Support Vector Machine Regression Model Research Articles

Remote Sensing Model for Estimating Atmospheric PM2.5 Concentration in the Guangdong-Hong Kong-Macao Greater Bay Area

PM2.5 is extremely harmful to the atmospheric environment and human health, and a timely and accurate understanding of PM2.5 with high spatial and temporal resolution plays an important role in the prevention and control of air pollution. Based on multi-angle implementation of atmospheric correction algorithm (MAIAC), 1 km AOD products, ERA5 meteorological data, and pollutant concentrations (CO, O3, NO2, SO2, PM10, and PM2.5) in the Guangdong-Hong Kong-Macao Greater Bay Area during 2015-2020, a geographically and temporally weighted regression model (GTWR), BP neural network model (BPNN), support vector machine regression model (SVR), and random forest model (RF) were established, respectively, to estimate PM2.5 concentration. The results showed that the estimation ability of the RF model was better than that of the BPNN, SVR, and GTWR models. The correlation coefficients of the BPNN, SVR, GTWR, and RF models were 0.922, 0.920, 0.934, and 0.981, respectively. The RMSE values were 7.192, 7.101, 6.385, and 3.670 μg·m-3. The MAE values were 5.482, 5.450, 4.849, and 2.323 μg·m-3, respectively. The RF model had the best effect during winter, followed by that during summer, and again during spring and autumn, with correlation coefficients above 0.976 in the prediction of different seasons. The RF model could be used to predict the PM2.5 concentration in the Greater Bay Area. In terms of time, the daily ρ(PM2.5) of cities in the Greater Bay Area showed a trend of "decreasing first and then increasing" in 2021, with the highest values ranging from 65.550 μg·m-3 to 112.780 μg·m-3 and the lowest values ranging from 5.000 μg·m-3 to 7.899 μg·m-3. The monthly average concentration showed a U-shaped distribution, and the concentration began to decrease in January and gradually increased after reaching a trough in June. Seasonally, it was characterized by the highest concentration during winter, the lowest during summer, and the transition during spring and autumn. The annual average ρ(PM2.5) of the Greater Bay Area was 28.868 μg·m-3, which was lower than the secondary concentration limit. Spatially, there was a "northwest to southeast" decreasing distribution of PM2.5 in 2021, and the high-pollution areas clustered in the central part of the Greater Bay Area, represented by Foshan. Low concentration areas were mainly distributed in the eastern part of Huizhou, Hong Kong, Macao, Zhuhai, and other coastal areas. The spatial distribution of PM2.5 in different seasons also showed heterogeneity and regionality. The RF model estimated the PM2.5 concentration with high accuracy, which provides a scientific basis for the health risk assessment associated with PM2.5 pollution in the Greater Bay Area.

Prediction of Autumn Ozone Concentration in the Pearl River Delta Based on Machine Learning

Based on the observation data of the daily maximum 8-hour ozone (O3) average concentration[MDA8-O3, ρ(O3-8h)] and meteorological reanalysis data in the Pearl River Delta Region from 2015 to 2022, four machine learning methods, i.e., support vector machine regression (SVR), random forest (RF), multi-layer perceptron (MLP), and lightweight gradient boosting machine (LG) were used to establish MDA8-O3 prediction models. The results showed that the SVR model had the best prediction performance on MDA8-O3 during the whole year, the coefficient of determination (R2) reached 0.86, and the root mean square error (RMSE) and mean absolute error (MAE) were 16.3 μg·m-3 and 12.3 μg·m-3, respectively. The prediction performance of the SVR model in autumn was still slightly better than that of LG and MLP, with R2,RMSE,and MAE values of 0.88, 19.8 μg·m-3,and 16.1 μg·m-3, respectively. The RF model performed the worst in the autumn prediction. In addition, the models trained by data from the whole year had better prediction ability on autumn MDA8-O3 than that of those only trained by autumn data, and the R2 differed 0.08-0.14.

Construction and evaluation of endometriosis diagnostic prediction model and immune infiltration based on efferocytosis-related genes.

Background: Endometriosis (EM) is a long-lasting inflammatory disease that is difficult to treat and prevent. Existing research indicates the significance of immune infiltration in the progression of EM. Efferocytosis has an important immunomodulatory function. However, research on the identification and clinical significance of efferocytosis-related genes (EFRGs) in EM is sparse. Methods: The EFRDEGs (differentially expressed efferocytosis-related genes) linked to datasets associated with endometriosis were thoroughly examined utilizing the Gene Expression Omnibus (GEO) and GeneCards databases. The construction of the protein-protein interaction (PPI) and transcription factor (TF) regulatory network of EFRDEGs ensued. Subsequently, machine learning techniques including Univariate logistic regression, LASSO, and SVM classification were applied to filter and pinpoint diagnostic biomarkers. To establish and assess the diagnostic model, ROC analysis, multivariate regression analysis, nomogram, and calibration curve were employed. The CIBERSORT algorithm and single-cell RNA sequencing (scRNA-seq) were employed to explore immune cell infiltration, while the Comparative Toxicogenomics Database (CTD) was utilized for the identification of potential therapeutic drugs for endometriosis. Finally, immunohistochemistry (IHC) and reverse transcription quantitative polymerase chain reaction (RT-qPCR) were utilized to quantify the expression levels of biomarkers in clinical samples of endometriosis. Results: Our findings revealed 13 EFRDEGs associated with EM, and the LASSO and SVM regression model identified six hub genes (ARG2, GAS6, C3, PROS1, CLU, and FGL2). Among these, ARG2, GAS6, and C3 were confirmed as diagnostic biomarkers through multivariate logistic regression analysis. The ROC curve analysis of GSE37837 (AUC = 0.627) and GSE6374 (AUC = 0.635), along with calibration and DCA curve assessments, demonstrated that the nomogram built on these three biomarkers exhibited a commendable predictive capacity for the disease. Notably, the ratio of nine immune cell types exhibited significant differences between eutopic and ectopic endometrial samples, with scRNA-seq highlighting M0 Macrophages, Fibroblasts, and CD8 Tex cells as the cell populations undergoing the most substantial changes in the three biomarkers. Additionally, our study predicted seven potential medications for EM. Finally, the expression levels of the three biomarkers in clinical samples were validated through RT-qPCR and IHC, consistently aligning with the results obtained from the public database. Conclusion: we identified three biomarkers and constructed a diagnostic model for EM in this study, these findings provide valuable insights for subsequent mechanistic research and clinical applications in the field of endometriosis.

Genetic biomarker prediction based on gender disparity in asthma throughout machine learning.

Asthma is a chronic respiratory condition affecting populations worldwide, with prevalence ranging from 1-18% across different nations. Gender differences in asthma prevalence have attracted much attention. The aim of this study was to investigate biomarkers of gender differences in asthma prevalence based on machine learning. The data came from the gene expression omnibus database (GSE69683, GSE76262, and GSE41863), which involved in a number of 575 individuals, including 240 males and 335 females. Theses samples were divided into male group and female group, respectively. Grid search and cross-validation were employed to adjust model parameters for support vector machine, random forest, decision tree and logistic regression model. Accuracy, precision, recall, and F1 score were used to evaluate the performance of the models during the training process. After model optimization, four machine learning models were utilized to predict biomarkers of sex differences in asthma. In order to validate the accuracy of our results, we performed Wilcoxon tests on the genes expression. In datasets GSE76262 and GSE69683, support vector machine, random forest, logistic regression, and decision tree all achieve 100% accuracy, precision, recall, and F1 score. Our findings reveal that XIST serves as a common biomarker among the three samples, comprising a total of 575 individuals, with higher expression levels in females compared to males (p < 0.01). XIST serves as a genetic biomarker for gender differences in the prevalence of asthma.

Hybrid grey wolf and whale optimization for enhanced Parkinson's prediction based on machine learning models using biomedical sound

BackgroundBiomedical voice measurements have been used by many physicians and scientists to distinguish Parkinson's patients from ordinary people. Measurements of biomedical voices involve many variables calculated from signal analysis of the voice. These variables can be used to distinguish Parkinson's patients from non-Parkinson's patients. Unfortunately, using all computed variables may be ineffective and inaccurate due to the complexity of establishing a relationship between all the input variables and Parkinson's states. MethodsThis paper describes the development of a hybrid optimizer by combining two optimization algorithms: the Grey Wolf Optimizer and the Whale Optimizer. The hybrid optimizer enhances feature selection to provide a fast and robust Parkinson's prediction model. Additionally, this research incorporates five other feature selection algorithms for comparison purposes: Ranker, Greedy, BestFirst, Hybrid Grey Wolf Optimization, and Whale Optimization. The outputs from these algorithms are fed into six prediction models to determine the most accurate combination. These models include the neural network, Quest, Chi-squared Automatic Interaction Detection, support vector machine, CR-tree, and logistic regression models. Subsequently, the developed models are compared to identify the most accurate model based on various performance metrics. ResultsThe combination of the hybrid grey wolf and whale models yielded the highest scores in most metrics, achieving a perfect recall and a high F1 score. All models generated similar output, with an accuracy greater than 0.89. Quest, CR-tree, and neural networks are the most reliable and accurate models. ConclusionsBiomedical sound measurements can be used to develop an accurate and cost-effective Parkinson's prediction model.

IoT enabled Intelligent Energy Management System employing advanced forecasting algorithms and load optimization strategies to enhance renewable energy generation

Effectively utilizing renewable energy sources while avoiding power consumption restrictions is the problem of demand-side energy management. The goal is to develop an intelligent system that can precisely estimate energy availability and plan ahead for the next day in order to overcome this obstacle. The Intelligent Smart Energy Management System (ISEMS) described in this work is designed to control energy usage in a smart grid environment where a significant quantity of renewable energy is being introduced. The proposed system evaluates various predictive models to achieve accurate energy forecasting with hourly and day-ahead planning. When compared to other predictive models, the Support Vector Machine (SVM) regression model based on Particle Swarm Optimization (PSO) seems to have better performance accuracy. Then, using the anticipated requirements, the experimental setup for ISEMS is shown, and its performance is evaluated in various configurations while considering features that are prioritized and associated with user comfort. Furthermore, Internet of Things (IoT) integration is put into practice for monitoring at the user end.

Cyberbullying Detection System on Social Media Using Supervised Machine Learning

The use of digital and social media is growing every day as technology advances. People in the twenty-first century are growing up in a social media and internet-enabled society. Digital media offers a lot of opportunities, but people frequently tend to misuse them. On social networking sites, people spread anger toward a person. People are affected by cyberbullying in various ways. It has an impact on more than just health; numerous other factors put life in danger. Cyberbullying is a widespread modern phenomenon that people cannot completely avoid but can prevent. The author proposes a system for automatic cyberbullying detection and prevention using supervised machine learning. The system considers key characteristics of cyberbullying, such as the intention to harm, repeated behavior, and the use of abusive language. Support vector machines and logistic regression are employed to identify cyberbullying and related themes/categories such as race, physical, sexuality, and politics.This proposed method offers a novel theory for the detection of cyberbullying: texting has evolved over time due to changes in context usage, and language. In the dataset that includes tweets, Support Vector Machine (SVM), Naïve Bayes, and Logistic Regression (LR) models were tested along with different Natural Language Processing methods. The accuracy of the system is improved by sentiment analysis, N-gram analysis, and other non-traditional feature extraction methods like Term Frequency-Inverse Document Frequency (TF-IDF) and profanity detection.

Enhancing Sentiment Analysis Accuracy by Optimizing Hyperparameters of SVM and Logistic Regression Models

The Analysis of Sentiments expressed on Twitter is a widely practiced application of Natural Language Processing (NLP) and Artificial Intelligence (AI). This process involves examining tweets to determine the emotional tone conveyed within the message. AI-based approaches are employed in Twitter sentiment analysis, typically following these steps: Data Collection, Data Preprocessing, and Sentiment Analysis, where AI techniques like Support Vector Machines (SVM) and Logistic Regression are utilized to categorize tweets into positive, negative, or neutral sentiments. Twitter data is a valuable source of information, serving diverse purposes such as real-time updates, user feedback, brand monitoring, market research, digital marketing, and political analysis. The Twitter API (Application Programming Interface) provides developers with tools and functionalities to access and interact with Twitter data, including tweets, user profiles, and timelines, enabling a wide range of applications and services. However, Twitter sentiment analysis presents challenges such as handling sarcasm, irony, colloquial language, and coping with the sheer volume and rapid flow of Twitter data. Nevertheless, with effective preprocessing techniques and AI methods, Twitter sentiment analysis can yield valuable insights into public opinion on various topics.

Comparative Analysis of Deaths and DALYs associated with Air Pollution for SAARC Countries Using Support Vector Machine Regression Model

Comparative Analysis of Deaths and DALYs associated with Air Pollution for SAARC Countries Using Support Vector Machine Regression Model

Estimation of Biochemical Pigment Content in Poplar Leaves Using Proximal Multispectral Imaging and Regression Modeling Combined with Feature Selection.

Monitoring the biochemical pigment contents in individual plants is crucial for assessing their health statuses and physiological states. Fast, low-cost measurements of plants' biochemical traits have become feasible due to advances in multispectral imaging sensors in recent years. This study evaluated the field application of proximal multispectral imaging combined with feature selection and regressive analysis to estimate the biochemical pigment contents of poplar leaves. The combination of 6 spectral bands and 26 vegetation indices (VIs) derived from the multispectral bands was taken as the group of initial variables for regression modeling. Three variable selection algorithms, including the forward selection algorithm with correlation analysis (CORR), recursive feature elimination algorithm (RFE), and sequential forward selection algorithm (SFS), were explored as candidate methods for screening combinations of input variables from the 32 spectral-derived initial variables. Partial least square regression (PLSR) and nonlinear support vector machine regression (SVR) were both applied to estimate total chlorophyll content (Chla+b) and carotenoid content (Car) at the leaf scale. The results show that the nonlinear SVR prediction model based on optimal variable combinations, selected by SFS using multiple scatter correction (MSC) preprocessing data, achieved the best estimation accuracy and stable prediction performance for the leaf pigment content. The Chla+b and Car models developed using the optimal model had R2 and RMSE predictive statistics of 0.849 and 0.825 and 5.116 and 0.869, respectively. This study demonstrates the advantages of using a nonlinear SVR model combined with SFS variable selection to obtain a more reliable estimation model for leaf biochemical pigment content.

A predicting method for the mechanical property response of the marine riser based on the simulation and data-driven models

The accurate and real-time prediction of the mechanical property response for the safety assessment of the marine riser is necessary during offshore oil and gas production. However, a finite element simulation is time-consuming, which obstructs the real-time monitoring and evaluation of the marine riser. Therefore, to obtain the real-time mechanical response of the marine riser, a predicting method based on the simulation and data-driven models is proposed. To obtain the prediction data, the finite element simulation model under the typical working conditions is established by the Abaqus software, and then the sensitivity analysis of influence factors is conducted due to the varied working conditions. The orthogonal experimental method is used to select the typical working conditions of the marine riser, and the selection of the sensitive influence factors is ensured based on the typical working conditions, the range analysis, and the grey relational method. To obtain enough training data, the Latin hypercube sampling method is used to enlarge the data for the analysis process. To find a more reliable prediction algorithm, four typical single surrogate models, which are the polynomial response surface model, the radial basis model, the kriging model, and the support vector machine regression model, are selected to establish a predicting model library. Meanwhile, a combining surrogate model, including the average weight surrogate model and the adaptive weight surrogate model, is established based on the combining weight to further improve the predicting accuracy. As a result, an optimal surrogate model is selected from the above four single and two combining surrogate models based on four evaluation criteria including the mean absolute percentage error, the mean absolute error, the root mean square error, and the goodness of fit. The cases show that the optimal surrogate model has a highly rapid response, with average relative errors are 8.17%, 3.42%, and 11.40% for the maximum bending moment, the maximum equivalent stress, and the maximum lateral deformation, respectively. In the above study, the accurate and reliable prediction method of the mechanical property responses will provide a theoretical basis for ensuring the safety of the marine riser.

Determining the geographical origin and glycogen content of oysters using portable near-infrared spectroscopy: Comparison of classification and regression approaches

Oysters are extensively cultivated worldwide. However, significant variations in chemical composition, quality, and price exist between oysters from different geographical origins. This study employed portable near-infrared spectroscopy in conjunction with chemometric analysis to determine the geographical origin and glycogen content of oysters. Pretreatment methods (multiplicative scattering correction, first derivative, and second derivative) were used to preprocess the raw spectra. Partial least squares discriminant analysis (PLS-DA), orthogonal partial least squares discriminant analysis (OPLS-DA), and support vector machine (SVM) were then adopted to establish the qualitative models. Partial least squares regression (PLSR) and support vector machine regression (SVMR) were compared for predicting the glycogen content. The results revealed that the PLS-DA, OPLS-DA, and SVM models classified the geographical origin of oysters with 100% accuracy. For quantitative analysis, the regression equations displayed high predictive ability. The SVMR model was superior to the PLSR model for glycogen content prediction, with a coefficient of determination of prediction (R2P) of 0.9253 and a residual prediction deviation (RPD) of 3.62. Therefore, the proposed approach is suitable for the accurate and environmentally friendly determination of the geographical origin and glycogen content of oysters, thus representing an attractive alternative method for the traceability supervision and quantitative analysis of seafood products.

Exploring the optimal model for assessing SOC and TN in Zanthoxylum bungeanum forest on the Loess Plateau using VNIR spectroscopy

Zanthoxylum bungeanum forest is an important economic forest on the Loess Plateau. The rapid assessment of its soil organic carbon (SOC) and total nitrogen (TN) concentrations is critical for the evaluation of soil quality. Soil samples of different forest ages and soil depths were collected for laboratory analyses and spectral measurements, and the visible and near-infrared reflectance (VNIR) spectral data were processed by mathematical transformations, such as first-order derivative (FD) and second-order derivative, multiple scattering correction, and logarithm of the reciprocal. The importance bands of SOC and TN were screened on the basis of competitive adaptive reweighted sampling. In addition, partial least squares regression and support vector machine regression models were constructed, and the applicability of SOC and TN to the models were compared. Results showed that forest age and soil depth remarkably affect SOC and TN concentrations. Among the calibration and validation models, the combination of the SVMR model with Savitzky–Golay smoothing and FD estimated SOC and TN with the highest accuracy, and the validation accuracy of the surface SOC and TN was higher than that of the bottom depths. Meanwhile, the importance bands involved in the modeling were mainly distributed in 400–600 nm and 1000–2400 nm. The combination of the FD transformation and the SVMR model is suitable for determining SOC and TN concentrations in Z. bungeanum forests, and the model has great potential for the quantitative evaluation of soil quality in the Loess Plateau.

A hybrid AHP-PROMETHEE II onshore wind farms multicriteria suitability analysis using kNN and SVM regression models in northeastern Greece

Wind energy presents a high growth potential in the EU as an emission reduction strategy and to achieve the climate neutrality goal by 2050. Wind farms suitability analysis is one of the primary goals in the spatial planning of wind energy developments. This research paper introduces a hybrid spatial multicriteria GIS-based framework that combines Analytic Hierarchy Process (AHP), PROMETHEE II and Machine Learning algorithms to determine and predict the most efficient onshore wind farm locations by generating suitability index mappings. The methodology allows to overcome PROMETHEE II limitations in raster driven suitability analysis, utilizing machine learning regression methods as the k Nearest Neighbor and Support Vector Machines to predict a graduating mapping of suitability index for wind farm locations in northeastern Greece. The best configured models presented a RMSE of 0.0344 and 0.0154 respectively, indicating a quite high predictive performance. Suitability results indicate that 56.10 % of the feasible locations in the Thrace area present a positive outranking character for the kNN model and 56.79 % for the SVR model. The proposed framework, enriched by PROMETHEE II capabilities, assists energy and spatial planners in identifying suitable sites for wind farm siting and enables rational decision making that enhances efficient wind energy investments.

Modeling the matching stage of HDPE hot plate welding: A study using regression and support vector machine models

AbstractThis research studies the material displacement of high‐density polyethylene (HDPE) during the initial stage of the hot plate welding (HPW) process, called the Matching stage. Newly developed mathematical models simulate the relationship between the main process parameters (force, temperature, and time) and the size of the surface area. The collected data was used to develop four mathematical models for material displacement and time. Two models are machine learning based models (support vector machines). The other two models are regression models in the form of functions. In addition, this study provides a visual representation of HDPE melt displacement with the changes in temperature and pressure. The obtained results indicate that these models can be used for developing a parameter adjustment process or determining specifications for new production equipment. The potential applications of the developed models can be extended to industries that use HPW of HDPE, such as automotive or aerospace. This could result in significant savings in the amount of scrap and waste due to inaccurate and ad hoc settings that currently take place in the industry.Highlights Study of HDPE material displacement in the hot plate welding Matching stage. Visualization of HDPE melt displacement with temperature and pressure changes. Development of SVM and mathematical regression models. Applications in parameter adjustment and equipment specification. Savings in scrap and waste by reducing inaccurate settings.

Correlation Analysis of Large-Span Cable-Stayed Bridge Structural Frequencies with Environmental Factors Based on Support Vector Regression

The dynamic characteristics of bridge structures are influenced by various environmental factors, and exploring the impact of environmental temperature and humidity on structural modal parameters is of great significance for structural health assessment. This paper utilized the Covariance-Driven Stochastic Subspace Identification method (SSI-COV) and clustering algorithms to identify modal frequencies from four months of acceleration data collected from the health monitoring system of the Jintang Hantan Twin-Island Bridge. Furthermore, a correlation analysis is conducted to examine the relationship between higher-order frequency and environmental factors, including temperature and humidity. Subsequently, a Support Vector Machine Regression (SVR) model is employed to analyze the effects of environmental temperature on structural modal frequencies. This study has obtained the following conclusions: 1. Correlation analysis revealed that temperature is the primary influencing factor in frequency variations. Frequency exhibited a strong linear correlation with temperature and little correlation with humidity. 2. SVR regression analysis was performed on frequency and temperature, and an evaluation of the fitting residuals was conducted. The model effectively fit the sample data and provided reliable predictive results. 3. The original structural frequencies underwent smoothing, eliminating the influence of temperature-induced frequency data generated by the SVR model. After eliminating the temperature effects, the fluctuations in frequency within a 24 h period significantly decreased. The data presented in this paper can serve as a reference for further health assessments of similar bridge structures.

Quantitative detection of zearalenone in wheat using intervals selection coupled to near-infrared spectroscopy

Wheat is a globally cultivated cereal crop. However, it is susceptible to Fusarium head blight, which leads to the production of zearalenone (ZEN), significantly impacting the value of wheat. This paper proposed a novel technique for quantitatively detecting ZEN in wheat using near-infrared spectroscopy. The absorbance of wheat flour samples with varying degrees of mildew were collected using a spectral detection system based on the spectrometer. And this paper introduced two methods for feature intervals selection, interval combination optimization (ICO) and interval variable iterative space shrinkage approach (iVISSA), combined with partial least squares (PLS) and support vector machine (SVM) established a regression model based on feature intervals selection for quantitatively detecting ZEN in wheat, and then compared the performance of them. The research results showed that the SVM model outperformed the PLS model in terms of detection performance. Additionally, the SVM model detecting the level of ZEN in wheat based on the feature intervals selected by ICO achieved the best generalization performance, with a root mean square error of prediction (RMSEP) of 31.4148 μg·kg−1, a coefficient of determination of prediction (RP2) of 0.9434, and a relative percent deviation (RPD) of 4.2768. These results demonstrated that the SVM regression model, established by using ICO for selecting the near-infrared spectral intervals, can accurately detect ZEN in wheat. Near-infrared spectroscopy combined with appropriate data analysis methods, which can be used as a simple and fast tool for quantitative detection of mycotoxins of wheat and other grains.

A sensitivity analysis on thermal conductivity of Al2O3-H2O nanofluid: A case based on molecular dynamics and support vector regression method

The current study examines the sensitivity study of the thermal conductivity of water-based alumina nanofluids with variations in concentration, sphericity, and temperature. Thermal conductivity data of alumina nanofluids were obtained by simulation using the non-equilibrium molecular dynamics method with the parameters of nanoparticle volume fraction (1.24–6.2%), particle sphericity (0.6975–1.0), and temperature (290–360 K). Volume fraction and temperature have been discovered to have a major effect on the thermal conductivity of nanofluids, but sphericity should also be taken into consideration. Further, for parameter sensitivity analysis, a support vector machine regression model of thermal conductivity versus parameters was created with a coefficient of determination up to 0.98. The findings show that an Al2O3-H2O nanofluid's thermal conductivity increases with temperature and volume fraction while decreasing with sphericity. Temperature, sphericity, and volume fraction are the variables that are most sensitive to modification, according to a sensitivity analysis. A change in thermal conductivity of up to 4 % can occasionally be brought on by temperature differences of merely 1 %. The use of spherical particles makes it possible for the thermal conductivity of the nanofluid to be more stable, and the sensitive volume fraction region that can cause thermal conductivity to fluctuate across a large range is between 2.5 % and 5.5 %.

A multi-parameter control method for maize threshing based on machine learning algorithm optimisation

A complex field environment and differences in maize density cause feed rate fluctuations in the combine. Traditional threshing methods do not adjust multiple operating parameters based on the feed rate, resulting in low threshing performance and high power consumption. A multi-parameter control method for maize threshing based on the feed rate was proposed to overcome these problems. Random forest, support vector machine, and multiple linear regression machine learning algorithms were used to estimate the threshing performance indices for different feed rates. The algorithm (random forest) was used to construct a control model for the rotor speed, threshing gap, and top cover guide vane angle. The performance of the control system was compared with a threshing system with constant parameters to verify the control model's accuracy. The results demonstrated that the threshing unit with the control system outperformed the one without. The broken grain rate and the power consumption were 2.18% and 36.22% lower, respectively, whereas the unthreshed grain rate was not significantly different. Random forest was more suitable than the support vector machine and multiple linear regression models for establishing a multi-parameter control model for maize threshing. The adjustment of multiple threshing parameters significantly improved the operating performance for different feed rates.

Determination of Molybdenum in Geological Ores by Laser-Induced Breakdown Spectroscopy (LIBS) with Support Vector Machine Regression (SVMR) and Data Preprocessing

A support vector machine regression (SVMR) model that integrates data preprocessing was devised for the determination of Mo in molybdenum ores. To eliminate the negative effects of spectral fluctuations and improve the computational efficiency, the model processes original measurements through the following steps: denoising via wavelet transform smoothing (WTS), debaselining via adaptive iteratively reweighted penalized least squares (airPLS), main characteristic peak extraction, elimination of abnormal spectral data via the box plot method, and normalization via min-max scaling. In this study, 255 characteristic peaks were selected from 17,916 spectral datasets, and the total number of datasets after removing the outliers was 491. The calibration curve approach was used to establish a univariate model. The limit of detection of Mo was 0.0080 wt%. The R2 value of the calibration curve was 0.6675. Linear regression (LR) and SVMR were used to establish a multivariate analysis model. Compared to that of the calibration curve approach, the determination coefficients (R P 2) of LR and SVMR increased from 0.8034 to 0.9859 and 0.9941, respectively. The range of relative errors (REP) decreased from 0.21%–67.66% to 0.48%–18.46% and 2.65%–7.44%, respectively; the mean absolute error (MAEP) was decreased from 0.0173 wt% to 0.0048 and 0.0039 wt%, respectively; and the root mean square error (RMSEP) decreased from 0.0243 wt% to 0.0065 and 0.0042 wt%, respectively. These results indicate that the integration of SVMR with data preprocessing is suitable for the determination of Mo in molybdenum ores.