Data selection using support vector regression

As the volume of scientific publications increases, the need for automated approaches to evaluate and analyze abstracts becomes increasingly important. This research not only aims to predict the abstract rating of scientific publications using machine learning algorithms, but also offers a unique approach by integrating regression and classification analysis to evaluate the relevance of abstracts more comprehensively. Four main models, namely XGBoost Regressor, Random Forest Regressor, Support Vector Regressor (SVR), and K-Nearest Neighbors Regressor (KNN), are evaluated for this task. The dataset is processed through preprocessing stages which include removing duplications, text representation using TF-IDF, handling data imbalances with Synthetic Minority Oversampling Technique (SMOTE), and dimension reduction using Truncated Singular Value Decomposition (SVD). The research results show that SVR provides performance the best with the lowest Mean Absolute Error (MAE) value of 0.4980, Mean Squared Error (MSE) of 0.5237, and the highest R² of 0.7321. XGBoost and Random Forest show competitive performance with advantages in computational efficiency and prediction stability respectively, while KNN provides varying results depending on the data distribution. Dimensionality reduction using Truncated SVD successfully preserves more than 70% of the initial variance, enabling higher computational efficiency without losing important information. This research makes a significant contribution in supporting machine learning-based decision making, especially in the analysis of abstracts of scientific publications. This approach can be further developed through exploration of ensemble or hybrid models, as well as testing on larger datasets to improve generalization and accuracy.

Due to the rapid adoption of renewable energy sources and the increasing complexity of residential electricity consumption, there is a growing need for intelligent, scalable, and context-aware energy management systems in smart homes. This paper presents an artificial intelligence (AI)-based model that integrates high-resolution household power forecasting with dynamic demand response (DR) simulations to optimize energy consumption, enhance grid stability, and support sustainable energy transitions. Using the publicly available UCI Smart Home Energy dataset, a seven-step framework was implemented, including data preprocessing, exploratory data analysis (EDA), feature engineering, and the development of various predictive models—linear regression (LR), random forest regressor (RFR), support vector regression (SVR), k-nearest neighbors (k-NN), and long short-term memory (LSTM) neural networks. Each model was evaluated under seven DR strategies to capture temporal dependencies and nonlinear load behaviors: Peak Clipping, Valley Filling, Load Shifting, Load Leveling, Time-of-Use (ToU) Optimization, Price-Based Control, and Behavioral DR. Model performance was assessed using the mean absolute error (MAE), root mean squared error (RMSE), and the coefficient of determination ( R ²). Results revealed that the LSTM model achieved the highest accuracy, with the lowest MAE (18.95 Wh), lowest RMSE (24.83 Wh), and highest R ² (0.94) under the Price-Based DR strategy. Random forest emerged as the most effective traditional model, yielding an MAE of 25.13 Wh and R ² of 0.89, particularly for Behavioral and ToU-based DR strategies. The SVR and k-NN models provided moderate accuracy, while LR performed poorly, underscoring its limitation in modeling nonlinear and dynamic energy patterns. DR simulations indicated that Price-Based, Behavioral, and ToU Optimization strategies achieved the best alignment between household loads and grid requirements while maintaining user flexibility. Visualization tools such as heatmaps, grouped bar plots, and R ² comparisons further confirmed the superior temporal modeling capability of deep learning (DL) methods. Overall, the proposed framework offers a scalable and interpretable AI-driven platform that integrates load forecasting with DR evaluation, demonstrating that DL—particularly LSTM—can substantially enhance forecasting accuracy, enable smarter DR programs, and promote sustainable energy management in smart homes.

Tropical cyclones (TCs) are destructive meteorological phenomena, necessitating accurate predictions of TC track and intensity to reduce risks to human life. This study evaluates three Transformer-based models – vanilla Transformer (Transformer), inverted Transformer (iTransformer), and temporal-variate Transformer (TVFormer) – which are trained, validated, and tested on best track data from 1980 to 2021 from the China Meteorological Administration for TC prediction, integrating temporal, variate, and hybrid token embeddings to analyze temporal and variate correlations. Comparative analysis with four recurrent neural network (RNN) models demonstrates the superiority of the refined Transformer models over RNNs: iTransformer reduces mean absolute error (MAE) and root mean square error (RMSE) by 29.55% and 25.80% (latitude), 50.31% and 46.18% (longitude), 8.71% and 9.98% (pressure), and 8.68% and 9.45% (wind speed), while TVFormer achieves MAE and RMSE reductions of 13.98% and 13.84% (latitude), 39.11% and 38.02% (longitude), 13.69% and 14.02% (pressure), and 12.84% and 12.94% (wind speed) on average. Among Transformer variants, iTransformer excels in track prediction, outperforming Transformer with 21.74% lower MAE and 18.26% lower RMSE for latitude, and 32.73% lower MAE and 24.01% lower RMSE for longitude. TVFormer dominates intensity prediction, reducing pressure errors by 4.42% (MAE) and 3.92% (RMSE) and wind speed errors by 19.21% (MAE) and 14.79% (RMSE) compared to Transformer, while outperforming iTransformer with 4.59% lower MAE and 3.68% lower RMSE for pressure and 3.83% lower MAE and 3.18% lower RMSE for wind speed. Notably, TVFormer also enhances track prediction, with 7.10% reduction in MAE and 7.02% reduction in RMSE for latitude, and 22.84% reduction in MAE and 17.09% reduction in RMSE for longitude compared to Transformer. These results highlight the superiority of iTransformer in track prediction and the efficacy of TVFormer in intensity prediction, thanks to their ability to exploit temporal and variate dependencies, offering potential for TC disaster preparedness systems.

Accurate prediction of solar irradiation, particularly Diffuse Horizontal Irradiance (DHI), is essential for optimizing solar energy systems. This paper presents a hybrid framework that integrates satellite imagery and satellite-derived data to improve the precision of DHI forecasts. Two key datasets were employed: ground-based Solar Irradiation Measurement (SRM) and satellite-based Solar Irradiation (SSR). The proposed methodology utilizes machine learning models along two paths. The first path processes satellite imagery using advanced techniques, including pixel imputation with a modified Random Forest (RF) and Generative Adversarial Network (GAN), noisy region detection with Self-Organizing Maps (SOM), and noise removal through a Latent Diffusion Model (LDM). The second path handles tabular data through a diffusion probabilistic model designed for missing data imputation. These features are then merged and fed into a Long Short-Term Memory (LSTM) network, enhanced to capture seasonality and trends for accurate DHI predictions. The paper makes significant contributions by introducing a robust hybrid framework that leverages both satellite imagery and tabular data, incorporating novel preprocessing methods such as GAN-based pixel imputation and diffusion-based noise removal. The LSTM model is further adapted to handle seasonal and trend components, resulting in enhanced DHI forecasting accuracy. The proposed model demonstrates superior performance, achieving a Mean Squared Error (MSE) of 8.170 W/m2, Root Mean Squared Error (RMSE) of 1.749 W/m2, Mean Absolute Error (MAE) of 0.693 W/m2, and an R-squared value of 2.574, significantly outperforming conventional methods such as Artificial Neural Networks (ANN), Support Vector Regression (SVR), and traditional LSTM models. Additionally, the model records a low Mean Absolute Percentage Error (MAPE) of 0.8183% and a computation time of 35.4 s, highlighting its efficiency. These results contribute to more accurate and reliable solar energy resource management by offering enhanced DHI forecasts across various spatial and temporal scales.

Wind energy is a promising alternativefor renewable source of energy pursued world-wide to reduce carbon emissions for a green future. The prediction of wind speed is a challenging subject and plays an instrumental role in development of wind power systems (particularly grid connected renewable energy systems where predicting wind speed facilitates manipulation of the load on the grid). Modern machine learning techniques including neural networks have been widely utilized for this purpose. Literature indicates availability of several models for estimation of the wind speed one hour ahead and the hourly wind speed data profile one day ahead. This paper considers the prediction of wind energy as a univariate time series (UVT) prediction problem and employs major prediction algorithms including the K-Nearest Neighbors (kNN), Random Forest (RF), Support Vector Regression (SVR), Holt-Winter and ARIMA method. Forecasting a univariate time series depends only on past wind speed data values, rather than use of external data attributes like wind direction or weather forecast for prediction algorithm. In the present study (as a case-study), 13 years of hourly average wind speed data (of the period 1970-1982) of Yanbu, Saudi Arabia has been utilized to evaluate the performance of selected algorithms. Yanbu is an industrial city that plays a major role in the economy of Saudi Arabia. The findings showed that SVR, RF and ARIMA methods exhibit a better forecastingperformance in relation to four evaluation parameters of Mean Absolute Percentage Error(MAPE),Symmetric Mean Absolute Percentage Error (sMAPE),Mean Absolute Error (MAE) and Mean Absolute Scaled Error (MASE).

The current work aims to develop computational models for the thermal characteristics of turbulent CH4 flames for varying burner dimensions. This study develops a platform for data-driven analysis of temperature prediction of turbulent non-premixed flames, in which the influence of flow and geometric parameters, including burner head diameter (D), half cone angles (α), and co-flow air velocity (Ucf), have been considered. The algorithms used were ridge regressor (RR), linear regressor (LR), and three variations of support vector regression (SVR): SVR with a linear kernel (SVR-LR), SVR with a radial basis function (SVR-RBF), and SVR with a polynomial kernel (SVR-Poly). The performance of each computational model was evaluated and contrasted based on several metrics: mean absolute error, regression coefficient (R2), mean absolute percentage error, and mean Poisson deviance. From the modeling of the output data, it was observed that the SVR-RBF predictions were more accurate compared to those from the other algorithms, as it achieved the highest training value of 0.955. The testing predictions of RR, SVR-LR, SVR-RBF, and SVR-Poly algorithms were also robust, with R2 values ranging between 0.91 and 0.94. It is, therefore, established that these computational models are effectively suited for predicting sensitive turbulent CH4 flame characteristics based on varying input factors.

<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>

. This study introduces support vector regression (SVR) approach to model the relationship between the glass transition temperature (Tg) and multipole moments for polymers. SVR was trained and tested via 60 samples by using two quantum chemical descriptors including the molecular traceless quadrupole moment and the molecular average hexadecapole moment Φ. The prediction performance of SVR was compared with that of reported quantitative structure property relationship (QSPR) model. The results show that the mean absolute error (MAE), mean absolute percentage error (MAPE) and root mean square error (RMSE) of training samples and test samples achieved by SVR model, are smaller than those achieved by the QSPR model, respectively. This investigation reveals that SVR-based modeling is a practically useful tool in prediction of the glass transition temperature of polymers.

Rainfall is the height of rainwater that falls on a flat area, assuming it doesn't evaporate, doesn't seep, and doesn't flow. Rain levels are measured in mm (millimeters). The target of the research being conducted is in Badung Regency, Bali because Bali is a tourist area that is often visited by tourists and from Indonesian itself, so predictions of meteorology, such as rainfall will greatly impact tourism. In this test, predictions use the Long Short Term Memory (LSTM) method, using daily weather data from the BMKG from 2010 to 2020 as training data and daily weather data for 2021 as prediction data. Based on the test results above, the results show that the two LSTM tests with LSTM Model 128.64 and LSTM Model 64.32 have low MAE and MAPE error values. From First Scenario, the Mean Absolute Error (MAE) value is 8.97246598930908 and Mean Absolute Percentage Error (MAPE) value is 1.7657206683278308%. From Second Scenario, the Mean Absolute Error is 9.706669940783014 and Mean Absolute Percentage Error is 1.9028466692362323%. From the MAE and MAPE values obtained in these two scenarios, it can be proven that from the evaluation results of Rainfall predictions in Badung Regency, Bali, the predictions can be said to be very accurate because they have an error value of less than 10.

GIS-based evaluation of landslide susceptibility using hybrid computational intelligence models

Demand forecasting is a critical function in Enterprise Resource Planning (ERP) systems, directly influencing inventory management, production planning, and overall operational efficiency. Traditional statistical models often fall short in handling the complexity and variability of modern supply chains. This study investigates the application of Artificial Intelligence (AI), specifically Machine Learning (ML) algorithms, to enhance demand forecasting accuracy within ERP environments. I conduct a comparative analysis of four widely used ML models: Linear Regression, Random Forest, Support Vector Regression (SVR), and Long Short-Term Memory (LSTM) networks. Using real-world ERP datasets, each model is evaluated based on Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and computational performance. The results reveal that while Random Forest and LSTM models outperform others in terms of accuracy, their complexity and training time vary significantly. My findings highlight the trade-offs between model accuracy and computational efficiency, offering practical insights for ERP stakeholders. This study contributes to the growing field of AI-driven enterprise analytics and provides guidance on selecting appropriate ML techniques tailored to specific forecasting needs within ERP systems.

The growth and sustainability of human development rely on water availability. Proper management of Groundwater as the main source of one-third of freshwater resources is compulsory because of its renewable sources and to safeguard food sanctuary and water security. The steps ahead modeling of GRACE Terrestrial Water Storage (TWS) was employed in this study using the GRACE TWS data from 2007 to 2017 and TWS spherical harmonic solution obtained from the University of Texas (UT) center for space research.  The data was used to create the artificial intelligence-based models viz: Elman neural network (ENN) and Support vector regression (SVR) based on several input variables, including t-12, t-24, t-36, t-48, and TWS as the output variable. The models were evaluated using mean absolute error (MAE), root means square error (RMSE), mean absolute percentage error (MAPE), correlation coefficient (CC), and Nash–Sutcliffe efficiency (NSE). The estimation outcomes depicted that only SVR-M1 (NSE=0.993, MAE0.0346) generated promising results, with ENN-M3 (NSE=0.6586, MAE=0.6895) as the second-best model. All other models’ combinations were within the range of good to marginal accuracies, which are unreliable for decision-making. 

In recent times, gold has been one of the prioritized commodities in terms of long term as well as short term investments since the investors consider gold as a hedgerow against the unforeseen events leading to chaos in the market. Consequentially, the price of gold in the market plays an important role. In this research work, time-series gold price prediction models have been developed using the support vector regression and anfis models for the prediction of daily gold prices. The support vector model was designed using epsilon support vector regression method while the adaptive neural fuzzy inference systems have been developed using grid partition and subtractive clustering methods. The gold prices obtained for the training and testing were obtained from Perth Mint of Australia. The evaluation criteria for the comparison of the models are Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Nash-Sutcliffe model efficiency coefficient (E) and Mean absolute percentage error (MAPE). It was observed that the models obtained using support vector regression outperformed the ANFIS models. In the ANFIS models, it was observed that ANFIS-GP performed slightly better than the ANFIS-SC model.

Tomato is one of the most important vegetables due to its high production and nutritional value. With the development of digital agriculture, the tomato breeding and processing industries have seen a rapid increase in the need for simple, low-labor, and inexpensive methods for analyzing tomato composition. This study proposes a digital method to predict four minerals (calcium, potassium, phosphorus, and magnesium) in beef-type tomato using machine learning models, including k-nearest neighbors (kNN), artificial neural networks (ANNs), and Support Vector Regression (SVR). The models were discriminated using the coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The kNN model showed the best performance for estimation of quantity of calcium, potassium, phosphorus, and magnesium. The results demonstrate that kNN consistently outperforms ANNs and SVR across all target nutrients, achieving the highest R2 and the lowest error metrics (RMSE, MAE, and MAPE). Notably, kNN achieved an exceptional R2 of 0.8723 and a remarkably low MAPE of 3.95% in predicting phosphorus. This study highlights how machine learning can provide a versatile, accurate, and efficient solution for tomato mineral analysis in digital agriculture.

Accurate forecast of carbon dioxide (CO2) emissions plays a significant role in China's carbon peaking and carbon neutrality policies. A novel two-stage forecast procedure based on support vector regression (SVR), random forest (RF), ridge regression (Ridge), and artificial neural network (ANN) is proposed and evaluated by comparing it with the single-stage forecast procedure. Nine independent variables’ data (study period: 1985–2020) are used to forecast the CO2 emissions in China. Our results reveal that, when the time gap, h increases from 1 to 8, the average root mean squared error (RMSE) and mean absolute error (MAE) of SVR–SVR, SVR–RF, SVR–Ridge, and SVR–ANN are almost uniformly lower than errors arising from their single-stage version, respectively. Among these two-stage models, SVR–ANN exhibits the lowest forecast errors, whereas SVR–RF admits the highest. The mean percentage decrease in forecast errors of SVR–SVR vs. SVR, SVR–RF vs. RF, SVR–Ridge vs. Ridge, and SVR–ANN vs. ANN are 36.06, 5.98, 43.05, and 14.81 for RMSE, and 36.06, 6.91, 43.27, and 15.35 for MAE. Our two-stage procedure is also suitable to forecast other variables, such as fossil fuel and renewable energy consumption.