymer materials is closely linked to the types and compositions of flame retardants used. However, due to the complex relationships involved, it is difficult to quantify and predict flame retardancy using linear equations and models. Alkyl phosphinate flame retardants have emerged as promising candidates for their environmentally friendly, low toxicity, and excellent flame retardant properties. In this study, we aimed to develop a novel, low‐cost alkyl phosphinate flame retardant by predicting the quantitative impact of flame retardant composition on flame retardancy. To establish prediction models for the limiting oxygen index (LOI) value of alkyl phosphinate flame retardants, we utilized artificial neural network (ANN) and adaptive neural fuzzy inference system (ANFIS) programs, namely ANN, ANFIS‐grid partition (GP), and ANFIS‐subtractive clustering (SC). The prediction models were trained and validated, and their reliability was assessed based on the root mean square error (RMSE), coefficient of determination (R2), and mean absolute percentage error (MAPE) criteria. Our results indicate that the ANFIS‐SC prediction model exhibits the highest reliability, with high accuracy and ideal prediction results.

<p>Accurate water level (WL) forecasting is important for water resources management and planning purposes in the Great Lakes. The objectives of this research are two-fold.  The first objective is to apply machine learning (ML) (i.e., random forest (RF) and support vector regression (SVR)) and hybrid convolutional neural network(CNN)-long-short term memory (LSTM) deep learning (DL) models for multi-step (i.e., one-, two- and three-monthly step ahead) WL forecasting in the Great Lakes (Michigan and Ontario). The second objective is to integrate the boundary corrected (BC) maximal overlap discrete wavelet transform (MODWT) with SVR, RF, and CNN-LSTM models to improve the performance of the individual models. By employing a BC-wavelet decomposition method, the ‘future data’ issue (i.e., data from the future that is not available), often overlooked in the literature and a major barrier to achieving realistic forecasting performance is overcome. </p><p>For Lakes Michigan and Ontario, 1212 monthly WL (m) records (spanning Jan 1918–Dec 2018) were used to develop the models. For the non-wavelet-based models (SVR, RF, and CNN-LSTM), candidate model inputs included the WL recorded over the previous 12 months.  For the BC-MODWT-based models (BC-MODWT-SVR, BC-MODWT-RF, and BC-MODWT-CNN-LSTM), the lagged input time series were decomposed into BC-wavelet and scaling coefficients by using different mother wavelets (Haar, Daubechies, Symlets, Fejer-Korovkin and Coiflets), filter lengths (from two up to 12) and decomposition levels (from one up to seven).  For each method (SVR, RF, and CNN-LSTM), mother wavelet, and decomposition level a model was generated.  For both wavelet- and non-wavelet-based models, the particle swarm optimization (PSO) method was used to select the most appropriate inputs to include in the proposed multi-step WL forecasting models.</p><p>The datasets were partitioned into calibration and validation subsets. After calibrating the models, various performance evaluation metrics, e.g., coefficient of determination (R<sup>2</sup>), root mean square error (RMSE), mean absolute error (MAE), root mean square percentage error (RMSPE), mean absolute percentage error (MAPE) and the Nash-Sutcliffe efficiency coefficient (NSC) were used to assess model accuracy.</p><p>Of the ML models, the SVR outperformed RF while the DL models outperformed the ML models for each forecast lead time (one-, two-, and three-step(s) ahead). Results from this case study indicate that not all wavelet families and decomposition levels perform equally and in some cases, the wavelet-based models do not improve performance over the non-wavelet-based models. However, the BC-MODWT-CNN-LSTM using suitable mother wavelets (e.g., Haar) outperforms the individual ML and BC-MODWT-ML-based models. More accurate forecasts were obtained for Lake Michigan although the performance in both Great Lakes was accurate. The outcomes of this research indicate that the BC-MODWT-CNN-LSTM model is a promising tool for generating accurate WL forecasts.</p>

본 연구는 Deep Neural Network(DNN)을 이용하여 광주-기아 챔피언스 필드의 일일 관중 수를 예측함으로써 이를 통해 구단과 관련기업의 마케팅 자료제공 및 구장 내 부대시설의 재고관리에 자료로 쓰임을 목적으로 수행 되었다. 본 연구 에서는 Artificial Neural Network(ANN)의 종류인 DNN 모델을 이용하였으며 DNN 모델의 과적합을 막기 위해 Dropout 과 Batch normalization 적용한 모델을 바탕으로 총 4종류를 설계하였다. 각각 10개의 DNN을 만들어 예측값의 Root Mean Square Error(RMSE)와 Mean Absolute Percentage Error(MAPE)의 평균값을 낸 모델과 예측값의 평균으로 RMSE와 MAPE를 평가한 Ensemble 모델을 만들었다. 모델의 학습 데이터는 2008년부터 2017년까지의 관중 수 데이터를 수집하여 수집된 데이터의 80%를 무작위로 선정하였으며, 나머지 20%는 테스트 데이터로 사용하였다. 총 100회의 데이터 선정, 모델구성 그리고 학습 및 예측을 한 결과 Ensemble 모델은 DNN 모델의 예측력이 가장 우수하게 나왔으며, 다중선 형회귀 모델 대비 RMSE는 15.17%, MAPE는 14.34% 높은 예측력을 보이고 있다.In this paper, we used the Deep Neural Network (DNN) to predict the number of daily spectators of Gwangju -KIA Champions Field in order to provide marketing data for the team and related businesses and for managing the inventories of the facilities in the stadium. In this study, the DNN model, which is based on an artificial neural network (ANN), was used, and four kinds of DNN model were designed along with dropout and batch normalization model to prevent overfitting. Each of four models consists of 10 DNNs, and we added extra models with ensemble model. Each model was evaluated by Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The learning data from the model randomly selected 80% of the collected data from 2008 to 2017, and the other 20% were used as test data. With the result of 100 data selection, model configuration, and learning and prediction, we concluded that the predictive power of the DNN model with ensemble model is the best, and RMSE and MAPE are 15.17% and 14.34% higher, correspondingly, than the prediction value of the multiple linear regression model.