Search

Tool wear prediction is key to ensuring product quality and machining efficiency. However, the prediction results of most models are unstable or inaccurate. To address the issues, a tool wear prediction model, based on support vector regression which was optimized by differential evolution and gray wolf optimization algorithms, was proposed in this paper. The method optimized the parameters of support vector regression model through differential evolution and grey wolf optimization algorithms to make the model more balanced in terms of its global and local search capabilities. First, the vibration and power signals were collected by sensors during the milling processes. Then, the features extraction and features selection were performed on the vibration and power signals. Next, the proposed model was developed and trained. Finally, the tool wear was predicted using the proposed model. The results showed that the proposed model had better performance than other models in terms of prediction accuracy and prediction efficiency, and it was applicable to the condition of multiple cutting parameters with generalizability, which will provide some valuable technical support for machining. [ABSTRACT FROM AUTHOR]

• Consummatory pleasure scores significantly lower in patients with FES. • Wavelet-ALFF indicates widespread abnormal spontaneous activity in FES patients. • Abnormal brain activity in FES patients effectively predicts consummatory pleasure. • Putamen and SOG crucial in predictive modeling of consummatory pleasure in FES. Anhedonia is one of the core features of the negative symptoms of schizophrenia and can be extremely burdensome. Our study applied resting-state functional magnetic resonance imaging (fMRI)-based support vector regression (SVR) to predict anhedonia in patients with first-episode schizophrenia (FES) and analysed the correlation between the wavelet-based amplitude low-frequency fluctuation (wavelet-ALFF) of the main brain region and anhedonia. We recruited 31 patients with FES and 33 healthy controls (HCs) from the Affiliated Brain Hospital of Guangzhou Medical University. All subjects completed the Temporal Experience of Pleasure Scale (TEPS) and received resting-state fMRI (rs-fMRI). We used the wavelet-ALFF method and SVR to analyse the data. Patients with FES had lower consummatory pleasure scores than healthy subjects (t = -2.71, P <0.01). FES displays variable wavelet-ALFF in a wide range of cerebral cortices (P <0.05, GFR corrected). The SVR analysis showed that wavelet-ALFF, based primarily on the right putamen (r = 0.40, P <0.05) and right superior occipital gyrus (r = -0.39, P <0.05), was effective in predicting consummatory pleasure scores with an accuracy of 56.43 %. Our study shows that abnormal spontaneous neural activity in FES may be related to the state of consummatory anhedonia in FES. Wavelet-ALFF changes in the right putamen and superior occipital gyrus may be a biological feature of FES with anhedonia and could serve as a potential biological marker of FES with anhedonia. [ABSTRACT FROM AUTHOR]

In order to better detect and identify the running state of the wind turbine equipment and its generator in the power system wind farm, and then improve the operation reliability of the wind turbine in the power system wind farm, the monitoring method of power system state operation based on Supervisory Control and Data Acquisition (SCADA) model was studied. The SCADA model pre installs different types of sensors on the units of the power system to collect, record and store the power data of the power system. The empirical wavelet transform method is selected to extract the signal characteristics from the state operation signals collected by the SCADA model. ReliefF algorithm is used to select features related to equipment status monitoring from the extracted status operation signal features. Fuzzy C-means clustering algorithm is used to analyze the correlation of feature selection results and identify power system operating conditions. According to the condition identification results of power system, support vector regression prediction algorithm is selected to output the monitoring results of power system state operation. The experimental results show that the monitoring time of the generator and other equipment is less than 100 ms, which provides a strong guarantee for the reliable operation of the power system. This result not only validates the validity of the monitoring and data acquisition model proposed in this paper, but also provides a new idea and method for the intelligent operation and safety management of power system. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is a neurodegenerative disorder that influence brain's neurological, behavioral, and physiological functions and includes motor and nonmotor manifestations. Although there have been several PD diagnosis systems with supervised machine learning techniques, there are more efforts that need to enhance the accurate detection of PD in its early stage. The current paper developed a novel approach by integrating Least Squares Support Vector Regression (LS-SVR) and Fuzzy Clustering for Unified Parkinson's Disease Rating Scale (UPDRS) diagnosis. This paper used feature selection and Principal Component Analysis (PCA) to overcome the multicollinearity issues in data. This paper used a large medical dataset including Motor- and Total-UPDRS to demonstrate how the proposed method can improve prediction performance via extensive evaluations and comparisons with existing methods. Compared to other prediction methods, the experimental results demonstrate that the proposed method provided the best accuracy for Total-UPDRS (Root Mean Squared Error = 0.7348; R 2 = 0.9169) and Motor-UPDRS (Root Mean Squared Error = 0.8321; R 2 = 0.8756) predictions. [ABSTRACT FROM AUTHOR]

The neurophysiological mechanisms underlying generalized anxiety disorder (GAD) with or without depressive symptoms are obscure. This study aimed to uncover them and assess their predictive value for treatment response. We enrolled 98 GAD patients [58 (age: 33.22 ± 10.23 years old, males/females: 25/33) with and 40 (age: 33.65 ± 10.49 years old, males/females: 14/26) without depressive symptoms] and 54 healthy controls (HCs, age: 32.28 ± 10.56 years old, males/females: 21/33). Patients underwent clinical assessments and resting-state functional MRI (rs-fMRI) at baseline and after 4-week treatment with paroxetine, while HCs underwent rs-fMRI at baseline only. Regional homogeneity (ReHo) was employed to measure intrinsic brain activity. We compared ReHo in patients to HCs and examined changes in ReHo within the patient groups after treatment. Support vector regression (SVR) analyses were conducted separately for each patient group to predict the patients' treatment response. Both patient groups exhibited higher ReHo in the middle/superior frontal gyrus decreased ReHo in different brain regions compared to HCs. Furthermore, differences in ReHo were detected between the two patient groups. After treatment, the patient groups displayed distinct ReHo change patterns. By utilizing SVR based on baseline abnormal ReHo, we effectively predicted treatment response of patients (p -value for correlation < 0.05). The dropout rate was relatively high. This study identified shared and unique neural substrates in GAD patients with or without depressive symptoms, potentially serving as biomarkers for treatment response prediction. Comorbid depressive symptoms were associated with differences in disease manifestation and treatment response compared to pure GAD cases. • Existing shared neural substrates of GAD with or without depressive symptoms • Existing distinctive neural substrates of GAD with or without depressive symptoms • Comorbidity with depressive symptoms affects the neuroplasticity of GAD patients • Shared and distinctive neural substrates may assist in predicting prognosis of GAD [ABSTRACT FROM AUTHOR]

Proteolysis is a complex biochemical event during cheese storage that affects both functionality and quality, yet there are few tools that can accurately predict proteolysis for Mozzarella and Cheddar cheese across a range of parameters and storage conditions. Machine learning models were developed with input features from the literature. A gradient boosting method outperformed random forest and support vector regression methods in predicting proteolysis for both Mozzarella (R2 = 92%) and Cheddar (R2 = 97%) cheese. Storage time was the most important input feature for both cheese types, followed by coagulating enzyme concentration and calcium content for Mozzarella cheese and fat or moisture content for Cheddar cheese. The ability to predict proteolysis could be useful for manufacturers, assisting in inventory management to ensure optimum Mozzarella functionality and Cheddar with a desired taste, flavor and texture; this approach may also be extended to other types of cheese. [ABSTRACT FROM AUTHOR]

Selecting appropriate input variables for developing a rainfall prediction model is significantly difficult. The present study proposed an innovative framework for input variable selection (IVS) model bootstrapped long short-term recurrent neural network (BTSP-LSTM-RNN) to identify relevant variables for monthly rainfall forecasting. Monthly meteorological and large-scale climatic variables (LCVs) from 1993 to 2022 at two selected river basins in the northern region of Thailand were used for model development. The proposed BTSP-LSTM-RNN model results were compared with the support vector regression with recursive feature elimination (SVR-RFE) and Gradient boosting (GB) by statistical metrics such as coefficient of determination (R2), mean absolute error (MAE), relative root mean squared error (RRMSE), Pearson's correlation coefficient (r) and mean absolute percentage error (MAPE). BTSP-LSTM-RNN demonstrated exceptional performance, boasting a higher R2 (0.84), MAE (92.28), RRMSE (10.36) in the Wang basin, and R2 (0.83), MAE (242.60), RRMSE (9.93) in the Nan basin. BTSP-LSTM-RNN also achieved the lowest MAPE of 29.82%. Based on this IVS model results, two input variable combinations (IVCs) were designed. IVC-1 is based on BTSP-LSTM-RNN selection, and IVC-2 is an original set of variables. LSTM-RNN, multi-layer perceptron artificial neural network (MLP-ANN), and ensemble model with bootstrapping on random forest (RF) were employed for monthly prediction. When BTSP-LSTM-RNN's selected input variables from IVC-1 are utilized, the BSTP-RF model demonstrates robust performance. It achieves a high R2 (0.82), a low RRMSE (10.13%) suggests accurate predictions, and the r of 0.91 further supports the model's strong linear relationship with observed rainfall data. Based on prediction model results, the BTSP-LSTM-RNN (IVS) model plays a pivotal role in the selection of input variables for rainfall forecasting and its impact on the performance of prediction models (BSTP-RF, MLP-ANN, and LSTM-RNN). These results consistently underscored the pivotal role of the BTSP-LSTM-RNN IVS model in enhancing the precision and reliability of rainfall predictions. [ABSTRACT FROM AUTHOR]

While academic metrics such as transcripts and GPA are commonly used to evaluate students' knowledge acquisition, there are limited comprehensive metrics to measure their preparedness for the challenges of post-graduation life. This research paper explores the impact of various factors on university students' readiness for change and transition, with a focus on their preparedness for careers. The methodology employed in this study involves designing a survey based on Paul J. Mayer's "The Balance Wheel" to capture students' sentiments on various life aspects, including satisfaction with the educational process and expectations of salary. The collected data from a KBTU student survey (n=47) were processed through machine learning models: Linear Regression, Support Vector Regression (SVR), and Random Forest Regression. Subsequently, an intelligent system was built using these models and fuzzy sets. The system is capable of evaluating graduates' readiness for their future careers and demonstrates a high predictive power. The findings of this research have practical implications for educational institutions. Such an intelligent system can serve as a valuable tool for universities to assess and enhance students' preparedness for post-graduation challenges. By recognizing the factors contributing to students' readiness for change, universities can refine curricula and processes to better prepare students for their career journeys. [ABSTRACT FROM AUTHOR]

[Display omitted] • Support vector regression is used to predict tunnel-induced strata displacement. • Heuristic algorithms are applied to determine SVR hyperparameters. • Accuracy, stability and efficiency are used to evaluate the applicable algorithms. Machine learning method with heuristic optimization algorithms is proposed to predict the stratum displacement induced by earth pressure balanced shield tunneling. Support vector regression is used as the machine learning method. Four heuristic intelligent optimization algorithms, namely, genetic algorithm, particle swarm optimization, grey wolf optimizer and sparrow search algorithm, are applied to optimize the two hyperparameters of support vector regression model, namely, penalty factor and bandwidth term. Simulated annealing algorithm is introduced to show the necessity of using heuristic algorithms. Mean square error of k -fold cross validation is considered as the fitness function for optimization algorithms. Normalization method and dummy variables are used for data preprocessing. For 115 samples from field measurement, 92 samples are used as the training set, and 23 samples are used as the test set. Three categories of parameters, namely, shield tunneling parameters, tunnel geometrical parameters and stratum types, are used as input parameters for the proposed method. Correlations among parameters are analyzed by Pearson correlation coefficient. The prediction results show that grey wolf optimizer and sparrow search algorithm are suitable methods for determining hyperparameters of support vector regression due to higher accuracy, efficiency, and stability. [ABSTRACT FROM AUTHOR]

• COVID-19 undermines progress toward SDG number 3 of good health and well-being. • The COVID-19 pandemic has hard hit the SADC region and Zimbabwe has not been left out. • Statistical forecasting models play a vital role in predicting future pandemic and threats. • Support vector regression with pairwise interactions provides robust forecasts. • The can assist decision-makers in planning adequate policies. This study aims to show that including pairwise hierarchical interactions of covariates and combining forecasts from individual models improves prediction accuracy. The least absolute shrinkage and selection operator via hierarchical pairwise interaction is used in selecting variables that are not correlated and with the greatest predictive power in single forecast models (Gradient boosting method [GBM], Generalized additive models [GAMs], Support vector regression [SVR]) are used in the analysis. The best model was selected based on the mean absolute error (MAE), the best key performance indicator for skewed data. Forecasts from the 5 models were combined using linear quantile regression averaging (LQRA). Box and Whiskers plots are used to diagnose the overall performance of fitted models. Single forecast models (GBM, GAMs, and SVRs) show that including pairwise interactions improves forecast accuracy. The SVR model with interactions based on the radial basis kernel function is the best from single forecast models with the lowest MAE. Combining point forecasts from all the single forecast models using the LQRA approach further reduces the MAE. However, based on the Box and Whiskers plot, the SVR model with pairwise interactions has the smallest range. Based on the key performance indicators, combining predictions from several individual models improves forecast accuracy. However, overall, the SVM with pairwise hierarchical interactions outperforms all the other models [ABSTRACT FROM AUTHOR]

• ANNMLP provides the highest accuracy in predicting heat transfer coefficient. • SVR has the highest generalization capability to predict heat transfer coefficient. • XGBoost shows the highest accuracy and generalization capability for pressure drop. • Significant features for heat transfer coefficient: mass velocity and vapor quality. • Significant features for pressure drop: inclination angle and mass velocity. Machine learning techniques have great potential to predict two-phase flow characteristics instead of classic empirical correlations. In the present study, four different machine learning models, including multi-layer perceptron artificial neural network (ANNMLP), support vector regression (SVR), K nearest neighbors (KNN), and extreme gradient boosting (XGBoost), are employed to predict the heat transfer coefficient (HTC) and the frictional pressure drop (FPD) of R134a and R1234yf condensation flow in horizontal and inclined tubes. The dataset includes 348 points from previous works and the current research. To extend the data, an experimental study is also performed on the condensation of R134a in a horizontal tube for different mass velocities and vapor qualities. The results show that, in the best model, HTC can be estimated by ANNMLP with the mean absolute percentage error (MAPE) of 7.01%. The best prediction of FPD is achieved using XGBoost machine with MAPE of 10.87% on test data. Also, the feature importance procedure is implemented to recognize the most useful features. Based on the results, the mass velocity and the inclination angle are identified as the most influencing parameters on the prediction of HTC and FPD, respectively. [ABSTRACT FROM AUTHOR]

Solar Chimney Power Plant (SCPP) is a renewable energy system that indirectly converts solar energy to electricity. However, the efficiency of SCPP is not sufficient for practical applications. Integrating SCPPs with Photovoltaic-Thermal systems (PVT) could enhance their performance to levels acceptable for industrial adoption. This study investigates the combined SCPP-PVT performance for the weather conditions of Austin (Texas), San Diego (California), and Phoenix (Arizona), all on a similar latitude. Various configurations of this combined system are numerically simulated, and their efficiencies are compared with a conventional SCPP, SCPP-Photovoltaic (PV), and stand-alone PV modules. Moreover, to predict and optimize the performance of these systems, the Support Vector Regression with Linear (LSVR), Polynomial (PSVR), Gaussian (GSVR), and Hybrid (HSVR) kernels are implemented. In order to optimize the hyperparameters of the Machine Learning (ML) models, the Grey Wolf Optimizer (GWO) is implemented. Also, the optimum performance of the SCPP-PVT system is obtained using the Multi-objective Grasshopper Optimization Algorithm (MOGOA). The results show that the HSVR ML model has the highest accuracy, followed by PSVR, GSVR, and LSVR models. It is shown that the SCPP-PVT system outperforms both SCPP-PV and stand-alone PV modules, respectively. Finally, the SCPP-PVT is shown to outperform the PV modulus by up to 4.8%. [Display omitted] [ABSTRACT FROM AUTHOR]

The In this Internet Era, most of the people are using world-wide-web (www. based websites extensively for accomplishing their daily activities including E-commerce. As per latest report, total of 1.5 billion URLs are accessed every day and it is increasing every second. From another perspective, malicious URLs are employed in URL phishing- which in turn steal customer credentials and thereby lead to loss of billions of dollars. Due to these aspects, malevolent URL detection is gaining huge attention in the literature in the past few years. However, the state-of-the art literature employ only popular ML techniques and small datasets with less diversity for detecting malicious URLs. Further, the existing malicious URL detection methods are less focusing on bottleneck issues such as Overfitting and hyper-parameter tuning of ML models, which play a significant role in deciding the prediction accuracy of the proposed detection framework. In order to tackle these issues, this research article proposes a robust Malevolent URL Detection framework, which utilizes a hybrid machine learning algorithm, Support Vector Regression (SVR) and hyper parameters tuning strategies to enhance the prediction accuracy. The experimental results conducted on training and testing datasets clearly demonstrate the performance of the proposed detection framework in terms of PR and accuracy metrics respectively. [ABSTRACT FROM AUTHOR]

This study demonstrated the application of a hybrid Bayesian algorithm (BA) and support vector regression (SVR) as a potential super-learner tool (BA-SVR) to predict biohydrogen production from food waste-originated feedstocks. The novelty of the present approach, as compared to the existing response surface methodology (RSM), includes (i) hybridization of BA with SVR for modeling of biohydrogen production and minimization of biomethane formation, (ii) performance evaluation and comparison of the developed BA-SVR models with the existing RSM models based on the several indicators such as coefficient of determination (R2), relative error (RE), mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE), (iii) analysis of the robustness of the model and (iv) testing generalization ability. The calculated values of these indicators suggested that the proposed super leaner models demonstrated better performance predicting the biohydrogen and biomethane (products) responses than those using the existing RSM models - as reported in Rafieenia et al. 2019 [45]. The estimated low errors for biohydrogen: MAE = 0.5919, RMSE = 0.592, MAPE = 11.1387; for biomethane: MAE = 0.2681, RMSE = 0.2688, MAPE = 0.3708 , signifie the reliable model predictions. The BA-SVR model also provided high adj R2 (>0.99 for both biohydrogen and biomethane), indicating an excellent fitting of the model. Concerning the MAPE, the proposed BA-SVR models for both the biohydrogen and biomethane responses showed superior performances (as compared to the RSM models) with a performance enhancement of 64.16% and 98.81%, respectively. • Biohydrogen has emerged as a green energy source due to its non-polluting nature. • An AI approach was applied to model and predict of biohydrogen production. • Model predicted values are compared with the experiments successfully. • The studied super learner models can reduce number of lab trials and saving resources. [ABSTRACT FROM AUTHOR]

• Machine learning models to predict daily ZTD value. • Increasing the data quality of ZTD products in the reference stations. • Using of support vector regression to predict the tropospheric delay. • Performance comparison of IGS-ZTD product, VMF1 and RBF-SVR models. Modelling of tropospheric delay has a crucial place in the Global Navigation Satellite System (GNSS) as well as atmospheric and space research. Until now, many different modelling put forward and are still being developed to predict tropospheric delay. Developments in Machine Learning (ML) provide alternative approaches to the predictions of Zenith Tropospheric Delay (ZTD) in GNSS observations and allow an increase in the efficiency of current models. This study focusses on Support Vector Regression (SVR) modelling for predicting ZTDs over selected NYAL (North Europe), BAIE (North America), GOPE (Central Europe) and NKLG (Central Africa) stations in different regions globally. The datasets for the SVR are meteorological data, station coordinates (φ, λ and h) and the site-wise ZTDs obtained from the VMF1 product for the period 2019–2020. SVR model predictions were realized by using Linear, Polynomial and Radial Basis Function (RBF). Predictive results of SVR models were compared through various performance metrics such as coefficient of determination (R2), Root Mean Squared Error (RMSE), etc. The results from the NYAL station show a good level of prediction capability of the RBF-SVR model with average RMSE and R2 of 17.5 mm and 0.859. This model also presents good predictions at BAIE and GOPE stations with average RMSEs of 20.1 mm and 20.3 mm, and R2 of 0.810 and 0.805 respectively. The station with the lowest model success is NKLG with 24.8 mm average RMSE and 0.698 R2. According to these results, it was obvious that the RBF-SVR model achieved more success in mid-high latitudes and the height differences at the stations do not affect the model. In addition, the RBF-SVR model has obtained close and realistic results that are compatible with the IGS-ZTD product. These conclusions indicated that the ML model is usable as a means of improving the data missing in the current ZTD products and predicting daily tropospheric delay. [ABSTRACT FROM AUTHOR]

The Sejila tunnel, part of the Sichuan-Tibet railway, is in a complex geostress environment because of its deep burial depths and tectonic movement. Based on the measured stress data combined with the structural history and features, the stress characteristics of the Sejila area are preliminarily identified. Then, a three-dimensional numerical model that can provide real topographic features is established, and a distribution law of stress boundary conditions is proposed according to compilations of much measured stress data. By means of support vector regression (SVR), the stress field of the whole Sejila region is determined and finds a reasonable accordance with the measured stress data. Results show that the vertical stress in deep buried stratum can be approximately regarded as one of the principal stresses, and it is reasonable to apply the lateral stress to the model boundary according to a linear function with burial depth. The in situ stress in the tunnel site exhibits that σH > σV > σh, and the σH direction deflects when it encounters faults or strata interfaces; the larger that the intersecting angle between fault strike and σH is, the smaller the deflection. Compared to the entrance, the rear of the tunnel is subjected to a high maximum principal stress with a high angle; moreover, most sections of the tunnel are estimated to suffer from severe rockbursts, except for a range of 5 km away from the tunnel entrance and 2.5 km away from the exit, according to the Russense criterion. This paper can provide the basis for the prediction and prevention of rockbursts in the Sejila tunnel. [ABSTRACT FROM AUTHOR]

[Display omitted] • Maximum removal of Congo Red on black cardamom activated carbon occurs at pH 6. • Langmuir adsorption capacity was found to be 69.93 mg/g. • Uptake of Congo Red follows pseudo-second-order kinetics. • Congo Red adsorption was found to be spontaneous, random, and exothermic. • Predictions of Congo Red adsorption by Machine Learning models were accurate and generalized (R2 > 0.99). The present work utilizes waste black cardamom (BC) as an inexpensive and environmentally friendly adsorbent for sequestering the Congo Red (CR) dye from aqueous media for the first time. Following a carbonization process at 600 °C, chemical activation with KOH was carried out for waste BC and subsequent black cardamom activated carbon (BCAC) was employed as an absorbent for CR eradication. The effect of experimental factors, including pH, adsorption time, dose and CR initial concentration, was investigated. 96.21 % of CR dye removal was achieved at pH 6 for 100 mg/L of CR concentration having 0.1 g dose at 30 °C. Maximum Langmuir adsorption capacity of BCAC was found to be 69.93 mg/g at 30 °C. The kinetic analyses showed that the CR adsorption over BCAC behaved in accordance with a pseudo-second order kinetic model as high R2 values (0.997–1) were obtained. Thermodynamic parameters (ΔH°, ΔS°, and ΔG°) demonstrated that the CR adsorption over BCAC was feasible, spontaneous and exothermic in nature. In addition, the state-of-the-art machine learning (ML) approaches namely, support vector regression (SVR) and artificial neural network (ANN) were employed for modeling the BCAC adsorbent for CR removal. The statistical analysis revealed high prediction performance of SVR model with AARE value of 0.0491 and RMSE value of 0.4635 while the corresponding values for the ANN model were 0.0781 and 0.5395, respectively. Furthermore, the plots between experimental CR data and ML forecasted data were closely matched (R2 > 0.99). Thus, it can be concluded that BC, an agro waste could be utilized for CR removal and that the adoption of ML approaches can benefit users by providing them with a tool to enhance the design and performance of wastewater treatment operations. [ABSTRACT FROM AUTHOR]

In this paper, Long Short-Term Memory (LSTM) was proposed to predict the energy consumption of an institutional building. A novel energy usage prediction method was demonstrated for daily day-ahead energy consumption by using forecasted weather data. It used weather forecasting data from a local meteorological organization, the Malaysian Meteorological Department (MET). The predictive model was trained by considering the dependencies between energy usage and weather data. The performance of the model was compared with Support Vector Regression (SVR) and Gaussian Process Regression (GPR). The experimental results with a dataset obtained from a building in Multimedia University, Malacca Campus from January 2018 to July 2021 outperformed the SVR and GPR. The proposed model achieved the best RMSE scores (561.692–592.319) when compared to SVR (3135.590–3472.765) and GPR (1243.307–1334.919). Through experimentation and research, the dropout method reduced overfitting significantly. Furthermore, feature analysis was done with SHapley Additive exPlanation to identify the most important weather variables. The results showed that temperature, wind speed, rainfall duration and the amount had a positive effect on the model. Thus, the proposed approach could aid in the implementation of energy policies because accurate predictions of energy consumption could serve as system fault detection and diagnosis for buildings. [ABSTRACT FROM AUTHOR]

The risk of thermal runaway in lithium-ion battery (LIB) attracts significant attention from domains of society, industry, and academia. However, the thermal runaway prediction in the framework of system safety requires further efforts. In this paper, we propose a methodology for dynamic risk prediction by integrating fault tree (FT), dynamic Bayesian network (DBN) and support vector regression (SVR). FT graphically describes the logic of mechanism of thermal runaway. DBN allows considering multiple states and uncertain inference for providing quantitative results of the risk evolution. SVR is subsequently utilized for predicting the risk from the DBN estimation. The proposed methodology can be applied for risk early warning of LIB thermal runaway. [ABSTRACT FROM AUTHOR]

• Experimental study on the performance of a centrifugal air compressor in a 100-kW PEM fuel cell system. • Predicting compressor output mass flow and power consumption by machine learning. • RBF kernel function improves the accuracy and generalization ability of the SVR model. • The SVR model optimized by DBO algorithm exhibits a superior prediction performance. The air compressor is a critical component in the cathode circuit of proton exchange membrane (PEM) fuel cell system, and its operating characteristics have a dramatic impact on the durability and performance of fuel cells. This article first analyzes the performance of a centrifugal air compressor in a 100-kW class fuel cell system for vehicle applications based on experimental data. Then, a novel compressor model is constructed to accurately determine the output mass flow rate (MFR) and power consumption of the compressor under different operating conditions using the support vector regression (SVR) technique. To obtain the optimal hyperparameters of the SVR model, two metaheuristic algorithms are introduced for parameter optimization: particle swarm optimization (PSO) and dung beetle optimization (DBO). The results show that the DBO-SVR model proposed in this paper has the optimal overall forecasting performance compared to the SVR model and PSO-SVR model. The R2 of the predicted values of compressor output MFR and power consumption obtained in the training and test phases both exceed 0.999, and the RMSE is less than 1.3 × 10−3 kg/s and 0.15 kW, respectively. This indicates that the DBO-SVR model can serve as an alternative solution to express the complicated nonlinear relations among the output MFR, power consumption and other influencing factors of the compressor system, thus avoiding many time-consuming and costly experiments. Furthermore, the compressor model presented in this work helps to achieve more precise air supply control and net output power optimization for automotive PEM fuel cell system. [ABSTRACT FROM AUTHOR]

• PLNF-DCV method improves airflow regulation in non-fully developed flow conditions. • CFD analysis reveals error sources in conventional pressure loss calculations. • SVR-based model enhances accuracy of pressure loss predictions. • Machine learning predicts optimal damper adjustment angles. This study addresses the challenges of airflow regulation in Demand Controlled Ventilation (DCV) systems under non-fully developed flow conditions by proposing an innovative approach based on pressure loss modeling, termed Pressure Loss Non-Fully Developed Flow Demand Controlled Ventilation (PLNF-DCV). The method integrates Computational Fluid Dynamics (CFD) and machine learning techniques to develop a more accurate and practical approach for pressure loss calculation and airflow regulation in real ventilation systems. Although the Darcy–Weisbach formula is widely used to estimate pressure losses in ventilation systems, its reliance on the assumption of fully developed flow limits its accuracy under real-world conditions. To address this issue, the present study first employs CFD simulations to thoroughly investigate the influence of non-fully developed flow on pressure losses, with particular emphasis on the dynamic variations in the total resistance coefficient of duct elbows at different coupling distances. Subsequently, a nonlinear pressure loss correction model based on Support Vector Regression (SVR) was constructed, successfully capturing the complex characteristics of non-fully developed flow and significantly enhancing the accuracy of pressure loss calculations. Furthermore, a machine learning-based method for predicting damper adjustment angles was proposed, effectively addressing the challenges of multi-variable strong coupling. Experimental results demonstrate that the PLNF-DCV method performs excellently in complex duct network systems, with an average relative error of only 5.033 % between the actual and desired flow rates after adjustment. By merging physical insights with data-driven methods, the approach demonstrates robust adaptability to diverse, complex ventilation systems. [Display omitted] [ABSTRACT FROM AUTHOR]

To enhance the grid capacity for accommodating renewable energy, large coal-fired power units frequently undergo load regulations and even operate at ultra-low loads, inevitably reducing the units' operating efficiency. To improve the thermal economy of turbines under ultra-low loads, it is essential to optimize the initial main steam pressure. Based on the operating data of a power generation unit, a heat rate prediction model is established by using the support vector regression (SVR) algorithm, and the improved sand cat swarm optimization (ISCSO) algorithm is proposed to optimize the hyperparameters of the SVR model. Subsequently, the ISCSO algorithm is employed to search for an optimal solution within the feasible pressure range under low and ultra-low loads, yielding an optimized sliding pressure curve for the steam turbine. Finally, this approach is validated by using a case study. The results indicate that the optimized prediction model demonstrates strong generalization capabilities and accurately predicts the heat rate under low and ultra-low loads. The heat rate after optimization decreases compared to that before optimization, which highlights that the proposed optimization scheme effectively raises the thermal economy of steam turbines operating at ultra-low loads. • Propose an improved sand cat swarm optimization algorithm. • Establish a turbine heat rate prediction model based on ISCSO-SVR. • The present optimization scheme exhibits better generalization and robustness. • Determine the optimal initial main steam pressure for turbines under low and ultra-low loads. [ABSTRACT FROM AUTHOR]

In pursuing accelerated material design, predictive modeling of lattice constants in perovskite materials has become essential for semiconductors, optoelectronics, and thermoelectrics applications. This study introduces machine learning models—Support Vector Regression (SVR), Gaussian Process Regression (GPR), Artificial Neural Networks (ANN), and Ensemble Regression Trees (ERT) trained on a comprehensive dataset incorporating ionic radii, electronegativity, density, and atomic number of perovskite constituents. Each model was optimized via the Bayesian optimization method to enhance accuracy in predicting lattice parameters. Notably, the GPR model achieved the highest precision, with an R2 of 100% in training and 99% in testing, underscoring its capacity to capture intricate structural correlations. Results indicate that machine learning, specifically GPR, can provide an efficient and scalable alternative to traditional experimental methods, positioning these models as invaluable tools for high-throughput screening in material discovery. This approach presents a promising pathway for advancing computational material science, enabling rapid and precise lattice constant predictions to facilitate innovations across diverse technological domains. • Machine learning models accurately predict lattice constants in perovskite materials. • The GPR model achieves the highest predictive precision with 100% R2 in training and 99% in testing. • Bayesian optimization enhances model accuracy by refining critical hyperparameters. • The study provides a scalable, high-throughput solution for rapid material discovery and design. [ABSTRACT FROM AUTHOR]

In subsea environments, sound navigation and ranging (SONAR) images are widely used for exploring and monitoring infrastructures due to their robustness and insensitivity to low-light conditions. However, their quality can degrade during acquisition and transmission, where standard SONAR image processing techniques can hardly produce high-quality outcomes. An effective image quality assessment (IQA) method can assess their usefulness and aid to develop refinement techniques by identifying the degradation issues, ensuring the reliability of SONAR data. Existing methods often fail to account for degradations from noise, distortion, and resolution changes simultaneously. To address this challenge, we propose a new blind quality assessment method that measures the overall quality of SONAR images by quantifying both the perceptual and utility qualities using the micro- and macro-scale texture and contour features derived from the wavelet domain. By combining the local binary pattern (LBP) micro-scale texture features with the proposed histograms of Schmid Gabor-like edge maps as macro-scale features, a support vector regression model is learned to map from these features to subjective quality scores. Extensive experiments have demonstrated the superiority of our method over existing SONAR IQA techniques on distorted and reconstructed super-resolution side-scan, acoustic lens, and forward-looking SONAR images. Specifically, our method achieves Pearson's and Spearman's correlation metrics of 0.8616 and 0.8541, respectively, for distorted SONAR images, demonstrating improvements of 4.69% and 4.8%. For reconstructed super-resolution SONAR images, our method attains correlation metrics of 0.9415 and 0.9408, reflecting improvements of 0.8% and 1.6% over the second-best method, respectively. To facilitate ease of access, a comprehensive list of key abbreviations and their full names is provided in Table A.9 in the Appendix section. The source code of the proposed method will be shared at https://github.com/hfarhaditolie/BSIQA. • Micro-/macro- wavelet-domain texture/gradient features for representing SONAR images. • Gradient-maps based contour descriptors from Schmid Gabor-like filter bank in wavelet. • Optimised predicting SONAR image quality by training various regression models. [ABSTRACT FROM AUTHOR]

Geopolymers are gaining attention as a viable alternative cementitious material in extrusion-based 3D printing aimed at improving the sustainability of the construction sector. In this regard, this study investigates the impact of various printing parameters, including extrusion speed, printing speed, nozzle distance, and nozzle diameter, on the extrusion quality of printable geopolymers, with a focus on controlling filament geometry. Experimental data were analyzed to assess the influence of each parameter, leading to the identification of optimal printing conditions for improved extrusion quality. A stability map was developed to define a "safe" printing zone, minimizing filament instability. Three supervised machine learning models—Random Forest (RF), Support Vector Regression (SVR), and Gradient Boosting Machine (GBM)—were utilized to predict filament width and optimize the process. The models were compared based on performance, with SVR demonstrating the best performance due to the highest R2 score (0.9771) and the lowest RMSE (0.1178) and MAE score (0.0959) on the test set. Consequently, the SVR model was selected for Shapley Additive Explanations (SHAP) analysis. The SHAP results indicated that nozzle diameter had the most significant impact on filament width, followed by extrusion speed and nozzle distance, while printing speed was less influential. The machine learning models demonstrated their potential in predicting filament width and guiding process control for 3D printing applications. • Key parameters for printable geopolymer extrusion quality were systematically evaluated. • A stability map was developed to define a "safe" printing zone for filament control. • Machine learning models were applied to predict filament width with high accuracy. • Nozzle diameter and extrusion speed had the greatest influence on filament geometry. [ABSTRACT FROM AUTHOR]

The utilization of edge devices in fog computing services is increasing every day to achieve effective communication between edge devices as it reduces the latency and processing time. When the number of edge devices increases and operate in various applications, it is seen an increase in malfunctioning of devices due to compromises in security aspects. An increase in the number of un-trustworthy activities leads to loosing of end users to any service provider. So all edge devices must be labeled as trustworthy or not, based on their previous transactions, leading to effective communications. Finding and maintaining the trust score of edge devices is the most pressing concern in the distributed communication environment. Considering all the issues, this paper propose a Machine Learning-based Trust Prediction for Edge Devices in the Blockchain enabled Fog Computing Environment (MLTPED-BFC). The proposed scheme uses an ensemble of Support Vector Regression (SVR) and Multivariable Logistic Regression (MLR) for predicting the trust score of each edge device and updates it after every successful communication. The prediction and updating of the trust score is carried out by the fog server without any biasing. This Artificial Intelligence driven approach enhances communication effectiveness and security by classifying devices as trustworthy or not, improving the overall reliability of the distributed system. The proposed scheme is proved to be secured based on informal security analysis. Extensive simulations are carried out to validate the proposed scheme's effectiveness and compare it with existing schemes. The proposed MLTPED-BFC mechanism have attained 98.91% of accuracy, 0.0048 loss rate, 98.92% of precision, 98.32% of recall, 98.96% of F-Measure and took 356 s for 100 iterations. [ABSTRACT FROM AUTHOR]

A rapid method was developed for determining the total flavonoid and protein content in Tartary buckwheat by employing near-infrared spectroscopy (NIRS) and various machine learning algorithms, including partial least squares regression (PLSR), support vector regression (SVR), and backpropagation neural network (BPNN). The RAW-SPA-CV-SVR model exhibited superior predictive accuracy for both Tartary and common buckwheat, with a high coefficient of determination (R 2 p = 0.9811) and a root mean squared error of prediction (RMSEP = 0.1071) for flavonoids, outperforming both PLSR and BPNN models. Additionally, the MMN-SPA-PSO-SVR model demonstrated exceptional performance in predicting protein content (R 2 p = 0.9247, RMSEP = 0.3906), enhancing the effectiveness of the MMN preprocessing technique for preserving the original data distribution. These findings indicate that the proposed methodology could efficiently assess buckwheat adulteration analysis. It can also provide new insights for the development of a promising method for quantifying food adulteration and controlling food quality. • The RAW-SPA-CV-SVR model showed superior predictive accuracy for Tartary buckwheat adulteration. • The MMN-SPA-PSO-SVR model demonstrated exceptional performance in predicting protein content. • SVR algorithm consistently outperformed PLSR and BPNN models in terms of overall performance. • The MMN preprocessing technique was effective in preserving the original data distribution. [ABSTRACT FROM AUTHOR]

In high dimensional statistical learning, variable selection and handling highly correlated phenomena are two crucial topics. Elastic-net regularization can automatically perform variable selection and tends to either simultaneously select or remove highly correlated variables. Consequently, it has been widely applied in machine learning. In this paper, we incorporate elastic-net regularization into the support vector regression model, introducing the Elastic-net Support Vector Regression (En-SVR) model. Due to the inclusion of elastic-net regularization, the En-SVR model possesses the capability of variable selection, addressing high dimensional and highly correlated statistical learning problems. However, the optimization problem for the En-SVR model is rather complex, and common methods for solving the En-SVR model are challenging. Nevertheless, we observe that the optimization problem for the En-SVR model can be reformulated as a convex optimization problem where the objective function is separable into multiple blocks and connected by an inequality constraint. Therefore, we employ a novel and efficient Alternating Direction Method of Multipliers (ADMM) algorithm to solve the En-SVR model, and provide a complexity analysis as well as convergence analysis for the algorithm. Furthermore, extensive numerical experiments validate the outstanding performance of the En-SVR model in high dimensional statistical learning and the efficiency of this novel ADMM algorithm. [ABSTRACT FROM AUTHOR]

Under the premise of ensuring the stable operation of solar coupled ground source heat pump systems (SGSHPs), optimizing the configuration to improve the thermal performance of the system and reduce the cost of the system area key measures to promote the popularization of such systems in cold regions. The SGSHPs models of three different operation modes are established in this paper, taking office buildings in the Shenyang area as an example and basing on the TRNSYS platform. The ground temperature imbalance rate and the total energy consumption of the system after thirty years of operation in different modes are compared and analyzed. The parallel transition season thermal storage mode with better energy saving potential is selected as the main research object, and six main design parameters are determined through sensitivity analysis, which are the number of buried pipe boreholes, solar collector area, thermal storage start temperature difference, thermal storage stop temperature difference, collector start temperature difference, and collector stop temperature difference. The 1000 groups of systems with different parameter combinations are simulated, and 1000 sample data are generated as a database.The multiple outputs support vector regression (MSVR) network was trained and validated using the sample database, and the particle swarm optimization (PSO) algorithm was used to optimize the hyper-parameters in the MSVR network, and the trained PSO-MSVR network could correlate the design variable parameters and performance parameters of SGSHPs. Finally, a multi-objective optimization model of the SGSHPs was established using a genetic algorithm, and the Pareto solution set for the optimization of the system configuration was obtained with the objectives of thermodynamic performance and economy of the system, and the optimal solution was obtained by using technique for order preference by similarity to ideal solution (TOPSIS) decision-making. Compared with the pre-optimization design of the heat balance method, the annual cost (AC) is reduced by 17.733 %, and the system COP (COP sys) and winter solar direct supply ratio (f solar) are improved by 29.174 % and 163.78 %, respectively. The data-driven optimization method proposed in this paper has a significant advantage in obtaining the optimized configuration parameters of the SGSHPs system with multi-objective optimization. • The performance of SGSHPs operating under three different modes was compared. • The key parameters that affect system performance have been identified. • The PSO-MSVR network has been trained for predicting the performance of SGSHPs. • Through multi-objective optimization, the AC of the system has been reduced while improving both the COP sys and f solar. [ABSTRACT FROM AUTHOR]

The study aimed to establish safe storage guidelines for long-term preservation of finger millet grains and to develop a model for predicting the allowable storage time. The experiment was conducted at various temperature (15, 25, 35 and 45 °C) and moisture contents (8, 11, 14, 17 and 20% wb). Changes in response variables such as germination, free fatty acid and mold growth were systematically monitored. Finger millet with a moisture content above 14% should be dried to safe moisture levels within 3–5 weeks at 30 °C or within 5–10 weeks at 15 °C to preserve grain quality. To maintain high quality and seed viability of finger millet, moisture content and storage temperature should be below 12% and 20 °C, respectively for up to 34 weeks. The study also assessed the use of artificial neural network and support vector regression models in predicting the safe storage period for finger millet grains. • Safe storage guidelines for finger millet grains were developed. • Insights on the quality changes occurring during the storage of finger millet. • Temperature and moisture content are the critical parameters in grain storage. • ANN & SVR models for predicting the allowable storage time of finger millet. • BRNN model demonstrated high predictability with high R2 value and low MSE. [ABSTRACT FROM AUTHOR]

• A multi-modal matching framework with high adaptability and robustness. • Sketch feature enhancement boosts correct matching rate. • A novel regression strategy reduces manual tuning. • An open-source dataset with 1055 image pairs and 10,599 check points. The generalizability and adaptiveness of multi-modal image matching (MMIM) techniques are hampered by the nonlinear radiometric differences that vary in a highly non-uniform manner across different modal combinations. A major challenge is the extensive filter tuning required by many filter-based matching methods to mitigate the impact of radiometric aberrations. Additionally, the low correct matching rate resulting from the non-repeatability and low similarity of local or detailed features presents another significant obstacle. In this paper, we introduce a novel MMIM framework, called Adaptive Matching with enhanced Edge Sketches (AMES), for reducing manual interference in filter parameter configuration and improving the correct matching rate of extracted feature points. Specifically, AMES trains a support vector regression model to adaptively predict the optimized filtering parameters for each test image using its internal statistical factors as input. We also propose a sketch feature enhancement method, based on fusing multi-scale moment maps through principal component analysis, for cross-modal adaptive feature point extraction. We generate matching results by applying feature descriptors within the Log-Polar window and performing outlier removal following a coarse-to-fine strategy. In an evaluation involving four datasets comprising 1055 image pairs with 26 different cross-modal combinations, the assessment of 10,599 manually measured checkpoints demonstrates that AMES surpasses the state-of-the-art in terms of success rate, correct matching rate, point coverage, average matching accuracy, and spatial distribution uniformity. Our source code and multi-modal image datasets are publicly available at https://dpcv.whu.edu.cn/zm1/gksjj.htm. [ABSTRACT FROM AUTHOR]