XGBoost Algorithm Research Articles

Optimization of big data analysis resources supported by XGBoost algorithm: Comprehensive analysis of industry 5.0 and ESG performance

To enable state-owned enterprises in Industry 5.0 to better carry out M&A activities, it is important and necessary to provide early warning of M&A risks, which directly affects the interests of both parties and even affects the effectiveness of state-owned enterprise reform. The author proposes the optimization of big data analysis resources supported by the XGBoost algorithm: a comprehensive analysis of Industry 5.0 and ESG performance. Design a comprehensive evaluation system to measure the M&A risk of state-owned listed companies. Using Python programming language to achieve data crawling and processing. Build an early warning model using the XGBoost algorithm. To further evaluate the effectiveness of the early warning model, comparative experiments were conducted. Using multiple linear regression models to study the significant factors of merger and acquisition risk. The experimental results show that the prediction accuracy based on the XGBoost algorithm is 80 %, which performs the best among all models and has stronger reliability and applicability. ConclusionThe return on investment capital, operating profit margin, and net profit from paid consideration are more important and effective in predicting merger and acquisition risks; The total asset turnover rate, return on investment capital, equity balance, and audit quality are more conducive to suppressing merger and acquisition risks.

Research on Status Assessment and Operation and Maintenance of Electric Vehicle DC Charging Stations Based on XGboost

With the rapid development of electric vehicles, the infrastructure for charging stations is also expanding quickly, and the failure rate of charging piles is increasing. To address the effective operation and maintenance of charging stations, a method based on the XGBoost algorithm for electric vehicle DC charging stations is proposed. An operation and maintenance system is constructed based on state analysis, considering the operational status of the charging stations and users’ charging habits. Factors such as driving and charging habits, road traffic, and charging station equipment are taken into account. The training sample data are established using historical data, online monitoring data, and external environmental data, and the charging station status evaluation model is trained using the XGBoost algorithm. Based on the condition assessment results, a risk assessment model is established in combination with fault parameters. Risk tracking of the charging stations is conducted using the energy not charged (ENC), evaluating the risk level of each station and determining the operation and maintenance order. The optimal operation and maintenance model for DC charging stations, aimed at achieving both economic and reliability goals, is constructed to determine the operation and maintenance schedule for each station. The results of the case study demonstrate that the state evaluation and operation and maintenance strategy can significantly improve the reliability of the system and the overall benefits of operation and maintenance while meeting the required standards.

Morphometric assessment and soil erosion susceptibility maping using ensemble extreme gradient boosting (XGBoost) algorithm: a study for Hunza-Nagar catchment, Northern Pakistan

Morphometric assessment and soil erosion susceptibility maping using ensemble extreme gradient boosting (XGBoost) algorithm: a study for Hunza-Nagar catchment, Northern Pakistan

Detecting event-related driving anger with facial features captured by smartphones

Driving anger is a serious global issue that poses risks to road safety, thus necessitating the development of effective detection and intervention methods. This study investigated the feasibility of using smartphones to capture facial expressions to detect event-related driving anger. Sixty drivers completed the driving tasks in scenarios with and without multi-stage road events and were induced to angry and neutral states, respectively. Their physiological signals, facial expressions, and subjective data were collected. Four feature combinations and six machine learning algorithms were used to construct driving anger detection models. The model combining facial features and the XGBoost algorithm outperformed models using physiological features or other algorithms, achieving an accuracy of 87.04% and an F1-score of 85.06%. Eyes, mouth, and brows were identified as anger-sensitive facial areas. Additionally, incorporating individual characteristics into models further improved classification performance. This study provides a contactless and highly accessible approach for event-related driving anger detection. Practitioner Summary: This study proposed a cost-effective and contactless approach for event-related and real-time driving anger detection and could potentially provide insights into the design of emotional interactions in intelligent vehicles.

Identification of Disc Cutter Wear via Operation Parameters Combined With Vibration Data: A Case Study

ABSTRACTThis paper proposed an approach to estimate disc cutter wear utilizing a combination of multiple operational parameters and vibration data collected during shield tunneling operations. The incorporation of vibration signals, notably those originating from acceleration sensors mounted on the back plate of the soil chamber, has markedly enhanced the accuracy of the model. Time‐frequency domain features were extracted through analysis methods such as Fast Fourier Transform (FFT), Short‐Time Fourier Transform (STFT), and Continuous Wavelet Transform (CWT). A predictive model utilizing vibration and shield operation parameters was developed using the XGBoost algorithm, and a deep GoogLeNet Convolutional Neural Network (CNN) was trained on time‐frequency graphs from the CWT. In addition, this study also investigated the impact of signal duration on wavelet image information and model accuracy. In the Huang‐Shang Intercity Railway Project, the approach effectively assessed disc cutter wear during tunneling operations and dynamically optimized the operational parameters of the shield tunnel machine through predictive analysis.

Landscape of the immune infiltration and identification of molecular diagnostic markers associated with immune cells in patients with kidney transplantation

Rejection seriously affects the success of kidney transplantations. However, the molecular mechanisms underlying this rejection remain unclear. The GSE21374 and GSE36059 datasets were downloaded from the Gene Expression Omnibus (GEO) database. Next, the Cell-type Identification by Estimating Relative Subsets of RNA Transcripts (CIBERSORT) algorithm was used to infer the proportions of 22 immune cells. Moreover, infiltrating immune cell-related genes were identified using weighted gene co-expression network analysis (WGCNA), and enrichment analysis was conducted to observe their biological functions. Extreme Gradient Boosting (XGBoost) and Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression algorithms were used to screen hub genes. Quantitative real-time PCR was conducted to verify the number of immune cells and hub gene expression levels. The rejection and non-rejection groups showed significantly different distributions (P < 0.05) of eight immune cells (B cell memory, Plasma cells, mast cells, follicular helper T cells, T CD8 cells, Macrophages M1, T Cells CD4 memory activated, and gamma delta T cells). Subsequently, CD8A, CRTAM, GBP2, WARS, and VAMP5 were screened as hub genes using the XGBoost and LASSO algorithms and could be used as diagnostic biomarkers. Finally, differential analysis and quantitative real-time PCR suggested that CD8A, CRTAM, GBP2, WARS, and VAMP5 were upregulated in rejection samples compared to non-rejection samples. The present study identified five key infiltrating immune cell-related genes (CD8A, CRTAM, GBP2,WARS, and VAMP5) involved in kidney transplant rejection, which may explain the molecular mechanism of rejection in kidney transplantation development.

Using machine learning for the assessment of ecological status of unmonitored waters in Poland

Advancements in Artificial Intelligence (AI) technology allow for development of new tools for analytics and management which present new opportunities in field of environmental protection. The following study showcases usage of Machine Learning (ML) techniques as a complementary method for water status assessment of water bodies. Since the main goal of Water Framework Directive (WFD) is to improve the quality of water and reach good status in all the water bodies across Europe intensive monitoring program was launched together with water status assessment procedure. Based on requirements of the European Union’s WFD concerning ecological status assessment it is presented how ML can be used for assessment of Polish unmonitored river water bodies. Due to the absence of monitoring data, the foremost challenge lay in securing relevant alternative data which was set to be anthropogenic pressures. The pivotal solution was implementation of ML techniques which enable processing of seemingly unrelated information concerning pressures in the catchment. Decision Tree, Random Forest, KNN, Support Vector Machine, Multinomial Naive Bayes, XGBoost models have been tested and the results indicated most suitable techniques. Study shows highest efficiency of XGBoost and Random Forest algorithms for classification of unmonitored water bodies. The models were compared by their overall accuracy (OA) reaching approximately 93% for binary classification and 72% for comprehensive classification as well as partial class accuracies and the Probability of Misclassification (PoM) parameter. The analyses demonstrates a practical application of AI in assessment of unmonitored water bodies in case of binary classification used for reporting water status objectives of WFD as well as possible usage of full classification for planning and operational uses. OA and PoM are postulated as the best measures of goodness of classification.

Boosting Algorithms for the Accident Severity Classification

&lt;div&gt;&lt;i&gt;Background:&lt;/i&gt; Road accident severity estimation is a critical aspect of road safety analysis and traffic management. Accurate severity estimation contributes to the formulation of effective road safety policies. Knowledge of the potential consequences of certain behaviors or conditions can contribute to safer driving practices. Identifying patterns of high-severity accidents allows for targeted improvements in terms of overall road safety. &lt;i&gt;Objective:&lt;/i&gt; This study focuses on analyzing road accidents by utilizing real data, i.e., US road accidents open database called “CRSS.” It employs advanced machine learning models such as boosting algorithms such as LGBM, XGBoost, and CatBoost to predict accident severity classification based on various parameters. The study also aims to contribute to road safety by providing predictive insights for stakeholders, functional safety engineering community, and policymakers using KABCO classification systems. The article includes sections covering theoretical methodology, data analysis, model development, evaluation, performance metrics, and implications for improving road safety measures by comparing the performance of different boosting algorithms on the CRSS dataset. This study aims to identify the most effective machine learning algorithm to integrate into our product line in the near future, enabling accurate prediction of both accident severity and occurrence. &lt;i&gt;Results and Conclusions:&lt;/i&gt; This study addresses challenges in evaluating performance metrics for different severity classes within unbalanced datasets, emphasizing the impact of dominant classes like Class O (O = no apparent injury) on overall accuracy. The investigation reveals the limitations and conservatism associated with imbalanced data in boosting models, hinting at a potential ceiling in their performance around 80%. Comparative analysis of algorithms, including CatBoost, XGBoost, and LGBM, demonstrates comparable performance even in the case of applying KNN algorithm for pre-processing, based on various metrics, especially accuracy, &lt;i&gt;F&lt;/i&gt;&lt;sub&gt;1&lt;/sub&gt;-score, ROC-AUC, and PR-AUC for all severity classes. XGBoost with KNN algorithm did not show any significant performance improvement compared to the XGBoost without KNN algorithm. The study includes performance metrics, such as &lt;i&gt;F&lt;/i&gt;&lt;sub&gt;1&lt;/sub&gt;-score, CM upper triangle, ROC-AUC, and PR-AUC applied to an accident analysis case study. Future work directions involve extending the application of CatBoost, XGBoost, and other algorithms to diverse datasets, exploring the capabilities of deep neural networks, refining dataset preparation for accuracy improvement, and creating unified tools for hazard analysis and risk assessment.&lt;/div&gt;

Clinically Guided Adaptive Machine Learning Update Strategies for Predicting Severe COVID-19 Outcomes

Background: Machine learning algorithms are essential for predicting severe outcomes during public health crises like COVID-19. However, the dynamic nature of diseases requires continual evaluation and updating of these algorithms. This study aims to compare three update strategies for predicting severe COVID-19 outcomes post-diagnosis: 'naive' (a single initial model), 'frequent' (periodic retraining), and 'context-driven' (retraining informed by clinical insights). The goal is to determine the most effective timing and approach for adapting algorithms to evolving disease dynamics and emerging data. Methods: A dataset of 1.11 million COVID-19 patients from diverse U.S. regions was used to develop and validate an XGBoost algorithm for predicting severe outcomes upon diagnosis. Data included patient demographics, vital signs, comorbidities, and immunity-related factors (prior infection and vaccination status) from January 2007 to November 2021. The study analyzed the performance of the three update strategies from March 2020 to November 2021. Results: Predictive features changed over the pandemic, with comorbidities and vitals being significant initially, and geography, demographics, and immunity-related variables gaining importance later. The 'naive' strategy had an average AUC of 0.77, the 'frequent' strategy-maintained stability with an average AUC of 0.81, and the 'context-driven' strategy averaged an AUC of 0.80, outperforming the 'naive' strategy and aligning closely with the 'frequent' strategy. Conclusion: A context-driven approach, guided by clinical insights, can enhance predictive performance and offer cost-effective solutions for dynamic public health challenges. These findings have significant implications for efficiently managing healthcare resources during evolving disease outbreaks.

Predicting the Risk of Loneliness in Children and Adolescents: A Machine Learning Study.

Loneliness is increasingly emerging as a significant public health problem in children and adolescents. Predicting loneliness and finding its risk factors in children and adolescents is lacking and necessary, and would greatly help determine intervention actions. This study aimed to find appropriate machine learning techniques to predict loneliness and its associated risk factors among schoolchildren. The data were collected from an ongoing prospective puberty cohort that was established in Chongqing, Southwest China. This study used 822 subjects (46.84% boys, age range: 11-16) followed in 2019. Five models, (a) random forest, (b) extreme gradient boosting (XGBoost), (c) logistic regression, (d) neural network, and (e) support vector machine were applied to predict loneliness. A total of 39 indicators were collected and 28 predictors were finally included for prediction after data pre-processing, including demographic, parental relationship, mental health, pubertal development, behaviors, and environmental factors. Model performance was determined by accuracy and AUC. Additionally, random forest and XGBoost were applied to identify the important factors. The XGBoost algorithm with SHAP was also used to interpret the results of our ML model. All machine learning performed with favorable accuracy. Compared to random forest (AUC: 0.87 (95%CI: 0.80, 0.93)), logistic regression (AUC: 0.80 (95%CI: 0.70, 0.89)), neural network (AUC: 0.80 (95%CI: 0.71, 0.89)), and support vector machine (AUC: 0.79 (95%CI: 0.79, 0.89)), XGBoost algorithm had the highest AUC values 0.87 (95%CI: 0.80, 0.93) in the test set, although the difference was not significant between models. Peer communication, index of general affect, peer alienation, and internet addiction were the top four significant factors of loneliness in children and adolescents. The results of this study suggest that machine learning has considerable potential to predict loneliness in children. This may be valuable for the early identification and intervention of loneliness.

MATHEMATICAL MODELLING OF SURVIVAL IN LOW GRADE GLIOMAS AT MALIGNANT TRANSFORMATION WITH XGBOOST

Abstract AIMS To develop non-linear machine learning models using the XGBoost algorithm to predict a continuous (overall survival (OS) and a binary survival outcome (OS &amp;gt; 5 years) using clinical, molecular and genetic, and radiomic data. METHOD Patients with LGGs treated at a single institution (2005-2020) with histology and MRIs at the time of malignant transformation (MT) were retrospectively included in this study. MRIs underwent in-house tumour segmentation pipeline with radiomic feature extraction of whole-tumour, enhancing, non-enhancing and oedema components, and masked disconnectome map components. Patients were split into training and testing sets for the development of the survival models, which were assessed with mean absolute error (MAE) and root mean square error (RMSE) for the prediction of OS; and receiver operating characteristics analysis for the prediction of OS &amp;gt; 5 years. RESULTS Of 553 patients, 415 patients were included in the training set and 138 patients in the testing set. The XGB Regressor model was able to predict overall survival (OS) from the time of malignant transformation (tMRI) with an MAE of 953 days (RMSE: 1163 days). The XGB Classifier model was able to predict the probability of OS &amp;gt; 5 years from tMRI with an accuracy of 64% (sensitivity: 58%, specificity: 70%). Age, IDH1 mutation, 1p/19q co- deletion, regularity of tumour shape, and disconnectome-related perilesional components were most predictive of survival outcome. CONCLUSION This study has investigated the predictive capabilities of clinical, molecular and genetic, and radiomic data to develop survival analysis models, using XGBoost, to predict OS and OS &amp;gt; 5 years in patients with LGG at tMRI. We corroborate previous findings that age, 1p/19q co-deletion and IDH1 mutation are positive prognosticators for survival. However, further investigation into the radiomics of the disconnectome, especially of the perilesional oedema compartment, presents an intriguing and novel avenue for survival analysis of patients with LGG.

Conversion of hazardous waste into thermal conductive polymer: A prediction and guidance from machine learning

The preparation methods and thermal conductivity (TC) of the reported thermal conductive polymers vary significantly. A method to clarify the relationship between TC and influencing factors and to reach consistent conclusions is needed. In this study, we compiled 403 sets of data from the literature. Six typical features and three machine learning (ML) algorithms were selected and optimized. XGBoost algorithm achieved the best prediction of TC of thermal conductive polymer (correlation coefficient with 0.855). To further investigate the influence of the 6 features on the TC of thermal conductive polymer, we conducted the SHapley Additive exPlanations (SHAP) analysis. Based on the above results, pyrrhotite tailings were determined as the filler and the corresponding process parameters were also determined. However, the above model built based on literature was still unsatisfactory. We further optimized XGBoost and built XGBoost-Exp through data from the real experiment. Finally, a small percentage (23%) of real experimental data can significantly improve the prediction power of XGBoost-Exp for unseen data (correlation coefficient with 0.815). To summarize, XGBoost-Exp exhibits exceptional predictive performance for the TC of the unseen data, offering valuable insights into the influence of various features. Meanwhile, this method provides a new perspective for the utilization of hazardous sulfide minerals.

Trajectory tracking multi-constraint model predictive control of unmanned vehicles based on sideslip stiffness estimation with XGBoost algorithm

When the vehicle is driving at high speed on a slippery road, the sideslip stiffness of the tire which is closely related to the lateral force of the tire, will vary with the change of road conditions, tire inflation pressure, vertical load, and other factors. If the tire sideslip stiffness is set to a fixed value in the control system based on the model design, the uncertainty of the sideslip stiffness will cause a large error with the actual application. Therefore, in order to improve the trajectory tracking accuracy of the vehicle on the slippery road surface under the premise of ensuring the stability of the vehicle, an intelligent vehicle trajectory tracking control strategy considering the influence of sideslip stiffness is designed in this paper. In order to solve the multiple constraints of the vehicle driving on the low-adhesion road surface, a trajectory tracking controller based on the multi-constraint model predictive control algorithm is designed, and then the tire sideslip stiffness estimation strategy is designed based on the XGBoost algorithm, and the estimated sideslip deviation stiffness is added to the trajectory tracking control model. Carsim and MATLAB/Simulink are used to perform co-simulation to verify the accuracy of the proposed tire sideslip stiffness estimation and the tracking performance of the trajectory tracking controller. In order to further verify the reliability of the research content, the relevant working condition tests are carried out on the hardware-in-the-loop platform based on Carsim and LabVIEW, and the effectiveness of the trajectory tracking controller considering the influence of sideslip stiffness is verified.

XAI-Augmented Voting Ensemble Models for Heart Disease Prediction: A SHAP and LIME-Based Approach.

Ensemble Learning (EL) has been used for almost ten years to classify heart diseases, but it is still difficult to grasp how the "black boxes", or non-interpretable models, behave inside. Predicting heart disease is crucial to healthcare, since it allows for prompt diagnosis and treatment of the patient's true state. Nonetheless, it is still difficult to forecast illness with any degree of accuracy. In this study, we have suggested a framework for the prediction of heart disease based on Explainable artificial intelligence (XAI)-based hybrid Ensemble Learning (EL) models, such as LightBoost and XGBoost algorithms. The main goals are to build predictive models and apply SHAP (SHapley Additive expPlanations) and LIME (Local Interpretable Model-agnostic Explanations) analysis to improve the interpretability of the models. We carefully construct our systems and test different hybrid ensemble learning algorithms to determine which model is best for heart disease prediction (HDP). The approach promotes interpretability and transparency when examining these widespread health issues. By combining hybrid Ensemble learning models with XAI, the important factors and risk signals that underpin the co-occurrence of heart disease are made visible. The accuracy, precision, and recall of such models were used to evaluate their efficacy. This study highlights how crucial it is for healthcare models to be transparent and recommends the inclusion of XAI to improve interpretability and medical decisionmaking.

ECG signal classification based on DWT denoising and XGBoost

Electrocardiogram signal (ECG) can directly reflect the health status of the heart, and is an important basis for prevention and treatment of heart disease. In order to realize ECG signal classification effectively, an ECG signal classification method based on discrete wavelet transform and Xgboost is proposed in this paper, which improves the accuracy of ECG signal classification. Specifically, we first divide, select and downsample the heart beat of the data, and then use the discrete wavelet transform to reduce the noise of the data set to improve the signal to noise ratio. Finally, we use Xgboost algorithm as the classifier to classify the data, and get 98.7% accuracy rate on the test set. In each module, we carried out comparative experiments to verify the correctness and rigor of our method. In addition, in order to make up for the lack of interpretability of traditional machine learning methods, we defined the importance of each feature according to the information gain generated by different features to the model during the training of XGBoost, and then got the key bands that should be paid attention to when distinguishing heart beats, which improved the interpretability of the model. It also provides a scientific basis for the classification of ECG signals and practical medical work.

Predictive and experimental assessment of chloride ion permeation in concrete subjected to multi-factorial conditions using the XGBoost algorithm

Chloride ions infiltrate concrete structures, causing corrosion of the steel reinforcement, which creates concrete spalling and decreases load-bearing capacity, ultimately leading to structural failure. Thus, it is essential to comprehend the diffusion process of chloride ions in concrete. Current models used to predict the chloride ion diffusion in concrete are hindered by poor accuracy due to their simplistic consideration of variables and the complex interplay of environmental and material factors affecting key parameters such as surface chloride concentration (Cs) and the chloride diffusion coefficient (D). These influences are challenging to capture with simple linear or non-linear relationships, and traditional machine learning models often overfit training data and underperform with new data. To address these challenges, this study presents physical model experiments conducted to explore the diffusion process of chloride ions under multi-field coupling conditions, examining chloride ion concentrations across different concrete layers under varying environmental temperatures (T), humidities (h), erosion times (t), water-cement ratios (W/C), and volumes of coarse aggregates (v). This study reveals the distribution patterns of chloride ions within concrete layers. An XGBoost machine learning predictive model was developed using environmental temperature, humidity, erosion time, water-cement ratio, and coarse aggregate volume as input variables, with Cs and D as output variables. The results show that when the water-cement ratio reaches 0.5 in high humidity, the SHAP value rises to 0.015, enhancing chloride diffusion. As erosion time exceeds 200 days and temperature surpasses 38 °C, the SHAP value peaks at 0.02. Additionally, when coarse aggregate volume is between 0.45 and 0.60, temperature changes have little effect on Cs. Additionally, a graphical user interface was developed for modeling Cs and D to enhance practical usability.

Prediction of carbon dioxide levels in the European Alps based on machine learning algorithms

With the rapid development of world industrialization, the continuous increase of global carbon dioxide emissions has led to the gradual deterioration of the ecological environment and the obvious aggravation of the greenhouse effect. In this paper, the carbon dioxide content in the air over the European Alps is taken as the research object, and the RNN and LSTM neural network prediction models are respectively used to compare and predict it. The results show that the fitting effect of LSTM is better than that of RNN, and the fitting effect of the prediction model will also improve with the increase of iteration times and sample size. Since carbon monoxide and methane in the air will cause changes in carbon dioxide content, this paper adds the two factors into the LSTM prediction model as influencing factors, and the goodness-of-fit can reach 0.95, which is higher than the prediction results when there are only one influencing factor or no influencing factor. In order to reduce the running time, XGBoost, LightGBM and random forest algorithms are respectively used in this paper and Bayesian optimization algorithm is used to predict the carbon dioxide content. The results show that the prediction effect is slightly lower than LSTM. Therefore, this paper takes the above three algorithms as the base model. Linear regression experiments are carried out for the meta-model's Stacking fusion algorithm. The goodness-of-fit can reach 0.92, which significantly improves the prediction effect compared with the base model. Finally, the sensitivity analysis of the Stacking fusion model is carried out in this paper. The experimental results show that the model has strong stability.

Prediction of Ionospheric Scintillations Using Machine Learning Techniques during Solar Cycle 24 across the Equatorial Anomaly

Ionospheric scintillation is a pressing issue in space weather studies due to its diverse effects on positioning, navigation, and timing (PNT) systems. Developing an accurate and timely prediction model for this event is crucial. In this work, we developed two machine learning models for the prediction of ionospheric scintillation events at the equatorial anomaly during the maximum and minimum phases of solar cycle 24. The models developed in this study are the Random Forest (RF) algorithm and the eXtreme Gradient Boosting (XGBoost) algorithm. The models take inputs based on the solar wind parameters obtained from the OMNI Web database from the years 2010–2017 and Pc5 wave power obtained from the Bear Island (BJN) magnetometer station. We retrieved data from the Scintillation Network and Decision Aid (SCINDA) receiver in Egypt from which the S4 index was computed to quantify amplitude scintillations that were utilized as the target in the model development. Out-of-sample model testing was performed to evaluate the prediction accuracy of the models on unseen data after training. The similarity between the observed and predicted scintillation events, quantified by the R2 score, was 0.66 and 0.74 for the RF and XGBoost models, respectively. The corresponding Root Mean Square Errors (RMSEs) associated with the models were 0.01 and 0.01 for the RF and XGBoost models, respectively. The similarity in error shows that the XGBoost model is a good and preferred choice for the prediction of ionospheric scintillation events at the equatorial anomaly. With these results, we recommend the use of ensemble learning techniques for the study of the ionospheric scintillation phenomenon.

A Machine Learning-Based Algorithm for the Prediction of Eigenfrequencies of Railway Bridges

As part of the development of advanced, data-driven methods for predictive maintenance of railway infrastructure, this paper analyzes and evaluates more realistic predictions of eigenfrequencies of railway bridges, also referred to as natural frequencies, based on a population of already assessed, measured existing bridges using regression techniques. For this purpose, Machine Learning (ML) techniques such as Polynomial Regression (PR), ANN and XGBoost are consistently evaluated and the application of the XGBoost algorithm is identified as the most suitable prediction model for these eigenfrequencies, usable for dynamic train-bridge interactions. The results of the post-processing are incorporated into the safety architecture for bridge verification (risk management). The presented data-based techniques are a steppingstone towards digitalization of structural health monitoring and offer safety and longevity of the railway bridges. Furthermore, the use of these methods can save costs that would be incurred by physical in-situ measurements. The types of bridges analyzed with ML are Filler Beam Bridges (FBE), which outnumber other construction types of bridges in Germany (DB InfraGO AG). This methodology is applicable to any bridge type as long as sufficient data are gathered for training, validation and testing.

Identifying fatigue of climbing workers using physiological data based on the XGBoost algorithm.

High-voltage workers often experience fatigue due to the physically demanding nature of climbing in dynamic and complex environments, which negatively impacts their motor and mental abilities. Effective monitoring is necessary to ensure safety. This study proposed an experimental method to quantify fatigue in climbing operations. We collected subjective fatigue (using the RPE scale) and objective fatigue data, including systolic blood pressure (SBP), diastolic blood pressure (DBP), blood oxygen saturation (SpO2), vital capacity (VC), grip strength (GS), response time (RT), critical fusion frequency (CFF), and heart rate (HR) from 33 high-voltage workers before and after climbing tasks. The XGBoost algorithm was applied to establish a fatigue identification model. The analysis showed that the physiological indicators of SpO2, VC, GS, RT, and CFF can effectively evaluate fatigue in climbing operations. The XGBoost fatigue identification model, based on subjective fatigue and the five physiological indicators, achieved an average accuracy of 89.75%. This study provides a basis for personalized management of fatigue in climbing operations, enabling timely detection of their fatigue states and implementation of corresponding measures to minimize the likelihood of accidents.