R2 Values Research Articles

Capillary flow velocity-based length identification of PCR and RPA products on paper microfluidic chips.

This work demonstrates a novel, non-fluorescence approach to the length identification of polymerase chain reaction (PCR) and recombinase polymerase amplification (RPA) products, utilizing capillary flow velocities on paper microfluidic chips. It required only a blank paper chip, aminated microspheres, and a smartphone, with a rapid assay time and under ambient lighting. A smartphone evaluated the initial capillary flow velocities on the paper chips for the PCR and RPA products from various bacterial samples, where the pre-loaded aminated microspheres differentiated their flow velocities. Flow velocities were analyzed at different time frames and compared with the instantaneous flow velocities and interfacial tension (γLV) data. Subsequent error analysis justified the use of the initial time frames. A robust linear relationship could be established between the initial flow velocities against the square root of the product lengths, with R2 values of 0.981 for PCR and 0.993 for RPA. The assay seemed not to have a significant dependency on the cycle numbers and initial target concentrations. This novel method can be potentially used with various paper microfluidic methods of nucleic acid amplification tests towards rapid and handheld assays.

Modelling of Power Semiconductor Devices Switching and Conduction Losses in a Power Electronic System

In power converters, power semiconductor devices, mainly Insulated-Gate Bipolar Transistor (IGBT), are generally used as they are less costly and capable of converting electrical energy into high frequency and voltage. It is critical to accurately determine the switching and conduction losses of power devices before they are assembled into an electronic system. The accurate values help to minimize power loss in a power converter system. With the aid of simulation, design problems are identified to help eliminate device destruction, and critical parameters are monitored. In addition, costly equipment for measuring purposes and testing prototypes is not required at the initial design stage. This research uses simulation work in a power converter system to predict IGBT and diode losses with varied frequencies and voltages. The predictive modelling is produced using regression analysis. The models have been validated by R square (R2) and Mean Absolute Percentage Error (MAPE) techniques. This work is aimed at providing a supervised learning technique mainly used in a machine learning environment, in line with the technological development in the semiconductor industry. With the simulation performed in this work, the efficiency of a boost converter system is enhanced as it shows the models have a good fit with an R2 value of almost 1, and MAPE values are noticed to be less than 5%.

Enhanced Crop Leaf Area Index Estimation via Random Forest Regression: Bayesian Optimization and Feature Selection Approach

The Leaf Area Index (LAI) is a crucial structural parameter linked to the photosynthetic capacity and biomass of crops. While integrating machine learning algorithms with spectral variables has improved LAI estimation over large areas, excessive input parameters can lead to data redundancy and reduced generalizability across different crop species. To address these challenges, we propose a novel framework based on Bayesian-Optimized Random Forest Regression (Bayes-RFR) for enhanced LAI estimation. This framework employs a tree model-based feature selection method to identify critical features, reducing redundancy and improving model interpretability. A Gaussian process serves as a prior model to optimize the hyperparameters of the Random Forest Regression. The field experiments conducted over two years on maize and wheat involved collecting LAI, hyperspectral, multispectral, and RGB data. The results indicate that the tree model-based feature selection outperformed the traditional correlation analysis and Recursive Feature Elimination (RFE). The Bayes-RFR model demonstrated a superior validation accuracy compared to the standard Random Forest Regression and Pso-optimized models, with the R2 values increasing by 27% for the maize hyperspectral data, 12% for the maize multispectral data, and 47% for the wheat hyperspectral data. These findings suggest that the proposed Bayes-RFR framework significantly enhances the stability and predictive capability of LAI estimation across various crop types, offering valuable insights for precision agriculture and crop monitoring.

Application of time series and multivariate statistical models for water quality assessment and pollution source apportionment in an Urban River, New Jersey, USA

Water quality monitoring reveals changing trends in the environmental condition of aquatic systems, elucidates the prevailing factors impacting a water body, and facilitates science-backed policymaking. A 2020 hiatus in water quality data tracking in the Lower Passaic River (LPR), New Jersey, has created a 5-year information gap. To gain insight into the LPR water quality status during this lag period and ahead, water quality indices computed with 16-year historical data available for 12 physical, chemical, nutrient, and microbiological parameters were used to predict water quality between 2020 and 2025 using seasonal autoregressive moving average (ARIMA) models. Average water quality ranged from good to very poor (34 ≤ µWQI ≤ 95), with noticeable spatial and seasonal variations detected in the historical and predicted data. Pollution source tracking with the positive matrix factorization (PMF) model yielded significant R2 values (0.9 < R2 ≤ 1) for the input parameters and revealed four major LPR pollution factors, i.e., combined sewer systems, surface runoff, tide-influenced sediment resuspension, and industrial wastewater with pollution contribution rates of 23–30.2% in the upstream and downstream study areas. Significant correlation of toxic metals, nutrients, and sewage indicators suggest similarities in their sources.Graphical

Artificial neural network (ANN) approach in predicting the thermo-solutal transport rate from multiple heated chips within an enclosure filled with hybrid nanocoolant

This study focuses on enhancing heat and mass transfer in an electronic cooling system such as a rectangular cavity that contains equidistant heated chips along the bottom wall. The cavity of the present study is filled with ethylene glycol (30:70) based hybrid nano coolants of different volume fractions (ϕ) of Multi-walled Carbon Nanotube (MWCNT), Aluminum Oxide (Al2O3), and Copper Oxide (CuO). The set of equations controlling the thermo-solutal natural convection within the enclosure is simulated using the Galerkin weighted residual finite element method (FEM). The study has shown a good agreement of numerical results with different experimental reports within the framework of the present study. A solution space is constructed based on governing parameters such as Rayleigh number, buoyancy ratio, and Lewis number. A hybrid nano-coolant containing ϕMWCNT = 1.5 %, ϕCuO = 0.5 %, and ϕAl2O3 = 2 % showed a 3.11% improvement in heat transfer rate compared to the base fluid, highlighting its potential for thermal management applications. This study also investigates various machine learning models for predicting the heat and mass transfer rate, and an error analysis is conducted on the K-Nearest Neighbour Regressor, Random Forest Regressor, Decision Tree Regressor, and ANN model. The ANN model with 6-50-100-50-2 architecture showcases the best fit with the mean squared error of 0.8923 and an R² value of 99.96 % on testing data. The ANN model exhibits its capability to predict heat transfer and mass transfer rates within the error ranges from 1–2 % and 2–3 %, respectively, even at a strong thermal buoyancy force (Ra = 10⁵). This accuracy showcases a novel use of ANN to efficiently predict thermo-fluidic transport behaviors of hybrid nanofluids, offering a faster alternative to resource-intensive simulations. The present study opens new possibilities for real-time, cost-effective cooling solutions, particularly in microelectronics and renewable energy, while maintaining high prediction accuracy by integrating machine learning with the nanotechnology approach.

Predictive pretrained transformer (PPT) for real-time battery health diagnostics

Modeling and forecasting the evolution of battery systems involve complex interactions across physical, chemical, and electrochemical processes, influenced by diverse usage demands and dynamic operational patterns. In this study, we developed a predictive pre-trained Transformer (PPT) model equipped with 1,871,114 parameters that enhance identification of both short-term and long-term patterns in time-series data. This is achieved through the integration of convolutional layers and probabilistic sparse self-attention mechanisms, which collectively enhance prediction accuracy and efficiency in diagnosing battery health. Moreover, the customized hybrid-model fusion supports parallel computing and employs transfer learning, reducing computational costs while enhancing scalability and adaptability. Consequently, this allows for precise real-time health estimations across various battery cycles. We validated this method using a public dataset of 203 commercial lithium iron phosphate (LFP)/graphite batteries charged at rates ranging from 1C to 8C. By using only partial charge data—from an 80 % state of charge to the maximum charging voltage (3.6 V for LFP batteries, 4.2 V for ternary batteries)—and avoiding complex feature engineering, error metrics were achieved below 0.3 % for root mean square error (RMSE), weighted mean absolute percentage error (WMAPE), and mean absolute error (MAE), with an R2 of 98.9 %. The generalization capabilities were further demonstrated across 36 different testing protocols, encompassing 23,480 cycles throughout the entire life cycle, with a total inference time of 9.88 s during the testing phases. Further experiments on 30 nickel cobalt aluminum (NCA) batteries and 36 nickel cobalt manganese (NCM) batteries, across different battery types and operational scenarios, resulted in RMSE, WMAPE, and MAE all below 0.9 %, with R2 values of 94.1 % and 94.4 %, respectively. These findings highlight the potential of our customized deep transfer neural networks to enhance diagnostic accuracy, accelerate training, and improve generalization in real-time applications.

Wingate anaerobic test as a potential predictor of 500-m time in short track speed skating

ABSTRACT Short-Track Speed Skating (STSS) is an Olympic discipline in which anaerobic performance plays a central role. An established assessment tool for anaerobic performance in STSS athletes is the Wingate Anaerobic Test (WAnT). The aim of this study was to investigate whether WAnT could be used as a predictor of sport-specific performance in the STSS 500-m races. Data from 72 German national STSS athletes (33 female, 39 male) were analysed retrospectively. The statistical analyses included descriptive procedures as well as linear mixed-model analyses. The results showed significant correlations between WAnT outcomes and 500 -m performance of STSS athletes. In male athletes, the coefficients were −0.40 for relative Mean Power (rMP) and −0.32 for relative Peak Power (rPP) (p < 0.001). For female athletes, the rMP showed no significant correlation whereas rPP was significantly correlated with a coefficient of −0.41 (p < 0.001). Marginal R2 values ranged between 0% and 12%. Conditional R2 reached up to 76% depending on sex and WAnT parameter investigated. In conclusion while WAnT can be regarded as a potential predictor of time in 500-m STSS races, it should be used in conjunction with other performance metrics and individualized assessments to better predict performance.

Rapid Method for Simultaneous Determination of γ-Oryzanol Compounds in Rice (Oryza sativa) Grains using UV-Vis Spectroscopy and Chemometrics

Rice (Oryza sativa) contains γ-oryzanol, which consists of 4 main compounds: Cycloartenol ferulate, 2,4-methylenecycloartanyl ferulate, campesterol ferulate, and β-sitosterol ferulate, that contribute to the health benefits of rice. This research aimed to develop a rapid method to determine the 4 major γ-oryzanol compounds in 45 varieties covering pigmented (black and red) and non-pigmented (white) rice grain. The method was developed by integrating UV-Vis spectroscopy with chemometrics, specifically principal component analysis (PCA) and partial least square (PLS) regression. Sampling was performed across the Indonesian archipelago collecting 180 samples, which comprises 60 samples for each type of rice in form of rice husk, bran, whole grain, and polished rice. The results of PCA on the spectroscopic data successfully identified distinction for the 3 types of rice attributable by different type and levels of chemical compound in the grain. White rice exhibited a characteristic absorption at 325 nm while in pigmented (red and black) rice showed a maximum absorbance at 280 nm, indicating the presence of different composition of chemical compounds. A reliable model to predict the 4 major γ-oryzanol compounds was established with R2 calibration, R2 cross-validation, and R2 prediction higher than 0.9 was obtained using the spectroscopic data in the range from 200 to 400 nm. However, the PLS modeling was unsuccessful for red and black rice samples most likely due to the interfering high absorption of red colored compounds. Compared to the existing techniques for analyzing individual compounds of the γ-oryzanol by high-performance liquid chromatography, the newly developed approach using UV-Vis spectroscopy combined with chemometrics is more practical, faster, and cost-efficient and mainly, solvent and residues free. HIGHLIGHTS A rapid method was developed to determine 4 major γ-oryzanol compounds in rice. This method integrates UV-Vis spectroscopy with PCA and PLS regression chemometrics. PCA successfully identified the distinction among white, red, and black rice types. Reliable PLS models were established for white rice with R2 values above 0.9. The developed approach is more practical, faster, and residue-free than HPLC. GRAPHICAL ABSTRACT

Analysis of the Impact of Strategic Thinking on Organizational Performance of Manufacturing Firms in Delta State Nigeria.

This study was carried out to examine the analysis of the impact of strategic thinking on organizational performance of manufacturing firms in Delta State, Nigeria. The objective of the study was to examine the impact of strategic thinking on organizational performance of manufacturing firms in delta State Nigeria. Structured questionnaire was used to obtain primary data from the employees of the manufacturing organizations, namely, Asaba Textile Mill Ltd, Coca-Cola Nigeria Plc, and Delta Glass Nigeria Plc. The hypotheses formulated were subjected to statistical tests using Regression analysis and correlation with the aid of SPSS. The findings or results of the study revealed that strategic thinking has a significant effect on corporate performance of manufacturing firms in Delta State Nigeria with the R2 value of 0.662. Strategic thinking is significantly and positively related on employee productivity of manufacturing firms in Delta State. That strategic thinking has a significant and positive relationship on employee efficiency of manufacturing firms in Delta State, Nigeria with R2 value of 0.681. From the findings of the study, it was concluded that strategic thinking has a significant positive impact on organizational performance since the majority of the stated variables are statistically significant with one another. The study therefore, recommended that in order to enhance or promote strategic thinking, an organization should emphasize to the employees the importance of strategic thinking for the growth of the organization. Finally improvement in the award scheme on the part of management in order to encourage managers and employees.

New generalized expressions for forced convective heat transfer coefficients across the flat plate

This study presents a novel generalized model for forced convective heat transfer coefficients (CHTC) over flat plates, addressing key limitations in existing models. Current expressions often provide averaged values and fail to capture the local variations in heat transfer, leading to inaccuracies, particularly in transitional zones. Moreover, there is no consensus on boundary layer classifications, which further complicates the development of reliable CHTC models. To address these issues, we conduct extensive CFD simulations to systematically analyze the combined effects of plate length (L), wind velocity (v), position along the plate (x), and temperature difference (Δt) on local CHTC. The simulations span a wide range of conditions (0.25 m ≤ L ≤ 8 m, 3 m/s ≤ v ≤ 25 m/s, and 5 °C ≤ Δt ≤ 80 °C), creating a comprehensive database of local CHTC values. Based on this data, a new generalized CHTC expression is derived as a function of L, v, x, and Δt, accurately predicting CHTC across laminar, transitional, and turbulent zones of flat plats. The accuracy of proposed CHTC expression is verified through thorough in-sample and out-of-sample evaluations, achieving R2 values between 0.973 and 0.999, with maximum deviations ranging from 2.6 % to 8.5 %. These research methods and conclusions can provide valuable references for optimizing thermal processes in applications such as industrial heat exchangers, electronics cooling, and building heating systems, where precise heat transfer modeling is critical for enhancing efficiency and system design.

An experimental investigation to predict the compressive strength of lightweight Ceramsite aggregate UHPC using boosting and bagging techniques

Ceramsite aggregate concrete is renowned for its lightweight properties but often exhibits low compressive strength (CS), limiting its structural applications. This study introduces ultra-high-performance powder into Ceramsite aggregate concrete to enhance its CS while maintaining low density. Achieving optimal CS for this composite material requires a carefully designed mix. In this research, advanced machine learning (ML) techniques, including random forest, extreme gradient boosting, categorical boosting, light gradient boosting machine (LightGBM), natural gradient boosting (NGBoost), and adaptive boosting, were employed to predict the CS of lightweight Ceramsite aggregate UHPC (LWCA-UHPC). The study utilized 189 datasets from the authors' own experimental results for training and testing the models. The results demonstrated that NGBoost and LightGBM outperformed other models, with R² values of 0.9614 and 0.9645, respectively, in the testing phase. The models also showed low errors, with NGBoost having a mean absolute error (MAE) of 2.0624 and a root mean squared error (RMSE) of 2.9140, while LightGBM recorded an MAE of 2.0161 and an RMSE of 2.7778. Moreover, feature importance and Shapley additive explanations (SHAP) analyses revealed that the most influential factors affecting the CS of LWCA-UHPC were cement content, density, sand, and Ceramsite aggregate content, consistent with experimental findings. Additionally, a graphical user interface was developed to integrate the hybrid ML model into a user-friendly desktop tool, achieving an R² value of 0.9671 with a low mean squared error of 3.5204 when tested against experimental datasets. This tool not only enables practical applications in engineering but also helps reduce the need for extensive experimental work by providing accurate predictions of CS.

Investigation of the relationship between socioeconomic status and literacy in PISA Türkiye data

Previous researchers have identified socioeconomic status as a significant predictor of achievement/literacy. However, it is important to recognize that the influence of socioeconomic status on literacy may vary at different levels of socioeconomic status. Thus, this study analyzes the relationship between socioeconomic status and literacy scores for all domains in PISA Türkiye data from 2003 to 2022 through the Classification and Regression Trees and linear regression methods. Upon examining the results, separate investigations carried out for the lower and upper socioeconomic status groups indicate that R2 values were found to be equal to or greater than .80 in 37 out of the 42 analyses. From 2003 to 2009, the R2 values in both groups were considerably high; however, there has been a notable decline in subsequent periods. The year 2009 demonstrated particularly high R2 values by ESCS in all domains for both upper and lower groups. Consequently, socioeconomic status exhibited a greater predictive power on literacy scores across all domains in the lower socioeconomic group than upper socioeconomic group.

Pt/ZnO and Pt/few-layer graphene/ZnO Schottky devices with Al ohmic contacts using Atlas simulation and machine learning

The search for highly efficient photodetectors, driven by various applications ranging from environmental monitoring to communication systems and imaging, continues to drive research into novel materials and innovative device architectures. This paper offers an in-depth comparative analysis to optimize the performance of two types of Schottky ultraviolet (UV) photodetectors: platinum (Pt)/zinc oxide (ZnO) and Pt/few-layer graphene (FLG)/ZnO, both featuring aluminum (Al) ohmic contacts. The study systematically examines and compares the electrical and optical characteristics of these two photodetector configurations using the Silvaco TCAD simulation tool and machine learning regression models. The research outcomes demonstrate that the proposed photodetector configurations exhibit remarkable improvements, showcasing their substantial potential for superior performance in UV applications. The Pt/ZnO photodetector demonstrates a dark current density of 8.2 × 10−11 pA/cm2, a photocurrent density of 0.26 μA/cm2, a 3-dB cut-off frequency of 85.4 GHz, an external quantum efficiency of 90.41%, and an external photocurrent responsivity of 0.26A/W, at a bias of −1.0 V. On the other hand, Pt/FLG/ZnO photodetector demonstrates near zero dark current density, a photocurrent density of 0.2 μA/cm2, a 3-dB cut-off frequency of 2.44 THz, an external quantum efficiency of 68.52%, and an external photocurrent responsivity of 0.2 A/W at a bias of −1.0 V. Furthermore, a comprehensive comparative analysis of various machine-learning regression models is conducted, validating the simulation findings and providing a predictive framework for optimizing the photodetector's performance. Each machine-learning regression model is evaluated by getting root mean squared error and R2 values across different test set sizes to assess their accuracy in predicting the photodetector's characteristics. This study underscores the promising role of cutting-edge materials and computational techniques in advancing the development of next-generation optoelectronic devices with enhanced capabilities and performance.

Cryptocurrency Security Risk: Awareness Among General Public in Malaysia

In the age of digital payments, cryptocurrencies have gained significant attention as an alternative investment option. However, security risks such as phishing, hacking, and fraudulent exchanges present challenges for investors. This study aims to assess the level of awareness among the general public in Malaysia regarding cryptocurrency security risks. A quantitative research method was employed, using a survey questionnaire distributed to 150 Malaysian citizens via social media platforms. The questionnaire explored respondents' knowledge of cryptocurrencies, awareness of security risks, and protective measures such as security programs, two-factor authentication (2FA), and education. The results of the regression analysis show that the installation of security programs, 2FA, and public education are all significant predictors of increased awareness of cryptocurrency security risks, with a combined R² value of 0.523. This suggests that 52.3% of the variance in awareness is explained by these factors. The study concludes that strengthening security measures and providing education can significantly improve public understanding of cryptocurrency risks, leading to safer investment practices. The implications of these findings highlight the need for targeted education and security initiatives to enhance public confidence in cryptocurrency, making digital currency investments more secure

Garbage prediction using regression analysis for municipal corporations of Indian cities

AbstractGarbage management is exceptionally critical and poses enormous environmental challenges. It has always been a vital issue in municipal corporations. However, municipal agencies have developed and used garbage management systems. Garbage forecasting still plays a crucial role in the management system and helps improve or create a garbage management system. This research examines the information from 212 cities to suggest a helpful regression model for garbage forecasting and control. To establish a connection between the variables, the descriptive study employs statistical techniques to learn about the composition of data collected from municipal corporations and conduct correlation analysis. Population and garbage depend highly on one another, as evidenced by their correlation coefficient of 0.922,144. The primary research is used to build an alternate hypothesis that shows the chosen variables are highly dependent on one another. The dataset is scaled and divided into a training and testing 80:20 ratio during the pre‐processing data phase. This research aims to do a regression analysis with daily garbage production, urban area, and population as independent variables. This research initiates a variety of regression models, including multiple linear regression (MLR), artificial neural network (ANN), decision tree regression (DTR), and random forest regression (RFR). The MLR model's R2 value of 0.85 indicates that it has the potential to accurately forecast daily garbage production based on just two independent variables and a single dependent variable. Random Forest Regression (RFR) with (MSE: 100,078.749 &amp; MAE: 182.212) shows that it has the lowest MSE among all the models, which provides the most accurate predictions on average and the fit values of 8.85 and 316.23 obtained from the error distribution with a bin value 25. The estimated results from each model are compared to the test data values on line graphs and Taylor plots. The mean square error and the mean absolute error in the analysis and the Taylor plot show that the RFR model is best suited for predicting daily garbage production in a city. This research, therefore, provides a Random Forest model that is optimal for such challenges and is recommended for this class of problem.

Analyzing the Fast-Food Marketing Strategies Impacting Consumer Buying Behavior

Kentucky Fried Chicken (KFC) has long been a dominant player in the global fast-food industry, known for its distinct fried chicken offerings. This study explores the effect of KFC’s marketing strategies on consumer buying behavior, using the marketing mix framework (4P: Product, Price, Place, Promotion). Primary data were gathered from a survey of 150 consumers in Malaysia via Google Forms, while secondary data included company reports and industry publications. Regression analysis was employed to determine the relationship between the independent variables (product, price, promotion, and place) and consumer buying behavior. Results indicated that product, price, and promotion significantly impact consumer decisions, with the product being the most influential factor (beta = 0.525). Price and promotion also had positive, albeit smaller, effects, while place was statistically insignificant. The R² value of 0.755 suggests that 75.5% of consumer behavior variation can be explained by these factors. These findings underscore the importance of product differentiation and effective promotional strategies in shaping consumer preferences, while the role of physical locations may be diminishing in the fast-food sector due to the rise of delivery services

The Development of Training Center as a Novel Business Concept

The objective of this study is to evaluate the effectiveness of innovative training methods, technology integration, personalized training, and strategic partnerships in enhancing business performance through the Qatar Skills Training Centre (QSTC). Employing quantitative methods, data were collected through a survey distributed via Google Forms, with responses from 154 participants representing various socio-economic backgrounds. The analysis revealed that while strategic partnerships did not significantly affect business performance, innovative training methods, technology integration, and personalized training demonstrated positive correlations with business success, supporting Hypotheses 1, 2, and 3. The results showed beta values of 0.588, 0.246, and 0.188 for these factors, respectively, and an R² value of 0.92, indicating that 92% of the variance in business performance is attributable to these elements. This highlights the critical role of innovative training methods, technology, and personalization in driving successful business strategies. The findings suggest that organizations should prioritize these factors to enhance employee engagement, satisfaction, and overall operational effectiveness

The Impact of Food Quality on Customer Satisfaction: A Study of Fast-Food Business

This study investigates the impact of food quality on customer satisfaction at KFC, focusing on key factors such as taste, packaging or presentation, and freshness. The primary objective is to analyze how these factors influence customer satisfaction and loyalty among KFC customers in Malaysia, India, and Indonesia. Data were collected through an online survey using Google Forms, targeting 150 KFC customers across the three countries. Respondents rated their experiences on a 5-point Likert scale, with the survey distributed via social media platforms like WhatsApp, Telegram, and Instagram. The results reveal that taste and customer loyalty significantly influence customer satisfaction, with taste having a β value of 0.262 and loyalty showing the strongest effect with a β value of 0.537. In contrast, packaging and freshness did not show a significant impact on satisfaction. The R² value of 0.637 indicates that 63.7% of customer satisfaction can be explained by these factors. In conclusion, the findings highlight the critical role of taste and loyalty in driving satisfaction at KFC, with implications for focusing on food quality and customer relationship strategies to enhance satisfaction and customer retention

Wind power prediction based on deep learning models: The case of Adama wind farm

Wind is a renewable energy source that is used to generate electricity. Wind power is one of the suitable solutions for global warming since it is free from pollution, doesn't cause greenhouse effects, and it is a natural source of energy. However, Wind power generation highly depends on weather conditions. It is very difficult to easily predict the amount of power generated from wind at a particular instant in time. Adama wind power farm is one of the wind farms in Ethiopia. There is no accurate and reliable forecasting model for the Adama wind farm that enables the forecasting of the power generated from the farm. The main objective of this research is to develop a wind power forecasting model for the Adama wind farm using deep learning techniques. Forecasting of wind power generation capacity involves appropriate modeling techniques that use past wind power generation data. The experiments have been conducted using Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (Bi-LSTM) and Gated Recurrent Unit (GRU). To achieve the highest forecasting accuracy, four years of data (from 2016 to 2019), with 5-min intervals, have been collected with a total of 163,802 rows. For hyperparameter optimization grid search and random search techniques have been utilized. The performances of the proposed deep learning models were investigated error metrics, including Mean Absolute Errors (MAE) and the Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE) and R squared (R2). Bi-LSTM outperforms the other two algorithms, scoring 0.644, 0.388, 0.769 and 0.978 MAE, MAPE, RMSE and R2 values respectively. Such wind power forecasting helps energy planners and regional power providers to compute power production and energy generated from other sources.

Household energy consumption forecasting based on adaptive signal decomposition enhanced iTransformer network

With the presence of volatility and noise in the energy consumption data, existing energy consumption forecasting methods have difficulties in achieving satisfactory forecasting results from multiple perspectives, including accuracy, robustness, generalization, and efficiency. This study introduces a novel energy consumption forecasting framework that combines the adaptive signal decomposition method and iTransformer (ASSA-iTransformer) to tackle the above-mentioned difficulties. Each subsequence obtained by ASSA decomposition was fed into the iTransformer framework, and deep-level time series information was extracted. Compared to state-of-the-art methods across various evaluation dimensions, ASSA-iTransformer has improved the average mean absolute error (MAE) by 23.7%, root mean square error (RMSE) by 27.6%, and mean absolute percentage error (MAPE) by 16.4%. Moreover, the R2 values on five real-world household energy consumption datasets are close to 1, demonstrating overall outstanding performance.