Gaussian Process Machine Learning Research Articles

Investigation of the Gaussian Process with Various Kernel Functions for the Prediction of the Compressive Strength of Concrete

The Compressive Strength of Concrete (CSC) is a critical parameter for evaluating the quality of concrete used in various construction projects, including buildings, bridges, and roads. The primary objective of this study is to examine the efficacy of a Gaussian Process (GP) Machine Learning (ML) model employing two kernel functions: Radial Basis Function (RBF) and Polynomial (POL), for predicting the CSC, considering readily quantifiable parameters. Based on these kernel functions, two models were created for this prediction, GP-RBF and GP-POL. The modeling process employed a total of 369 concrete sample data, including compressive strength values and eleven other physico-mechanical properties, collected from the Cua Luc bridge project in Vietnam. This dataset was partitioned into a training set (70%) and a testing set (30%) for model training and validation. Various validation metrics, including R2, Root Mean Square Error (RMSE), and Mean Absolute Error (MAE), were used to evaluate and compare the models. The findings of this study demonstrated that both models GP-RBF and GP-POL exhibited strong performance in predicting CSC, with GP-POL demonstrating marginal superiority over GP-RBF. Consequently, it can be concluded that POL is more efficacious than RBF in training the GP model for CSC prediction.

Physical Education Teaching Quality Assessment Model Based on Gaussian Process Machine Learning Algorithm

Physical education is an integral component of academic curricula focused on promoting overall health and well-being through physical activity and exercise. It encompasses a range of activities designed to enhance students' physical fitness, motor skills, and knowledge of healthy lifestyle habits. In addition to fostering physical development, physical education contributes to the development of social skills, teamwork, and discipline. Students engage in various sports, fitness routines, and educational modules that encourage a lifelong commitment to an active and healthy lifestyle. This demand for improvement in the teaching quality assessment of physical education among the students. Hence, this paper proposed a novel Gaussian Hidden Chain Probabilistic Machine Learning (GHCP-ML). The proposed GHCP-ML model estimates the features for the teaching quality assessment using the Gaussian Hidden Chain model. With the proposed GHCP-ML model features related to the teaching assessment of the physical education are computed. The proposed GHCP-ML model uses the machine learning model for the assessment and computation of the factors related to the teaching quality of students in physical education. With the Gaussian Chain model, the factors related to physical education are evaluated for the classification of the relationship between physical education and teaching quality assessment. Simulation analysis demonstrated that with the proposed GHCP-ML model physical education is improved significantly with teaching quality by ~12% than the conventional techniques. The student physical education performance is improved by more than 80% with the proposed GHCP-ML model compared with the conventional techniques.

Identification of Prolactinoma in Pituitary Neuroendocrine Tumors Using Radiomics Analysis Based on Multiparameter MRI.

This study aims to investigate the feasibility of preoperatively predicting histological subtypes of pituitary neuroendocrine tumors (PitNETs) using machine learning and radiomics based on multiparameter MRI. Patients with PitNETs from January 2016 to May 2022 were retrospectively enrolled from four medical centers. A cfVB-Net network was used to automatically segment PitNET multiparameter MRI. Radiomics features were extracted from the MRI, and the radiomics score (Radscore) of each patient was calculated. To predict histological subtypes, the Gaussian process (GP) machine learning classifier based on radiomics features was performed. Multi-classification (six-class histological subtype) and binary classification (PRL vs. non-PRL) GP model was constructed. Then, a clinical-radiomics nomogram combining clinical factors and Radscores was constructed using the multivariate logistic regression analysis. The performance of the models was evaluated using receiver operating characteristic (ROC) curves. The PitNET auto-segmentation model eventually achieved the mean Dice similarity coefficient of 0.888 in 1206 patients (mean age 49.3 ± SD years, 52% female). In the multi-classification model, the GP of T2WI got the best area under the ROC curve (AUC), with 0.791, 0.801, and 0.711 in the training, validation, and external testing set, respectively. In the binary classification model, the GP of T2WI combined with CE T1WI demonstrated good performance, with AUC of 0.936, 0.882, and 0.791 in training, validation, and external testing sets, respectively. In the clinical-radiomics nomogram, Radscores and Hardy'grade were identified as predictors for PRL expression. Machine learning and radiomics analysis based on multiparameter MRI exhibited high efficiency and clinical application value in predicting the PitNET histological subtypes.

Measuring wake deflection from SCADA data during wake steering using machine learning

As wake steering is implemented on large wind plants, methods for evaluating how well these systems optimize plant performance are needed. The data analysis from experiments conducted so far generally focuses on evaluating the improvement in power or energy production of the plant and comparing that to the predicted improvement. In this study, we explore a new approach to provide additional insight and validation of optimization tools by measuring the wake deflection experimentally using only the downstream turbine as a sensor. This approach is demonstrated using the SMARTEOLE wind plant wake steering experimental data. Light gradient boosting machines (LGBM) and Gaussian process (GP) machine learning models are trained and then interrogated by making a set of predictions under defined conditions to determine the wake deflection observed at the downstream turbine. The data set is sparse, particularly for larger yaw angles, and noisy due to factors not captured in the SCADA leading to relatively high uncertainty in the predictions. The GP model is better suited to smoothly fit this data. Using the GP model, a wake deflection of 0.35 rotor diameters at 3.7 rotor diameters downwind is estimated for a yaw error of 20 degrees on the upwind turbine.

Reservoir porosity assessment and anomaly identification from seismic attributes using Gaussian process machine learning

AbstractPorosity, as one of the reservoir properties, is an important parameter to numerous studies, i.e., the reservoir’s oil/gas volume estimation or even the storage capacity measurement in the Carbon Capture Storage (CCS) project. However, an approach to estimate porosity using elastic property from the inversion propagates its error, affecting the result’s accuracy. On the other hand, direct estimation from seismic data is another approach to estimating porosity, but it poses a high non-linear problem. Thus, we propose the non-parametric machine learning approach, Gaussian Process (GP), which draws distribution over the function to solve the high non-linear problem between seismic data with porosity and quantify the prediction uncertainty simultaneously. With the help of Random Forest (RF) as the feature selection method, the GP predictions show excellent results in the blind test, a well that is completely removed from the training data, and comparison with other machine learning models. The uncertainty, standard deviation from GP prediction, can act as a quantitative evaluation of the prediction result. Moreover, we generate a new attribute based on the quartile of the standard deviation to delineate the anomaly zones. High anomaly zones are highlighted and associated with high porosity from GP and low inverted P-impedance from inversion results. Thus, applying the GP using seismic data shows its potential to characterize the reservoir property spatially, and the uncertainty offers insights into quantitative and qualitative evaluation for hydrocarbon exploration and development.

Machine learning models for predicting the performance of solar-geothermal desalination in different meteorological conditions

This research aimed to evaluate the amount of produced fresh water (FWP) in a desalination system based on humidification-dehumidification using TRNSYS software. The study was conducted for one year, analyzing the results for five cities in Iran with different climatic conditions. Meteorological data from Meteonorm software were used for the simulation. Different heating sources, including solar energy (SE) and geothermal energy (GE), were considered in the design. The impact of using three types of collectors and the simultaneous use of SE and GE heating sources was investigated. The findings showed that using a flat plate solar collector resulted in the highest FWP in June and July, as well as during certain day time hours with increased solar radiation intensity. Increasing the number of flat plate collectors and their cross-sectional area intensified the FWP about 10.60%–33.16%. When SE and GE were used as heat sources, increasing the mass flow rate of water and air entering the system led to a decrease and increase in FWP, respectively. The highest FWP for Hamedan city was achieved when using GE simultaneously with a compound parabolic collector. Exergy destruction was analyzed for humidification and dehumidification devices, with the maximum observed in the case of Type74. The LSTM deep learning neural network and the Gaussian process (GP) machine learning algorithm were used to approximate the desalination efficiency, with the GP method exhibiting slightly higher accuracy.

Prediction of dislocation - grain boundary interactions in FCC aluminum bicrystals using a modified continuum criterion and machine learning methods

Mechanical properties of metals such as strength and toughness are strongly correlated to complex interactions between various defects in the crystalline structure. While elementary interactions between these defects have been investigated using recent micro- and nano-characterization techniques, understanding of the detailed interaction mechanisms has hardly been obtained. To understand defect-driven plasticity at various time and length scales, it is necessary to formulate a general guideline to predict both the interaction type (transmission or reflection) and the dislocation's subsequent slip system after the interaction. Many criteria based on the geometric alignment of the defects have been developed to predict this phenomenon, but these have yet to be found to be accurate when applied to general data sets of grain boundaries (GBs). With this motivation, we conduct a systematic study using molecular dynamics (MD) models of bicrystals to analyze defect interaction process between a prismatic dislocation loop and eleven different grain boundaries of the following character: three tilt, three twist, and five mixed. Based on the MD observations, two new prediction methods are developed: the first is a new data-driven parametric score function based on the classical geometric criteria, and the second is by applying Gaussian process machine learning methods to find the probability distribution of a hidden function. The proposed data-driven prediction methods could pave a new way to predict the unit interaction of dislocations with various GBs, which could show much higher accuracy compared to pre-existing geometric criteria.

Intelligent Tracking Error Prediction and Feedforward Compensation for Nanopositioning Stages With High-Bandwidth Control

In this paper, an intelligent feedforward prediction and compensation scheme to combine with a dual-loop high-bandwidth controller is proposed for high-speed and high-precision tracking control of a nanopositioning stage. Firstly, the dual-loop controller (DLC) consisting of an inner-loop damping and an outer-loop tracking controller is developed with all the parameters optimized simultaneously, which could provide a control bandwidth over the first resonant frequency of the stage. Next, the Gaussian process (GP) machine learning model is employed to capture the dynamic characteristics of the tracking error of the dual-loop controlled plant. Then, a feedforward compensator is constructed to add a compensation term to the initial reference trajectory. Experimental investigations on a self-made piezoelectric-actuated stage validate the effectiveness of the intelligent tracking error prediction method and the excellent performance of the control strategy for high-precision tracking of high-frequency reference trajectories.

Position-based impedance torque control for automatic clutch with robust predefined-time stability guarantee

Accurate clutch torque control is essential in improving vehicle comfort, drivability, and fuel economy. In this article, for automatic clutch system with electro-hydraulic clutch actuator, a clutch torque control strategy with a robust predefined-time stability guarantee based on position closed-loop impedance control is proposed and evaluated. For this purpose, a general second order model of electro-hydraulic clutch actuator with a disturbance term is established. Based on this model, a reference position compensator based on force control in the outer loop and a predefined-time backstepping position controller in the inner loop are developed. In addition, to obtain the release load of the release bearing, a virtual sensor is designed, composed of an online adaptive sliding mode disturbance observer with predefined-time stability and an offline Gaussian process model of uncertain disturbance based on the Gaussian process machine learning method. Finally, simulations and experiments are completed to verify the proposed control strategy. The results show that the control strategy can realize the precise clutch torque tracking control and achieve satisfactory performance.

Characterization of breast lesions using multi-parametric diffusion MRI and machine learning

Objective. To investigate quantitative imaging markers based on parameters from two diffusion-weighted imaging (DWI) models, continuous-time random-walk (CTRW) and intravoxel incoherent motion (IVIM) models, for characterizing malignant and benign breast lesions by using a machine learning algorithm. Approach. With IRB approval, 40 women with histologically confirmed breast lesions (16 benign, 24 malignant) underwent DWI with 11 b-values (50 to 3000 s/mm2) at 3T. Three CTRW parameters, D m , α, and β and three IVIM parameters D diff, D perf, and f were estimated from the lesions. A histogram was generated and histogram features of skewness, variance, mean, median, interquartile range; and the value of the 10%, 25% and 75% quantiles were extracted for each parameter from the regions-of-interest. Iterative feature selection was performed using the Boruta algorithm that uses the Benjamin Hochberg False Discover Rate to first determine significant features and then to apply the Bonferroni correction to further control for false positives across multiple comparisons during the iterative procedure. Predictive performance of the significant features was evaluated using Support Vector Machine, Random Forest, Naïve Bayes, Gradient Boosted Classifier (GB), Decision Trees, AdaBoost and Gaussian Process machine learning classifiers. Main Results. The 75% quantile, and median of D m ; 75% quantile of f; mean, median, and skewness of β; kurtosis of D perf; and 75% quantile of D diff were the most significant features. The GB differentiated malignant and benign lesions with an accuracy of 0.833, an area-under-the-curve of 0.942, and an F1 score of 0.87 providing the best statistical performance (p-value < 0.05) compared to the other classifiers. Significance. Our study has demonstrated that GB with a set of histogram features from the CTRW and IVIM model parameters can effectively differentiate malignant and benign breast lesions.

Vehicle stochastic response prediction of sea-crossing railway bridges under correlated wind and wave via machine learning

Offshore railway bridges are exposed to the complex coastal environment, and vehicles could experience significant responses when vehicles cross the sea-crossing bridge. To predict the vehicle response subjected to the stochastic excitations (wind and wave actions), Archimedes copulas are applied to identify the correlation between wind speed and wave height. Based on the Gibbs sampling, an algorithm of Markov Chain Monte Carlo (MCMC), training samples are sampled from the optimal copula model (e.g., Clayton copula) as the input parameters. Taking a representative vehicle-bridge model as the study object, wind tunnel and wave flume scaling tests are performed to obtain the aerodynamic characteristics with the influence of wave surface. The external loads are calculated using the Morison equation and the MacCamy-Fuchs equation. Vehicle indexes as the output parameters are quantified using Support Vector Machine (SVM), Gaussian Process (GP), and Neural Network (NN) Machine Learning (ML) method. Training and testing results indicate that the NN algorithm outperforms other training strategies even though SVM and GP reasonably predict the vehicle dynamic response. Since the wind and wave action is lateral, vertical acceleration performs insensitivity to input parameters and is mainly influenced by track irregularity.

A Machine Learning Approach for Rate Constants. III. Application to the Cl(2P) + CH4 → CH3 + HCl Reaction.

The temperature dependence of the thermal rate constant for the reaction Cl(3P) + CH4 → HCl + CH3 is calculated using a Gaussian Process machine learning (ML) approach to train on and predict thermal rate constants over a large temperature range. Following procedures developed in two previous reports, we use a training data set of approximately 40 reaction/potential surface combinations, each of which is used to calculate the corresponding database of rate constant at approximately eight temperatures. For the current application, we train on the entire data set and then predict the temperature dependence of the title reaction employing a "split" data set for correction at low and high temperatures to capture both tunneling and recrossing. The results are an improvement on recent RPMD calculations compared to accurate quantum ones, using the same high-level ab initio potential energy surface. Both tunneling at low temperatures and significant recrossing at high temperatures are observed to influence the rate constants. The recrossing effects, which are not described by TST and even sophisticated tunneling corrections, do appear in experiment at temperatures above around 600 K. The ML results describe these effects and in fact merge at 600 K with RPMD results (which can describe recrossing), and both are close to experiment at the highest experimental temperatures. These results are in accord with a recent high-level experiment-theory study of this reaction.

Machine learning-based method to adjust electron anomalous conductivity profile to experimentally measured operating parameters of Hall thruster

The problem of determining the electron anomalous conductivity profile in a Hall thruster, when its operating parameters are known from the experiment, is considered. To solve the problem, we propose varying the parametrically set anomalous conductivity profile until the calculated operating parameters match the experimentally measured ones in the best way. The axial 1D3V hybrid model was used to calculate the operating parameters with parametrically set conductivity. Variation of the conductivity profile was performed using Bayesian optimization with a Gaussian process (machine learning method), which can resolve all local minima, even for noisy functions. The calculated solution corresponding to the measured operating parameters of a Hall thruster in the best way proved to be unique for the studied operating modes of KM-88. The local plasma parameters were calculated and compared to the measured ones for four different operating modes. The results show the qualitative agreement. An agreement between calculated and measured local parameters can be improved with a more accurate model of plasma-wall interaction.

Modeling and Optimizing the Impact of Process and Equipment Parameters in Sputtering Deposition Systems Using a Gaussian Process Machine Learning Framework

We present a method for empirically modeling and optimizing variations in sputtering deposition processes using Gaussian Process (GP) machine learning methods. Our predictive models can be trained with limited training data to enable rapid sputtering process tuning. As a first case, we model the effect of process recipe parameters such as chamber pressure and power on sputtered film thickness uniformity. A second more challenging case is also demonstrated: modeling film thickness spatial uniformity as a function of equipment configuration parameters. The effects of the chamber configuration variables are complex, motivating incorporation of prior process knowledge into the GP framework by utilizing a physics-based solver. Because adjusting equipment configuration parameters and obtaining corresponding wafer fabrication data is costly, a key metric is the expected number of tunes required until process constraints are met. Using past experimental data, we show that tunes using the GP-based predictive model are expected to converge in significantly fewer iterations compared to tunes using polynomial, gradient boosted regression tree, multivariate spline, and deep learning based modeling methods.

Atomistic and machine learning studies of solute segregation in metastable grain boundaries

The interaction of alloying elements with grain boundaries (GBs) influences many phenomena, such as microstructural evolution and transport. While GB solute segregation has been the subject of active research in recent years, most studies focus on ground-state GB structures, i.e., lowest energy GBs. The impact of GB metastability on solute segregation remains poorly understood. Herein, we leverage atomistic simulations to generate metastable structures for a series of [001] and [110] symmetric tilt GBs in a model Al–Mg system and quantify Mg segregation to individual sites within these boundaries. Our results show large variations in the atomic Voronoi volume due to GB metastability, which are found to influence the segregation energy. The atomistic data are then used to train a Gaussian Process machine learning model, which provides a probabilistic description of the GB segregation energy in terms of the local atomic environment. In broad terms, our approach extends existing GB segregation models by accounting for variability due to GB metastability, where the segregation energy is treated as a distribution rather than a single-valued quantity.

Gaussian Process Regression and Machine Learning Methods for Carbon-Based Material Adsorption

Antibiotics have received a lot of attention as promising contaminants because of their ecotoxicological and long-term chemical stability in the atmosphere. Antibiotic adsorption on carbon-based materials (CBMs) such as charcoal and activated carbon has been identified as mainly effective for treating the wastewater strategies. Machine learning (ML) approaches were used to create generalized computation methods for tetracycline (TC) and sulfamethoxazole (SMX) adsorption in CBMs in this investigation. In the existing system, random forest and ANN methods were used for TC and SMX for predicting the quantities of antibiotics in the CBMs. For reducing the antibiotics from the industrial wastewater, the broadcast efforts of the experiments are a little complicated. In the proposed method, Gaussian process regression (GPR), active learning (AL), and ANN are used for predicting the antibiotic levels in the industrial wastewater. Below a variety of environmental parameters (e.g., warmth, solution pH) and adsorbent varieties, the created Ml algorithms outperformed classic isotherm models in conditions of generalisation. To evaluate TC and SMX adsorption on CBMs, we used comparative significance investigation and partial trust plots based on ML models. The proposed GPR reduces the antibiotics in wastewater; minimal experimental screening and the comparative significance and partial trust plot help in the treatment of wastewater.

An English teaching quality evaluation model based on Gaussian process machine learning

AbstractBackgroundThe efficiency of conventional English teaching quality evaluation is comparatively small, and evaluation statistics are challenging. To investigate the use of artificial intelligence (AI) technology in teacher teaching assessment, a machine learning algorithm is proposed to create a teaching evaluation model suitable for the current educational model to assist colleges and universities in overcoming existing teaching challenges.ObjectivesThe proposed Machine learning‐based Gaussian process model (MLGPM) improves the student's language skills. The proposed model uses Gaussian mixed model to express the circulation features of samples and enhances the support vector machine. Therefore, this paper suggests an active learning algorithm that, in association with Gaussian mixed model and sparse Bayesian learning, strategically chooses and labels samples to construct a classifier that syndicates the distribution characteristics of the samples. As a result, the accuracy of a considered quality index for English classrooms is verified, and the quality and control of English as a foreign language can be enhanced.ResultsThe experiment results show that the model presented in this study is effective and beneficial when assessing the efficiency of teaching in universities and analyzing big data sets.ConclusionThe simulation analysis with student performance improvement in English teaching quality using machine learning high fluency rate of 95.3, high accuracy ratio of 98.1%, improve vocabulary prediction ratio of 94.6%, improve passage prediction ratio of 92.7%, enhance learning rate of 95.2%, reduce the error rate of 24.1%, F1‐score of 91.5% and assessment score of 92.1% when compared with other methods.

Optimization and comparison of models for core temperature prediction of mother rabbits using infrared thermography

Core temperature is a measurement used to evaluate and diagnose the health status of mother rabbits. The preferred method is to use an indwelling probe to measure the rectal temperature. This procedure can be stressful to rabbits, are time and labor-consuming. The objective of this paper was to develop the fastest, accurate and non-invasive method to measure the rectal temperature of mother rabbits using Infrared thermography (IRT) and machine learning (ML). Two hundred lactating mother rabbits (LR) and two hundred non-lactating mother rabbits (NLR) of the YPLU breed were used in the experiment and IRT data, rectal temperature and ambient temperature were recorded. The results showed that there was a significant correlation between the maximum infrared temperature of eyes (EMIT) and ears (RMIT) and rectal temperature (p < 0.05) and a significant correlation between the EMIT, RMIT and the ambient temperature (p < 0.01) in two kinds of mother rabbits. Least squares support vector machine (LS-SVM), Gaussian process (GP), and partial least squares (PLS) machine learning methods were used to establish models of mother rabbits’ core temperature. Using the over-sampling method to process the training set, three models of LS-SVM, GP, and PLS with improved generalization performance were obtained. The RMSE for the test set by LS-SVM, GP, and PLS methods were 0.13℃, 0.12℃ and 0.07℃ and the R2 were 0.94, 0.96 and 0.98, respectively. Compared with the results obtained from two other regressions, LS-SVM and GP, the PLS method exhibited the best performance. The prediction error of the test set is <0.2℃, which can better predict the core temperature of the mother rabbits.

Gaussian process machine learning and Kriging for groundwater salinity interpolation

Gaussian processes (GPs) provide statistically optimal predictions in the sense of unbiasedness and maximal precision. Although the modern implementation of GPs as a machine learning technique is more capable and flexible than Kriging, their employment in environmental science is less routine. Their flexibility and capability as a spatial data interpolation technique are demonstrated by applying them to groundwater salinity prediction in a data-sparse region in Australia. By learning from multiple data sources, including AEM and DEM data, GPs have generated groundwater salinity maps with rich local details and quantified uncertainty to support risk-based decision making. The results demonstrate the great worth of nonpoint data with regional spatial coverage to provide more realistic heterogeneity in aquifer properties that are critical for many studies such as contaminant transport. GPs should be further encouraged in groundwater science for data interpolation and prediction, especially when point measurements are sparse and multiple predictors are available.

Machine learning algorithm improves accuracy of ortho-K lens fitting in vision shaping treatment

PurposeTo construct a machine learning (ML)-based model for estimating the alignment curve (AC) curvature in orthokeratology lens fitting for vision shaping treatment (VST), which can minimize the number of lens trials, improving efficiency while maintaining accuracy, with regards to its improvement over a previous calculation method. MethodsData were retrospectively collected from the clinical case files of 1271 myopic subjects (1271 right eyes). The AC curvatures calculated with a previously published algorithm were used as the target data sets. Four kinds of machine learning algorithms were implemented in the experimental analyses to predict the targeted AC curvatures: robust linear regression models, support vector machine (SVM) regression models with linear kernel functions, bagging decision trees, and Gaussian processes. The previously published calculation method and the novel machine learning method were then compared to assess the final parameters of ordered lenses. ResultsThe linear SVM and Gaussian process machine learning models achieved the best performance. The input variables included sex, age, horizontal visible iris diameter (HVID), spherical refraction (SER), cylindrical refraction, eccentricity value (e value), flat K (K1) and steep K (K2) readings, anterior chamber depth (ACD), and axial length (AL). The R-squared values for the output AC1K1, AC1K2 and AC2K1 values were 0.91, 0.84, and 0.73, respectively. The previous calculation method and machine learning methods displayed excellent consistency, and the proposed methods performed best based on flat K reading and e values. ConclusionsThe ML model can provide practitioners with an efficient method for estimating the AC curvatures of VST lenses and reducing the probability of cross-infection originating from trial lenses, which is especially useful during pandemics, such as that for COVID-19.