Failure Prediction Research Articles

Relationship between serum level of miR-338-3p and miR-105-3p and bone metabolic markers in patients with diabetes nephropathy

Objectives Diabetic nephropathy (DN) is one of the most common and serious complications of diabetes. The purpose of this study was to explore the relationship between serum microRNA-338-3p (miR-338-3p) and miR-105-3p and bone metabolic markers in patients with DN at different stages. Methods A total of 153 patients diagnosed and treated in the Department of Nephrology from July 2020 to October 2021 were selected as the study objects. According to the staging criteria of diabetic nephropathy and 24-h urinary albumin quantitative level, the patients were divided into control group (35 cases), microalbuminuria group (37 cases), clinical stage albuminuria group (27 cases) and renal failure group (54 cases). Gene expressions were measured by real-time fluorescence quantitative PCR. The correlation was analyzed by Spearman. Serum miR-338-3p and miR-150-5p in the prediction of renal failure in DN was analyzed by ROC curve. Results The levels of urinary albumin and serum creatinine were markedly increased with the increase of DN stage (p < 0.05). Compared with the microalbuminuria group, the expression levels of serum miR-383-3p, serum miR-105-3p, 25(OH)-D, BGP and PINP were obviously decreased, but the expression of parathyroid hormone (PTH) and type I collagen (β-CTX) was largely increased in clinical proteinuria group (p < 0.05). Compared with the clinical proteinuria group, the expression levels of serum miR-383-3p, serum miR-105-3p, 25(OH)-D, BGP and PINP were largely decreased, but the expression of PTH and β-CTX was obviously increased in the renal failure group (p < 0.05). Spearman correlation results showed that serum expressions of miR-383-3p and miR-105-3p were negatively correlated with PTH and β-CTX, and positively correlated with 25(OH)-D, BGP and PINP (p < 0.05). ROC curve analysis showed that the AUC of serum miR-338-3p and miR-150-5p was 0.896 with the specificity and sensitivity of 96.66% and 73.47%, which had certain predictive value for the occurrence of renal failure in DN. Conclusions The expression levels of serum miR-383-3p and miR-105-3p were significantly correlated with bone metabolism markers. The combined test can provide new ideas and insights for the clinical treatment of osteoporosis in DN.

Potential of plasma biomarkers for heart failure prediction, management, and prognosis: A multiomics perspective.

Heart failure (HF) remains a major global health challenge, and more effective and comprehensive plasma biomarkers are needed to effectively treat HF patients. Multiomics studies have shown that DNA fragments, noncoding RNAs, proteins, and metabolites may be potential plasma biomarkers for HF. However, comprehensive reviews that focus on research on plasma biomarkers for HF from an omics perspective are lacking. This review summarizes the applications of various omics approaches in the exploration of biomarkers related to the risk assessment, diagnosis, subtype classification, medical management, and prognosis prediction of HF. Moreover, as heart transplantation and left ventricular assistant device (LVAD) implantation are terminal therapies for end-stage HF patients, this review also discusses the role of cell-free DNA as a biomarker for cardiac transplant rejection and omics studies of plasma biomarkers in patients who respond to LVAD therapy. Our findings suggest that future omics research on HF biomarkers should employ integrated multiomics methods and expand the sample size to increase the robustness of the results and that the identified biomarkers should be further validated in large cohorts.

Simulation-assisted prediction of residual stress-induced failure during powder bed fusion of metals using a laser beam

Simulation-assisted prediction of residual stress-induced failure during powder bed fusion of metals using a laser beam

Residual multiscale attention based modulated convolutional neural network for radio link failure prediction in 5G

In the realm of the 5 G environment, Radio Access Networks (RANs) are integral components, comprising radio base stations communicating through wireless radio links. However, this communication is susceptible to environmental variations, particularly weather conditions, leading to potential radio link failures that disrupt services. Addressing this, proactive failure prediction and resource allocation adjustments become crucial. Existing approaches neglect the relationship between weather changes and radio communication, lacking a holistic view despite their effectiveness in predicting radio link failures for one day. Therefore, the Dynamic Arithmetic Residual Multiscale attention-based Modulated Convolutional Neural Network (DARMMCNN) is proposed. This innovative model considers radio link data and weather changes as key metrics for predicting link failures. Notably, the proposed approach extends the prediction span to 5 days, surpassing the limitations of existing one-day prediction methods. In this, input data is collected from the Radio Link Failure (RLF) prediction dataset. Then, the distance correlation and noise elimination are used to improve the quality and relevance of the data. Following that, the sooty tern optimization algorithm is used for feature selection, which contributes to link failures. Next, a multiscale residual attention modulated convolutional neural network is applied for RLF prediction, and a dynamic arithmetic optimization algorithm is accomplished to tune the weight parameter of the network. The proposed work obtains 79.03 %, 65.93 %, and 67.51 % of precision, recall, and F1-score, which are better than existing techniques. The analysis shows that the proposed scheme is appropriate for RLF prediction.

Graft Failure and Contralateral ACL Injuries After Primary ACL Reconstruction: An Analysis of Risk Factors Using Interpretable Machine Learning.

Anterior cruciate ligament (ACL) reconstruction (ACLR) can be successful in restoring knee stability. However, secondary ACL injury, either through graft failure or contralateral injury, is a known complication and can significantly impact the ability of a patient to return successfully to previous activities. To develop and internally validate an interpretable machine learning model to quantify the risk of graft failure and contralateral ACL injury in a longitudinal cohort treated with ACLR. Case-control study; Level of evidence, 3. An established geographic database of >600,000 patients was used to identify patients with a diagnosis of ACL rupture between 1990 and 2016 with a minimum 2-year follow-up. Medical records were reviewed for relevant patient information and 4 candidate machine learning algorithms were evaluated for prediction of graft failure and contralateral ACL injury in patients after ACLR as identified either on magnetic resonance imaging or via arthroscopy. Performance of the algorithms was assessed through discrimination, calibration, and decision curve analysis. Model interpretability was enhanced utilizing global variable importance plots and partial dependence curves. A total of 1497 patients met inclusion criteria. Among them, 140 (9.4%) had graft failure and 128 (8.6%) had a contralateral ACL injury after index surgery at a median follow-up of 140.7 months (interquartile range, 77.2-219.2 months). The best performing models achieved an area under the receiver operating characteristics curve of 0.70 for prediction of graft failure and 0.67 for prediction of contralateral ACL injury, outperforming a logistic regression fitted on the identical feature set. Notable predictors for increased risk of graft failure included younger age at injury, body mass index (BMI) <30, return to sports <13 months, initial time to surgery >75 days, utilization of allograft, femoral/tibial fixation with suspension/expansion devices, concomitant collateral ligament injury, and active or former smoking history. Predictors of contralateral ACL injury included greater preoperative pain, younger age at initial injury, BMI <30, active smoking history, initial time to surgery >75 days, history of contralateral knee arthroscopies, and involvement in contact sports. Less than 18% of all patients who undergo ACLR should be expected to sustain either a graft failure or contralateral ACL injury. Machine learning models outperformed logistic regression and identified greater preoperative pain, younger age, BMI <30, earlier return to higher activity, and time to surgical intervention >75 days as common risk factors for both graft failure as well as contralateral ACL injury after ACLR. Surgeon-modifiable risk factors for graft failure included allograft and femoral/tibial fixation with a suspension/expansion combination.

Role of Heart Rate, Acidosis, Consciousness, Oxygenation, and Respiratory Rate Score in Predicting Outcomes of Noninvasive Ventilation in Chronic Obstructive Pulmonary Disease Patients.

In patients with chronic obstructive pulmonary disease (COPD), early detection of noninvasive ventilation (NIV) failure is a promising technique for decreasing mortality. The objective of this study was to evaluate the efficacy of heart rate, acidosis, consciousness, oxygenation, and respiratory rate (HACOR) score in predicting NIV outcome in COPD-associated respiratory failure. A prospective observational study was conducted on 100 COPD patients with acute respiratory failure who were initiated on NIV. HACOR score was calculated at the start of NIV and after 1-2, 12, and 24 hours. NIV failure was defined as progression to invasive mechanical ventilation or death. NIV success was defined as liberation from NIV prior to hospital day seven and not meeting criteria for failure. In this study, 100 patients with COPD and respiratory failure were enrolled. Their mean age was 65.34 years [standard deviation (SD) 8.19]. Male patients were predominant (n = 81). Eighty-nine percent of patients were smokers, and the remaining had exposure to biomass fuel. At the initiation of NIV, the median HACOR score was 3 (interquartile: 2, 4). In 13% of patients, there was NIV failure. There were 17 (17%) patients whose HACOR score at initiation was ≥5. In patients with a HACOR score ≥5, the NIV failure rate was 76.4% and mortality was 41.1%. The area under the curve (AUC) for prediction of NIV failure by HACOR score at initiation was 0.980 (p-value < 0.05). The HACOR score had high sensitivity as well as specificity at initiation in the prediction of NIV failure. A higher HACOR score predicts a high chance of NIV failure. Obtaining the HACOR score at the bedside makes it convenient for assessing the efficacy of NIV in patients with COPD.

Predicting crack nucleation in commercially pure titanium using orientation imaging microscopy and machine learning

Due to the prohibitively long experimental and simulation times, dwell fatigue (DF) failure prediction in titanium and its alloys is a challenging task. Since most of these failures have a microstructural level origin, this work focusses on utilizing minimal experiments and machine learning for predicting failure initiation points in a given microstructure. Failure initiation points in commercially pure titanium were identified using interrupted tensile and DF tests. Orientation imaging data was used to train a Random Forest model to calculate the relative importance of various grain orientation-based features to crack nucleation. Subsequently a predictive model for identifying locations that are likely to form a DF crack in a microstructure is developed.

Examining the effect of the shear coefficient on the prediction of progressive failure of fiber-reinforced composites

The ultimate damage of composites under tension usually results from fiber damage, which includes both tensile and shear contributions. In this study, the shear coefficient α of the fiber yarn is incorporated into the failure criterion to consider the shear effect of the fiber yarn. An analytical model is then proposed that combines a homogenization method and the enhanced failure criterion to facilitate quick evaluation of the progressive damage and failure of the composite. The sensitivity of α on the behaviors of progressive damage and failure are comprehensively explored for different types of fiber-reinforced composites, including a laminate, a plain weave composite, a two-dimensional triaxially braided composite, and a three-dimensional woven composite. The results indicate that damage and failure behaviors are generally sensitive to the shear coefficient, and composites with more complex textile structure demonstrates greater sensitivity to the α. An analysis of the sensitivity of α for different failure criteria was also conducted, and the results reveal that the Hashin–Hou criterion shows more sensitivity to α than the Chang–Chang criterion, the Hoffman criterion, or the Tsai–Wu criterion. Therefore, the identification of the shear coefficient is significant for exploring the damage and failure behaviors of fiber-reinforced composites.

Heart Activity Visualization in Embryos with Crown-Rump Length Shorter Than 5 mm and Its Role in Prediction of Early Pregnancy Failure in Patients of Recurrent Early Pregnancy Loss

Heart Activity Visualization in Embryos with Crown-Rump Length Shorter Than 5 mm and Its Role in Prediction of Early Pregnancy Failure in Patients of Recurrent Early Pregnancy Loss

Isolated non-immune-mediated second-degree atrioventricular block in the fetus: natural history and predictive factors for spontaneous recovery.

To determine the clinical course of fetal isolated non-immune-mediated second-degree atrioventricular block (AVB) and the factors associated with spontaneous recovery in these cases. Fetuses with isolated non-immune-mediated second-degree AVB were recruited prospectively between 2014 and 2022. These fetuses were divided into two groups: those which recovered spontaneously and those which did not. Maternal and fetal characteristics and intrauterine and postnatal outcomes were compared between the two groups. The study cohort included 20 fetuses with isolated non-immune-mediated second-degree AVB, diagnosed at a median gestational age of 22.0 (range, 17.0-35.0) weeks. In 12 fetuses, 1:1 atrioventricular conduction was restored spontaneously in utero and there was no recurrence during the postnatal follow-up period. In the remaining eight fetuses, second-degree AVB was maintained and, in six of these, the pregnancy was terminated on parental request. Of the two liveborn children who had persistent second-degree AVB prenatally, one had progressed to complete AVB at the latest follow-up, at the age of 34 months, but was asymptomatic, without heart enlargement or dysfunction. The other child progressed to complete AVB after delivery and was diagnosed with type-2 long QT syndrome. This infant died aged 2 months. Fetuses in the group that recovered spontaneously had earlier gestational age at diagnosis (median, 20.0 (range, 17.0-26.0) vs 24.5 (range, 18.0-35.0) weeks; P = 0.004) and higher atrial rate at diagnosis (median, 147 (range, 130-160) vs 138 (range, 125-149) bpm; P = 0.006) in comparison with the group that did not recover spontaneously. The best cut-off values for prediction of failure to recover spontaneously were 22.5 weeks' gestational age at diagnosis and 144 bpm atrial rate at diagnosis, with sensitivities of 87.5% and 75.0%, respectively, and specificities of 92.0% and 87.5%, respectively. The outcome of 60% of fetuses with isolated non-immune-mediated second-degree AVB was favorable. Earlier gestational age and higher atrial rate at diagnosis were associated with spontaneous reversion to normal sinus rhythm. Prenatal genetic testing should be performed in cases with persistent AVB, to exclude heritable disorders including long QT syndrome. These findings provide important information for clinical management and prenatal counseling in these cases. © 2024 International Society of Ultrasound in Obstetrics and Gynecology.

Progressive degradation behavior and mechanism of lithium-ion batteries subjected to minor deformation damage

Minor deformation damage poses a concealed threat to battery performance and safety. This study delves into the progressive degradation behavior and mechanisms of lithium-ion batteries under minor deformation damage induced by out-of-plane compression. The effects of varying initial states of charge and loading speed on battery degradation are also analyzed. It has been observed that a deformation damage degree as low as 3.1 % can cause a significant transient capacity reduction up to 6.3 %. More transient capacity reduction can occur at higher initial state of charges and loading speed. Additionally, the investigation reveals that the capacity decay rate between the normal cell and cells experiencing deformation damage degree of <4.7 % is almost similar, with a maximum difference of merely 1.887 mAh/cycle and a minimum difference of 0.001 mAh/cycle, both observed over 3000 cycles. Non-destructive and destructive analysis methods are used to investigate degradation behaviors of the cells experiencing minor deformation dagame. It is found that such progressive degradation is primarily driven by the loss of active lithium ions, followed by the loss of cathode and anode active materials. It is anticipated that the findings will offer theoretical underpinnings for advancements in battery damage assessment, early failure prediction, and facilitation of loss adjustment and compensation by insurance agencies.

Predictive Maintenance with Machine Learning: A Comparative Analysis of Wind Turbines and PV Power Plants

The transition to renewable energy requires innovations in new renewable energy sources, such as wind turbines and photovoltaic (PV) systems. Challenges arise in ensuring efficient and reliable performance in their operation and maintenance. Predictive maintenance using machine learning (PdM-ML) is relevant for addressing these challenges by enhancing failure predictions and reducing downtime. This study examines the effectiveness of PdM-ML in wind turbine and PV systems by analyzing operational data, performing data preprocessing, and developing machine learning models for each system. The results indicate that the model for wind turbines can predict failures in critical components such as gearboxes and blades with high accuracy. In contrast, the model for PV systems is effective in predicting efficiency declines in inverters and solar panels. Regarding operational complexity, each model has advantages and disadvantages of its own, but when compared to conventional maintenance techniques, both provide lower costs with greater operational efficiency. In conclusion, machine learning-based predictive maintenance is a promising solution for enhancing the reliability and efficiency of renewable energy systems.

Implementation of machine learning methods in predicting failures in electrical submersible pump machines

The Electric Submersible Pump (ESP) is one of the artificial lift tools widely used in oil and gas wells. Approximately 25% of oil and gas wells have been equipped with ESP. The ESP unit excels in lifting fluid rates much larger than most other types of artificial lift. The purpose of this research is to develop a machine learning model that can predict the likelihood of ESP installation failure. By making predictions at the early stage, necessary actions can be prepared to prevent and anticipate these issues. Thus, the reduction in the amount of produced fluid can be minimized. The model in this study uses 8 input parameters, namely, motor Ampere, Frequency, Pump Intake Pressure, Temperature Motor, Output Volt, Pump Discharge Pressure, Input Voltage, and Motor Horse Power (HP). There are also 8 failure classifications for which the model will be created. The initial stage involves collecting and cleaning raw data and processing it to detect anomalies. Once the data is processed, it proceeds to the model formation and model validation stage. The method used for the model is based on the comparison of two methods, namely, decision tree and k-nearest neighbor. The output of the research is a dashboard that can display visualizations of data and the prediction results from the created model. Millions of data points are used to create a database consisting of 77 wells over the past 2 years. The model developed generates several types of failures that can be read. These failures have their own characteristic parameters. The model obtained has an accuracy rate above 90%. The output of this model includes the most likely failure prediction based on the latest input data, thus effectively addressing well problems, warning of impending failures, reducing failures, and assisting in scheduling ESP repairs and maintenance.

Prediction of micro/meso scale forming limit for metal foils using a simple criterion

Accurately forecasting the forming limit of metal foils is essential in their micro-forming due to the appearance of necking failure easily. In order to accurately and easily forecast the forming limit of metal foils influenced by size effect, an idea for failure modeling of metal foils using the mechanism that different fracture modes of metal foils are related to shear bands is presented in this work. Based on the idea, a simple ductile failure criterion that considers the maximum shear stress and grain size effect but excludes the stress triaxiality is proposed, motivated by the demand to decrease the complexity of parameter calculation tests in micro-forming failure prediction. The proposed criterion and another criterion called as the μ-DF2022 model are applied to capture the forming limit curves of various thick copper and 304 stainless steel foils with different grain sizes to verify its advantage and performance, and the corresponding mechanisms of their prediction capabilities are also elucidated. Furthermore, the proposed and μ-DF2022 models are applied to forecast the limit drawing ratio of a 304 stainless steel foil to further show its performance and advantage in real micro-forming. The applications show that the proposed failure criterion effectively forecasts the forming limit of metal foils between equi-biaxial tension and uniaxial tension influenced by size effect. Moreover, the prediction accuracies using the proposed model and the μ-DF2022 model are comparable, whereas the proposed model does not require complex micro equi-biaxial tension tests, which are typically unavailable to many engineers and researchers, to calibrate its material parameters. Therefore, it is recommended to utilize the proposed criterion to capture the forming limit of metal foils in micro-forming. This work advances the forming limit modeling method of metal foils and provides insight into the application of uncoupled ductile failure criteria in the micro-forming of metal foils, which contributes to the development of their optimal micro-forming processes.

Fatigue life predictions for welded boiler water walls

Boiler water walls experience in-phase thermo-mechanical loading during start-ups and shut-downs, leading to low cycle fatigue (LCF) failure. This study aims at establishing an FEA-based failure prediction method for estimating the fatigue performance and service life of the welded water walls. The developed model is validated for predicting failure in the defect-free uniaxial fatigue specimens. Stress-mechanical strain hysteresis loops and accumulated inelastic strain energy density per cycle parameters are extracted from fatigue tests at 0.4%, 0.6%, and 0.7% strains. A combination of cyclic plasticity and continuous damage mechanics (CDM) theory is utilized to predict fatigue crack initiation sites and estimate the specimen fatigue life. Accumulated damage has been calculated for the life cycle of each specimen. FEA model predicted failure and service life agrees well with the experimental results. The established failure analysis parameters are then transferred from the specimen level to the water wall component level, thereby estimating the service life of defect-free water walls at 750 cycles.

Risk Stratification and Management of Acute Respiratory Failure in Patients With Neuromuscular Disease.

Guillain-Barré syndrome (GBS) and myasthenia gravis (MG) are the most common causes of acute neuromuscular respiratory failure resulting in ICU admission. This synthetic narrative review summarizes the evidence for the prediction and management of acute neuromuscular respiratory failure due to GBS and MG. We searched PubMed for relevant literature and reviewed bibliographies of included articles for additional relevant studies. English-language publications were reviewed. Data regarding study methodology, patient population, evaluation metrics, respiratory interventions, and clinical outcomes were qualitatively assessed. No single tool has sufficient sensitivity and specificity for the prediction of acute neuromuscular respiratory failure requiring mechanical ventilation. Multimodal assessment, integrating history, examination maneuvers (single breath count, neck flexion strength, bulbar weakness, and paradoxical breathing) and pulmonary function testing are ideal for risk stratification. The Erasmus GBS Respiratory Insufficiency Score is a validated tool useful for GBS. Noninvasive ventilation can be effective in MG but may not be safe in early GBS. Airway management considerations are similar across both conditions, but dysautonomia in GBS requires specific attention. Extubation failure is common in MG, and early tracheostomy may be beneficial for MG. Prolonged ventilatory support is common, and good functional outcomes may occur even when prolonged ventilation is required. Multimodal assessments integrating several bedside indicators of bulbar and respiratory muscle function can aid in evidence-based risk stratification for respiratory failure among those with neuromuscular disease. Serial evaluations may help establish a patient's trajectory and to determine timing of respiratory intervention.

Industrial IoT Sensor Data Federation in an Enterprise for an Early Failure Prediction

Industrial IoT Sensor Data Federation in an Enterprise for an Early Failure Prediction

Prediction Method for Mechanical Characteristic Parameters of Weak Components of 110 kV Transmission Tower under Ice-Covered Condition Based on Finite Element Simulation and Machine Learning

Icing on transmission lines may cause damage to tower components and even lead to structural failure. Aiming at the lack of research on predicting mechanical characteristic parameters of weak components of transmission towers, and the cumbersome steps of building a finite element model (FEM), the study of prediction for mechanical characteristic parameters of weak components of towers based on a finite element simulation and machine learning is proposed. Firstly, a 110 kV transmission tower in a heavily iced area is taken as an example to establish its FEM. The locations of the weak components are analyzed, and the accuracy of FEM is verified. Secondly, meteorological and terrain parameters are considered as input parameters of the prediction model. The axial stresses and nodal displacements of four weak components are selected as output parameters. The FEM of the 110 kV transmission tower is used to obtain input and output datasets. Thirdly, five machine learning algorithms are considered to establish the prediction models for mechanical characteristic parameters of weak components, and the optimal prediction model is obtained. Finally, the accuracy of the prediction method is verified through an actual tower collapse case. The results show that ACO-BPNN is the optimal model that can accurately and quickly predict the mechanical characteristic parameters of the weak components of the transmission tower. This study can provide an early warning for the failure prediction of transmission towers in heavily iced areas, thus providing an important reference for their safe operation and maintenance.

Research on Failure Pressure Prediction of Water Supply Pipe Based on GA-BP Neural Network

The water supply pipeline is regarded as the “lifeline” of the city. In recent years, pipeline accidents caused by aging and other factors are common and have caused large economic losses. Therefore, in order to avoid large economic losses, it is necessary to analyze the failure prediction of pipelines so that the pipelines that are going to fail can be replaced in a timely manner. In this paper, we propose a method for predicting the failure pressure of pipelines, i.e., a genetic algorithm was used to optimize the weights and thresholds of a BP neural network. The first step was to determine the topology of the neural network and the number of input and output variables. The second step was to optimize the weights and thresholds initially set for the back propagation neural network using a genetic algorithm. Finally, the optimized back-propagation neural network was used to simulate and predict pipeline failures. It was proved by examples that compared with the separate back propagation neural network model and the optimized and trained genetic algorithm-back propagation neural network, the model performed better in simulation prediction, and the prediction accuracy could reach up to 91%, whereas the unoptimized back propagation neural network model could only reach 85%. It is feasible to apply this model for fault prediction of pipelines.

Optimization of multidimensional feature engineering and data partitioning strategies in heart disease prediction models

The relentless rise in heart disease incidence, a leading global cause of death, presents a significant public health challenge. Precise prediction of heart disease risk and early interventions are crucial. This study investigates the performance improvement of heart disease prediction models using machine learning and deep learning algorithms. Initially, we utilized the Heart Failure Prediction Dataset from Kaggle. After preprocessing to ensure data quality, three distinct feature engineering techniques were applied: PCA for dimensionality reduction, ET for feature selection, and Pearson's correlation coefficient for feature selection. We assessed their impact on model performance. The dataset was then partitioned into three different data split ratios—1:9, 2:8, and 3:7—to determine their specific effects on model performance. Twelve machine learning classifiers—LGBM, Adaboost, XGB, RF, DT, KNN, LR, GNB, ET, SVC, GB, and Bagging—were trained and evaluated based on five key metrics: accuracy, recall, precision, F1 score, and training time. The influence of different feature engineering methods and data partitioning ratios on model performance were systematically analyzed using paired-sample t-tests. Among the feature engineering methods compared, the Bagging classifier, when combined with feature selection via ET, exhibited superior performance. It achieved an accuracy of 97.48 % and an F1-Score of 97.48 % with a data split ratio of 1:9 between the test and training sets. With a 2:8 split, the accuracy was 94.96 % and the F1-Score was 94.95 %. For a 3:7 split, the accuracy was 94.12 % and the F1-Score was 94.11 %. Paired sample T-test results indicate that feature selection using Pearson correlation coefficient can shorten training duration, but this also leads to a decline in classifier performance. After applying PCA dimensionality reduction, compared with the control group, there was no significant difference in the training efficiency and efficacy of the classifier. However, feature selection through ET significantly reduced the training time for various classifiers while ensuring their performance.