Multiple Regression Algorithm Research Articles

Machine learning-based bladder effusion estimation model construction on intravesical pressure data

BackgroundThe volume of the bladder effusion is a crucial metric for monitoring patients with intermittent catheterization in, and it serves as a crucial benchmark for bladder rehabilitation training. Clinically, bladder effusion is mainly estimated by ultrasound, which is not convenient for real-time monitoring. It is essential to explore a real-time method for obtaining the intravesical effusion volume to maintain bladder function and rehabilitative training for patients. PurposePrevious clinical trials have demonstrated a close correlation between intravesical pressure and bladder effusion in patients. Currently, there are devices available in clinical practice that can monitor intravesical pressure in real-time. Hence, the aim of this study is to analyze the dynamic relationship between real-time intravesical pressure and bladder effusion and develop a predictive model for bladder effusion. MethodTo validate our hypothesis, we compiled a dataset comprising intravesical pressure curves and corresponding effusion information from patients. Relevant features were extracted from the dataset, and an effusion prediction model was constructed using multiple regression algorithms. The performance of these algorithms was evaluated using the dataset. Finally, we designed a clinical experiment and verified the practical error of the above model. ResultsWe conducted sufficient comparative experiments on two datasets. The gradient boosting regression (GBR) model performs the best on the prediction set of the multi-center merged dataset. It achieved an explained variance score index of 0.84 and a mean absolute error of 23.28 ml. Additionally, actual validation experiments were conducted on 18 patients using the GBR method, confirming the feasibility of this approach in clinical practice. ConclusionThis study verified the validity of our concept and pioneered a method for effusion prediction using intravesical pressure data with promising results. This study is expected to be of great assistance in maintaining bladder function and rehabilitative training for patients.

Novel method for obtaining transfer characteristics of subway-induced ground vibrations

Aiming at the multiple-input multiple-output vibration problem in rail transit, this paper presents a novel method for obtaining transfer characteristics of vehicle-induced vibrations. To verify its accuracy and applicability, the obtained transfer coefficients are further combined with vehicle-track coupling simulations to predict environmental vibrations under different conditions. The results prove that the transfer characteristics from the vibration source to the environment target can be accurately obtained through the multiple regression algorithm and superposition algorithm. Compared with the traditional numerical simulation method composed of both the vehicle-track coupling model and the track-tunnel-soil model, the coefficient of determination R-squared of the two methods in the time domain can reach above 0.9, and errors of the environment evaluation index in the frequency domain are within 0.2 dB. However, the computational effort has been reduced significantly without establishing a complex numerical model of the tunnel-soil (structure) system. Moreover, it is found that environmental vibrations on the ground surface are mainly affected by fastening forces in the vicinity of 60 m centered by the observation point. In particular, the proposed method is expected to supply a certain reference for predicting vibrations under multi-source load in mechanical science and civil engineering.

Predictive Analysis of Hospital Stay after Caesarean Section: A Single-Center Study.

Caesarean section (CS) rate has seen a significant increase in recent years, especially in industrialized countries. There are, in fact, several causes that justify a CS; however, evidence is emerging that non-obstetric factors may contribute to the decision. In reality, CS is not a risk-free procedure. The intra-operative, post-pregnancy risks and risks for children are just a few examples. From a cost point of view, it must be considered that CS requires longer recovery times, and women often stay hospitalized for several days. This study analyzed data from 12,360 women who underwent CS at the "San Giovanni di Dio e Ruggi D'Aragona" University Hospital between 2010 and 2020 by multiple regression algorithms, including multiple linear regression (MLR), Random Forest, Gradient Boosted Tree, XGBoost, and linear regression, classification algorithms and neural network in order to study the variation of the dependent variable (total LOS) as a function of a group of independent variables. We identify the MLR model as the most suitable because it achieves an R-value of 0.845, but the neural network had the best performance (R = 0.944 for the training set). Among the independent variables, Pre-operative LOS, Cardiovascular disease, Respiratory disorders, Hypertension, Diabetes, Haemorrhage, Multiple births, Obesity, Pre-eclampsia, Complicating previous delivery, Urinary and gynaecological disorders, and Complication during surgery were the variables that significantly influence the LOS. Among the classification algorithms, the best is Random Forest, with an accuracy as high as 77%. The simple regression model allowed us to highlight the comorbidities that most influence the total LOS and to show the parameters on which the hospital management must focus for better resource management and cost reduction.

Can chronic kidney disease staging early predict outcome of large-artery ischemic stroke with impaired renal function?

Ischemic stroke poses a major threat to human beings, and a prompt intravenous thrombolytic management remains the gold standard protocol for stroke sufferers. Although the role of thrombolytic therapy (r-tPA) for ischemic stroke patients and those with underlying impaired renal function has been advocated as effective treating strategy, there is still a lack of investigation as to finding out baseline important variables that are capable of early outcome prediction. In this project, we hypothesize that the change of clinical chronic kidney disease (CKD) staging (delta stage = CKD stage after 3-month follow-up - CKD stage at admission) could serve as a crucial predictor of the prognosis of patients. This is a cohort longitudinal retrospective study. A total of 765 cerebral artery ischemic stroke patients with impaired renal function were recruited and followed up for 1 year. Among them, 116 had received the thrombolytic treatment (r-tPA) after being evaluated at the triage in the emergency department and the rest had not (non-r-tPA). Propensity-matching was applied to compare the mortality between the r-tPA and non-r-tPA groups. Multiple logistic regression (LR) and decision tree (DT) algorithm were used to identify important prediction factors for mortality as well as the improvement in neurological function. The 1-year mortality rates for r-tPA and non-r-tPA groups were 32.8% and 44.4%, respectively. The propensity-matched odds ratio of mortality for the r-tPA group compared with the non-r-tPA group is 0.469, with p = 0.003. Logistic regressions suggest that age, Hct, diabetes mellitus type 2, coronary artery disease, and delta stage are important factors for mortality for the non-r-tPA group, whereas age, diabetes mellitus type 2, chronic heart failure, hospital day, and delta stage are important factors for the r-tPA group. On the usage of antihypertensive drugs, ACEI/ARB was not associated with mortality (p = 0.198), whereas the diuretic was, with odds ratio at 1.619 (p = 0.025), indicating higher mortality after administration. Both LR and DT analyses indicate that delta stage is the most important predictor. For the r-tPA group, patients with delta stage ⩽0 had a 24% mortality, while that for delta stage >0 the mortality is 75%. For non-r-tPA patients, the corresponding mortalities were 30.9 and 66.3, respectively. Delta stage is also useful for predicting patients' improvement of neurological function, assessed by NIHSS, mRS, and Barthel Index. The areas under the curve for the three assessments are 0.83, 0.835, and 0.663, respectively. Large-artery ischemic stroke patients who received thrombolytic treatment had significantly lower mortality, even when presenting underlying impaired renal function. The change of CKD staging (delta stage) is capable of acting as a powerful clinical baseline surrogate for both r-tPA and non-r-tPA patients in terms of early outcome prediction. Long-term use of diuretics could be potentially harmful to this group of patients. Moreover, delta stage correlates well with clinical long-term neurological functionality assessment (NIHSS, mRS, and Barthel index), which is helpful in aiding urgent clinical decision-making.

Багатокласовий класифікатор на основі бінарних логістичних регресій, одержаних за принципами МГУА

Introduction. The issue of accuracy improvement in classification tasks is always topical, and various approaches have been developed, applied in accordance with the peculiarities of the problem formulation and properties of the feature space. Among the most effective models, classifiers based on multiple logistic regressions have proved themselves. Purpose. The aim of the paper is to develop an algorithm for solving multiclassification problems on the basis of binary logistic models built by the stepwise multiple logistic regression algorithm of the Stepwise type, improved according to the principles of the method of group accounting of arguments. Methods. The paper proposes a modification of the stepwise algorithm for creating binary multivariate logistic regressions Stepwise, where it is proposed to optimize the algorithm parameters in accordance with the principles of the method of group consideration of arguments: significance levels by the logarithmic likelihood ratio test for inclusion and exclusion of model arguments. The choice of optimal parameters is realized in accordance with an external criterion that takes into account the balance of classification accuracy of training and test samples and the balance of class classification accuracy. Subsequently, the binary class models obtained by the one-versus-all principle are combined into a multiclass classifier that returns the answer according to the maximum likelihood of the class. The comparison of classification models obtained by the classical Stepwise algorithm and the one proposed in the robot is carried out on the medical data of the publicly available Internet resource Kaggle. Conclusion. The paper substantiates and demonstrates the advantages of classifiers based on logistic multivariate regressions optimized according to the principles of the method of group consideration of arguments relative to the classical version of the Stepwise algorithm. The effective application of the algorithm in solving multiclass classification problem is shown.

Machine learning for the analysis of quality of life using the World Happiness Index and Human Development Indicators

Machine learning algorithms play an important role in analyzing complex data in research across various fields. In this paper, we employ multiple regression algorithms and statistical techniques to investigate the relationship between objective and subjective quality of life indicators and reveal the key factors affecting happiness at the international level based on data from the Human Development Index and the World Happiness Index covering the period from 2015 to 2021. The Pearson correlation analysis showed that happiness is related to the HDI score and GNI per capita. The best-performing model for forecasting happiness was the random forest regression, with a R2 score of 0.93667, a mean squared error of 0.0033048, and a root mean squared error of 0.05748, followed by the XGBoost regression and the Decision Tree regression, respectively. These models indicated that GNI per capita is the most significant feature in predicting happiness.

Application of Data Visualization and Big Data Analysis in Intelligent Agriculture

Intelligent agriculture can renovate agricultural production and management, making agricultural production truly scientific and efficient. The existing data mining technology for agricultural information is powerful and professional. But the technology is not well adapted for intelligent agriculture. Therefore, this paper introduces data visualization and big data analysis into the application scenarios of intelligent agriculture. Firstly, an intelligent agriculture data visualization system was established, and the RadViz data visualization method was detailed for intelligent agriculture. Moreover, the intelligent agriculture data were processed using dimensionality reduction through principal component analysis (PCA) and further optimized through k-means clustering (KMC). Finally, the crop yield was predicted using the multiple regression algorithm and the residual principal component regression algorithm. The crop yield prediction model was proved effective through experiments.

The impact of CDIO's dimensions and values on IT Learner's attitude and behavior: A regression model using Partial Least Squares

CDIO (Conceiving-Designing-Implementing-Operating), crowdsourcing and gamification are gaining more popularity in IT education. However, factors that influence learners' attitude toward this method are yet to be discovered. Therefore, this study aims to develop and test a conceptual model of implementing CDIO-based curriculum in IT education. For this purpose, CDIO dimensions were conceptualized and developed into questionnaire items. Then 141 students who experienced the CDIO method in information security course and lab, were sampled through action-research approach to investigate their perceptions and experiences about the learning stages, dimensions and values of this teaching method. Data gathered were analyzed by multiple regression algorithm using Partial Least Squares-Structural Equation Modeling (PLS-SEM) statistical approach. The results reveal that the ‘mastery of the concept’, ‘implement and operate’, ‘perceived values’, ‘demonstration and resources’, and ‘admin’ could significantly (in direct and indirect paths) affect learner's intention to accept the CDIO method and adopt it in IT classes. Finally, implications to theory and practice were indicated, and future research directions were suggested.

Construction of mRNA prognosis signature associated with differentially expressed genes in early stage of stomach adenocarcinomas based on TCGA and GEO datasets

BackgroundStomach adenocarcinomas (STAD) are the most common malignancy of the human digestive system and represent the fourth leading cause of cancer-related deaths. As early-stage STAD are generally mild or asymptomatic, patients with advanced STAD have short overall survival. Early diagnosis of STAD has a considerable influence on clinical outcomes.MethodsThe mRNA expression data and clinical indicators of STAD and normal tissues were obtained from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) database. The gene expression differences were analyzed by R packages, and gene function enrichment analysis was performed. Kaplan–Meier method and univariate Cox proportional risk regression analysis were used to screen differential expressed genes (DEGs) related to survival of STAD patients. Multivariate Cox proportional risk regression analysis was used to further screen and determine the prognostic DEGs in STAD patients, and to construct a multigene prognostic prediction signature. The accuracy of predictive signature was tested by receiver operating characteristic (ROC) curve software package, and the nomogram of patients with STAD was drawn. Cox regression was used to investigate the correlation between multigene prognostic signature and clinical factors. The predictive performance of this model was compared with two other models proposed in previous studies using KM survival analysis, ROC curve analysis, Harrell consistency index and decision curve analysis (DCA). qRT-PCR and Western blot were used to verify the expression levels of prognostic genes. The pathways and functions of possible involvement of features were predicted using the GSEA method.ResultsA total of 569 early-stage specific DEGs were retrieved from TCGA-STAD dataset, including 229 up-regulated genes and 340 down-regulated genes. Enrichment analysis showed that the early-stage specific DEGs were associated with cytokine–cytokine receptor interaction, neuroactive ligand–receptor interaction, and calcium signaling pathway. Multiple Cox regression algorithm was used to identify 10 early-stage specific DEGs associated with overall survival (P < 0.01) of STAD patients, and a multi-mRNA prognosis signature was established. The patients were divided into high-risk group and low-risk group according to the risk score. In the training set, the prognostic signature was positively correlated with tumor size and stage (P < 0.05), survival curve (P < 0.001) and time-dependent ROC (AUC = 0.625). In the training dataset and test dataset, the both signatures had good predictive efficiencies. Cox regression and DCA analysis revealed that the prognostic signature was an independent factor and had a better predict effect than the conventional TNM stage classification method and the earlier published biomarkers on the prognosis of STAD patients.ConclusionIn this study, based on the early-stage specifically expressed genes, the prognostic signature constructed through TCGA and GEO datasets may become an indicator for clinical prognosis assessment of STAD and a new strategy for targeted therapy in the future.

Prediction of high-speed train delay propagation based on causal text information

The delay-causing text data contain valuable information such as the specific reasons for the delay, location and time of the disturbance, which can provide an efficient support for the prediction of train delays and improve the guidance of train control efficiency. Based on the train operation data and delay-causing data of the Wuhan–Guangzhou high-speed railway, the relevant algorithms in the natural language processing field are used to process the delay-causing text data. It also integrates the train operating-environment information and delay-causing text information so as to develop a cause-based train delay propagation prediction model. The Word2vec model is first used to vectorize the delay-causing text description after word segmentation. The mean model or the term frequency-inverse document frequency-weighted model is then used to generate the delay-causing sentence vector based on the original word vector. Afterward, the train operating-environment features and delay-causing sentence vector are input into the extreme gradient boosting (XGBoost) regression algorithm to develop a delay propagation prediction model. In this work, 4 text feature processing methods and 8 regression algorithms are considered. The results demonstrate that the XGBoost regression algorithm has the highest prediction accuracy using the test features processed by the continuous bag of words and the mean models. Compared with the prediction model that only considers the train-operating-environment features, the results show that the prediction accuracy of the model is significantly improved with multiple regression algorithms after integrating the delay-causing feature.

Performance Prediction in EDM Process for Al 6061 Alloy Using Response Surface Methodology and Genetic Algorithm

The Electric Discharge (EDM) method is a novel thermoelectric manufacturing technique in which materials are removed by a controlled spark erosion process between two electrodes immersed in a dielectric medium. Because of the difficulties of EDM, determining the optimum cutting parameters to improve cutting performance is extremely tough. As a result, optimizing operating parameters is a critical processing step, particularly for non-traditional machining process like EDM. Adequate selection of processing parameters for the EDM process does not provide ideal conditions, due to the unpredictable processing time required for a given function. Models of Multiple Regression and Genetic Algorithm are considered as effective methods for determining the optimal processing variables of Electrical Discharge Machining. The material removal rate (MRR) and tool wear (Tw) were investigated using the process variables of pulse on time (Ton), pulse off time (Toff), and current intensity (Ip). The established empirical models were used to perform Genetic Algorithm (GA) to maximize (MRR) and minimize (Tw). The optimization results were utilized to establish machining conditions, validate empirical models, and obtain optimization outcomes. The optimal result that appears in this work was the pulse on (176.261 μs), pulse off (39.42 μs), and current intensity (23.62 Amp.) to maximize the MRR to (0.78391 g/min) and reduce tool wear to (0.0451 g/min).

Electric Vehicle Transient Speed Control Based on Vector Control FM-PI Speed Controller for Induction Motor

The speed control of induction machines for multiple-speed handling is critical. When the vector control method is applied to induction machines, it has a significant impact on speed utilization. This strategy of operating the machine at a fixed predefined speed mode presents better results for electric vehicles. An effective model for a speed control loop is proposed in this paper, using a fixed-mode proportional integral (FM-PI) controller based on an upper and lower limit torque limiter. The power supply is fed using a lithium-ion battery with an inverter-fed mechanism. Moreover, the proposed model is validated using simulations with user-defined speed modes (40, 60, and 80 km/h). These speed modes, with different torque commands, have been considered for advanced modeling. In this model, torque is developed via a closed-loop control operation to attain the required speed assigned by the user. The sensors are used to collect data, and a multiple regression algorithm analyzes the dataset to predict input parameters (voltage (Vab), phase current (I), and torque (T)) required to achieve the desired speed mode. The efficiency of the proposed model is compared with induction motors bearing the same rating for the loaded and unloaded speed test. Effective machine parameter control is achieved by reaching the desired performance levels of 94.37% and 78.30% in a shorter time for the loaded and unloaded modes. A speed response comparison of the FOPID, KW-WOA-PID, SVR-PI, and FM-PI controller model simulation results indicates that the FM-PI speed controller guarantees better performance and displays an improvement in rising time and settling time, compared to other controllers. The implementation of different driving scenarios proves the model’s effectiveness for robust speed applications.

Prediction of Elastic Modulus for Fibre-Reinforced Soil-Cement Mixtures: A Machine Learning Approach

Soil-cement mixtures reinforced with fibres are an alternative method of chemical soil stabilisation in which the inherent disadvantage of low or no tensile or flexural strength is overcome by incorporating fibres. These mixtures require a significant amount of time and resources for comprehensive laboratory characterisation, because a considerable number of parameters are involved. Therefore, the implementation of a Machine Learning (ML) approach provides an alternative way to predict the mechanical properties of soil-cement mixtures reinforced with fibres. In this study, Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), Random Forest (RF), and Multiple Regression (MR) algorithms were trained for predicting the elastic modulus of soil-cement mixtures reinforced with fibres. For ML algorithms training, a dataset of 121 records was used, comprising 16 properties of the composite material (soil, binder, and fibres). ANN and RF showed a promising determination coefficient (R2 ≥ 0.93) on elastic modulus prediction. Moreover, the results of the proposed models are consistent with the findings that the fibre and binder content have a significant effect on the elastic modulus.

Adsorptive removal of toxic malachite green from its aqueous solution by Bambusa vulgaris leaves and its acid-treated form: DFT, MPR and GA modeling

In the current investigation, bamboo leaves (BL), H2SO4 treated bamboo leaves (SBL), and H3PO4 treated bamboo leaves (PBL) were utilized as biosorbents for the elimination of Malachite Green (MG) from the synthetic medium. The adsorption study was executed under the variation of different experimental conditions like pH, biosorbent dosage, contact time, and the temperature on the MG. Langmuir isotherm fit the adsorption data with maximum monolayer adsorption capacity, 151.735 mg/g at 298 K − 168.339 mg/g at 318 K for PBL. The data fitted the pseudo-2nd -order kinetic model for all three adsorbents with a correlation coefficient greater than 0.99, indicating that chemisorption controls adsorption. The Dubinin-Radushkevich isotherm indicated that the mean sorption energy (E) is a physisorption mechanism. So, the process involves physical sorption as well as chemical sorption processes with negligible sorption energy. The FTIR, Raman Spectra, and 13C NMR results show that different functional groups of cellulose, hemicellulose and lignin are involved in MG elimination. The theoretical studies were applied for a deeper understanding of the adsorption mechanism of MG using semi-empirical quantum chemical calculations. The DFT Calculations yielded valuable information about quantum chemical properties, like EHOMO, ELUMO, electrophilicity, chemical reactivity, dipole moment, and hardness for adsorbent/adsorbate components and the binding energy from adsorbent/adsorbate interactions. Multiple polynomial regression and genetic algorithm also have been successfully applied to predict the removal percentage of malachite green.

Comparison of the Performance of Several Regression Algorithms in Predicting the Quality of White Wine in WEKA

The goal of the study was to examine the efficacy of multiple regression algorithms in predicting white wine quality. The white wine dataset from the UCI Machine Learning Repository was used. The Waikato Environment for Knowledge Analysis uses and implements regression methods. The correlation coefficient reveals that the result of performance is that the According to the results of the experiment, the Random Forest (r = 0.7459) ranked first, followed by k-Nearest Neighbor (r = 0.6225), Decision Tree (r= 0.5500), Linear regression (r =0.5257), Multi-layer perceptron (r = 0.5236), and Support Vector Machine (r= 5225). Alcohol and fixed acidity, with (r=0.48) and (r=-0.39), respectively, show a substantial correlation on regression model performance prediction, but other variables have a weak to no significant link. Future research, such as the use of additional prediction models, could be utilized to determine and compare its performance to the study's existing findings

A real-time collaborative machine learning based weather forecasting system with multiple predictor locations

Weather forecasting is an important application in meteorology and has been one of the most scientifically and technologically challenging problems around the world. As the drastic effects of climate change continue to unfold, localised short term weather prediction with high accuracy has become more important than ever. In this paper, a collaborative machine learning-based real-time weather forecasting system has been proposed whereby data from several locations are used to predict the weather for a specific location. In this work, five machine learning algorithms have been used and tests have been performed in four different locations in Mauritius to predict weather parameters such as Temperature, Wind Speed, Wind Direction, Pressure, Humidity, and Cloudiness. The weather data were collected using the OpenWeather API from a mobile as well as a desktop edge device. The data were stored as a JSON file in both the IBM Cloudant database and a local MySQL database. Analytics were performed on both a local server that captures the incoming data from the edge device and via a servlet deployed on the IBM cloud platform. Five machine learning algorithms namely Multiple Linear Regression (MLP), Multiple Polynomial Regression (MPR), K-Nearest Neighbours (KNN), Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN) were tested using both collaborative and non-collaborative methods. The experiments showed that the collaborative regression schemes achieved 5% lower Mean Absolute Percentage Error (MAPE) than non-collaborative ones and the Multiple Polynomial Regression (MLR) algorithm outperformed all the other algorithms with errors ranging from 0.009% to 9% for the different weather parameters. In general, the results showed that collaborative based weather forecasting with multiple predictor locations can potentially increase the accuracy of the predictions in machine learning algorithms.

Studying the Impact of Health Education on Student Knowledge and Behavior through Big Data and Cloud Computing

Artificial intelligence and big data, as emerging technologies that have attracted much attention in recent years, have broad application and development space in improving the development of intelligent and refined education in colleges and universities. The application of artificial intelligence and big data to the mental health education practice of college students has a very positive effect on accurately discovering and scientifically solving the mental health problems of college students. In order to combine big data and cloud computing platform organically, this paper introduces an intelligent algorithm based on multi-output support vector regression (MSVR) model and immune clone selection algorithm (ICSA). At the same time, we couple the two to obtain a new intelligent algorithm, namely, immune multiple output support vector regression (ICSA-MSVR) algorithm. Based on the prediction results of health education on students' knowledge and behavior by cloud computing platform, the necessary conditions for three intelligent algorithms to complete the task are summarized. Numerical experimental results show that ICSA-MSVR plays a role in both local search and global search, and is more effective in large-scale cloud computing task scheduling. In addition, in task scheduling, when the task completion time is short, ICSA-MSVR has a lower load imbalance than ICSA and MSVR, which can achieve better load balancing, and the load between virtual machines is closer. Finally, combined with the problems and the needs of students’ health education, suggestions are put forward to deepen the application of technology in students’ mental health education. This approach can provide corresponding ideas and reference methods for improving the scientificity, pertinence, and effectiveness of mental health education.

Filling Gaps in Daily Precipitation Series Using Regression and Machine Learning in Inter-Andean Watersheds

As precipitation is a fundamental component of the global hydrological cycle that governs water resource distribution, the understanding of its temporal and spatial behavior is of great interest, and exact estimates of it are crucial in multiple lines of research. Meteorological data provide input for hydroclimatic models and predictions, which generally lack complete series. Many studies have addressed techniques to fill gaps in precipitation series at annual and monthly scales, but few have provided results at a daily scale due to the complexity of orographic characteristics and in some cases the non-linearity of precipitation. The objective of this study was to assess different methods of filling gaps in daily precipitation data using regression model (RM) and machine learning (ML) techniques. RM included linear regression (LRM) and multiple regression (MRM) algorithms, while ML included multiple regression algorithms (ML-MRM), K-nearest neighbors (ML-KNN), gradient boosting trees (ML-GBT), and random forest (ML-RF). This study covered the Malas, Omas, and Cañete River (MOC) watersheds, which are located on the Pacific Slope of central Peru, and a nineteen-year period of records (2001–2019). To assess model performance, different statistical metrics were applied. The results showed that the optimized machine learning (OML) models presented the least variability in estimation errors and the best approximation of the actual data from the study zone. In addition, this investigation shows that ML interprets and analyzes non-linear relationships between rain gauges at a daily scale and can be used as an efficient method of filling gaps in daily precipitation series.

Implementation of regression algorithms for oil recovery prediction

This paper presents the work of predicting oil production using machine learning methods. As a machine learning method, a multiple linear regression algorithm with polynomial properties was implemented. Regression algorithms are suitable and workable methods for predicting oil production based on a data-driven approach. The synthetic dataset was obtained using the Buckley-Leverett mathematical model, which is used to calculate hydrodynamics and determine the saturation distribution in oil production problems. Various combinations of parameters of the oil production problem were chosen, where porosity, viscosity of the oil phase and absolute permeability of the rock were taken as input parameters for machine learning. And the value of the oil recovery factor was chosen as the output parameter. More than 400 thousand synthetic data were used to test multiple regression algorithms. To estimate the quality of regression algorithms, the mean square error metrics and the coefficient of determination were used. It was found that linear regression does not cover all patterns in the data due to underfitting. Various degrees of polynomial regression were deployed and tested, and it was also found that for our synthetic data, the quadratic polynomial model trains quite well and perfectly predicts the value of the oil recovery factor. To solve the overfitting problem, L1 regularization known as the Lasso regression method was applied. For the quadratic polynomial regression model, the coefficient of determination was 0.96, which is a pretty good result for the test data. Thus, it is assumed that the data-driven machine learning methods discussed in the paper can be useful for predicting the oil recovery factor using practical data from oil fields at the stages of production

Wind Turbines Fault Classification Treatment Method

With the aim of solving the problems arising from the low efficiency and low accuracy of fault classification of wind power towers and turbine equipment (referred to as wind power systems for short) using artificial data analysis, this paper takes the operational data for wind power systems as the research object and proposes an improved K-means weighted dynamic clustering fault classification algorithm (DT clustering). First, historical and asymmetrical operational data from wind power systems were pre-processed to construct the data time series matrix and establish the fault classification model; second, the linear approximate constrained optimization algorithm and multiple regression algorithm were combined to build the model parameter optimization model. Finally, the comparative analysis of various algorithms showed the superiority of this algorithm, and the effectiveness of this model should be proved in practical applications.