Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 18 of 18 for “"xg-boost"”.

  1. Solar Irradiance Prediction Using Xg-boost With the Numerical Weather Forecast

    To defeat global warming, the world expects to look at renewable energy sources. Solar energy is one of the best renewable energy sources which causes no harm to the environment. As solar energy changes with atmospheric parameters like temperature, relative humidity, cloud coverage, dewpoint, sun …

    utahstate Repository record for Solar Irradiance Prediction Using Xg-boost With the Numerical Weather Forecast (opens in a new tab)

  2. CODE FOR CARE: HYPERTENSION PREDICTION IN WOMEN AGED 18-39 YEARS

    … including Decision Tree, Random Forest, and XG Boost results in weighted recall values of 81.73%, 90.26%, and 90.14% respectively. (Q3.) A SHAP value analysis on the 3 tree-based machine learning algorithms produced the top 20 most influential features for each, Decision Tree, Random Forest, …

    csusb Repository record for CODE FOR CARE: HYPERTENSION PREDICTION IN WOMEN AGED 18-39 YEARS (opens in a new tab)

  3. Πρόβλεψη εξάπλωσης πυρκαγιάς με γνώμονα την Τεχνητή Νοημοσύνη

    … και συγκρίσεων κατέληξε στην επιλογή ενός XG-Boost μοντέλου. Τα πιο κλασικά μοντέλα, όπως το logistic ή ένα Random forest υπέκυψαν σε θέματα μεροληψίας. Η κατανόηση των δεδομένων που έδειξαν, με οριακά μηδενικά θετικά αποτελέσματα, οδήγησε στον αποκλεισμό τους. Οι ακρίβειες τους ήταν …

    athens Repository record for Πρόβλεψη εξάπλωσης πυρκαγιάς με γνώμονα την Τεχνητή Νοημοσύνη (opens in a new tab)

  4. Recommendation System using machine learning for fertilizer prediction

    … (SVM), Artificial Neural Networks (ANN), and XG-Boost, were implemented to facilitate the prediction process. Through comprehensive experimentation and evaluation, we assessed the performance of each algorithm in accurately predicting the best fertilizer for maximizing crop yield. The project …

    csusb Repository record for Recommendation System using machine learning for fertilizer prediction (opens in a new tab)

  5. Decision Support for Energy Efficiency Operations of Double Ended Ferry

    … Furthermore, a full black box machine learning XG Boost model-based simulator was built in order to forecast the total fuel consumption for a trip, given the meteocean conditions and some engine-related initial conditions (IC), on the assumption that the speed overground and the route remains …

    chalmers Repository record for Decision Support for Energy Efficiency Operations of Double Ended Ferry (opens in a new tab)

  6. Advanced CNN architecture integrating machine learning algorithms for precise Alzheimer's disease classification

    … conventional machine learning algorithms like XG Boost, k-nearest neighbor (KNN), and Random Forest. The innovative CNN architecture is meticulously designed to maximize classification accuracy. The preprocessing steps involve resizing fMRI images to 109x91 pixels and labeling them accordingly. …

    regina Repository record for Advanced CNN architecture integrating machine learning algorithms for precise Alzheimer's disease classification (opens in a new tab)

  7. Football By the Numbers: A Look Into Sports Analytics Currently Used in the National Football League

    … learning algorithms: logistic regression, XG Boost, decision trees, and time series, to analyze the NFL data, both tracking data from the first six weeks of the 2020 season as well as play by play data from 1999 to 2022 to introduce these new algorithms to sports analytics community.

    ucf Repository record for Football By the Numbers: A Look Into Sports Analytics Currently Used in the National Football League (opens in a new tab)

  8. Exploring feasibility of AI-driven insights for decision making in an e-commerce environment

    … evaluates two distinct machine learning models: XG Boost and NeuralProphet. The XGBoost model reveals limitations in handling the wide variance in sales data, leading to a general trend of overestimation in smaller campaigns and underestimation in larger ones. The NeuralProphet model, employed …

    chalmers Repository record for Exploring feasibility of AI-driven insights for decision making in an e-commerce environment (opens in a new tab)

  9. Predicting Newsworthiness of California Bill Discussions

    … learning algorithms. Our best-performing model, XG-Boost, achieved 89.91% accuracy, 90.81% precision, and 89.90% F1-score. Feature importance analysis revealed that temporal features dominate predictions, accounting for 62.3% of total importance. The results demonstrate that machine learning …

    calpoly Repository record for Predicting Newsworthiness of California Bill Discussions (opens in a new tab)

  10. MedBench: Benchmarking Machine Learning Methods for Medical Tabular Prediction

    … ranking above classical baselines and tuned XG Boost. MITRA was competitive but less consistent. The advantage of TabPFN and TabICL was clearest on medium-sized tasks, while smaller tasks showed higher rank uncertainty due to limited sample sizes and fewer task instances. However, the largest …

    chalmers Repository record for MedBench: Benchmarking Machine Learning Methods for Medical Tabular Prediction (opens in a new tab)

  11. Leveraging Computational Modelling/Simulation, Machine Learning, And Additive Manufacturing For Customized Design Of Periodontal And Bone Tissue Scaffolds

    … was high, at >93%, for the Random Forest and XG Boost models, which showed that filament diameter, chamber temperature, and extruder temperature were significant variables according to SHAP analysis. Dimensional analysis showed <8% deviation in filament and pore dimensions. Thermal analysis …

    uab Repository record for Leveraging Computational Modelling/Simulation, Machine Learning, And Additive Manufacturing For Customized Design Of Periodontal And Bone Tissue Scaffolds (opens in a new tab)

  12. DRY-WET PACKING OPTIMIZATION OF ULTRAHIGH-PERFORMANCE CONCRETE FOR RADIATION SHIELDING: UNVEILING THE INTERACTIVE EFFECTS OF MAGNETITE, ILMENITE, AND FERROBORON

    … (µ). Among all models, the Random Forest and XG Boost models demonstrated superior predictive accuracy, achieving high R² values of 81% and 77%, respectively, and low error metrics. Lastly, an experimental program was implemented to develop an advanced RS-UHPC through a two-phase optimization …

    mcmaster Repository record for DRY-WET PACKING OPTIMIZATION OF ULTRAHIGH-PERFORMANCE CONCRETE FOR RADIATION SHIELDING: UNVEILING THE INTERACTIVE EFFECTS OF MAGNETITE, ILMENITE, AND FERROBORON (opens in a new tab)

  13. Physics-Informed Machine Learning model for Emission Prediction in Exhaust Aftertreatment Systems: Prediction of NOX, CO, HC and NH3 Emissions for Volvo Penta Off-Road Diesel Engines

    … industrial and off-road applications. Separate XG Boost regression models were developed for each target variable using both directly measured signals and derived physics-informed features related to SCR behaviour, catalyst thermal conditions, flow dynamics, and ammonia availability. Model per …

    chalmers Repository record for Physics-Informed Machine Learning model for Emission Prediction in Exhaust Aftertreatment Systems: Prediction of NOX, CO, HC and NH3 Emissions for Volvo Penta Off-Road Diesel Engines (opens in a new tab)

  14. Developing a machine learning-based platform for analyzing photovoltaic shading devices (PVSDs): Enhancing occupant visual comfort and electricity production

    … a machine learning (ML) platform using the XG boost (ExtremeGradientboost) algorithm to predict occupant control strategies for PVSDs, focusing specifically on remote workers in Des Moines, Iowa. To train and test the ML model, simulation results were extracted from the Climate Studio and …

    iastate Repository record for Developing a machine learning-based platform for analyzing photovoltaic shading devices (PVSDs): Enhancing occupant visual comfort and electricity production (opens in a new tab)

  15. Developmental Validation of a Bacterial Signature-Based Identification Method of Forensically Relevant Human Biological Samples

    … different from one another. The developed XG Boost prediction model accurately identified human body fluid samples with an overall accuracy of more than 88%. The man v cube study showed that there was no significant difference in bacterial DNA yields and bacterial community compositions; …

    vcu Repository record for Developmental Validation of a Bacterial Signature-Based Identification Method of Forensically Relevant Human Biological Samples (opens in a new tab)

  16. Enhancing foam concrete sustainability with low-carbon cement, municipal solid waste, and artificial intelligent analysis

    … for AI model training. In the fourth study, the XG-Boost and Deep-ANN models achieved the lowest RMSE (0.04) for dry density of FC prediction, demonstrating high modeling accuracy. For the compressive strength (fc) of FC, Random Forest (RF) achieved the best balance between accuracy and …

    iastate Repository record for Enhancing foam concrete sustainability with low-carbon cement, municipal solid waste, and artificial intelligent analysis (opens in a new tab)

  17. Outsmarting Fraud: A Machine Learning Framework for Detecting Evolving Credit Card Fraud Patterns

    … Logistic Regression, Random Forest, and XGBoost, alongside drift-aware techniques such as sliding- window retraining and drift detection methods, to assess how model performance changes as transaction patterns shift over time. The study addresses the severe class imbalance inherent in …

    rit Repository record for Outsmarting Fraud: A Machine Learning Framework for Detecting Evolving Credit Card Fraud Patterns (opens in a new tab)

  18. Identifying Racial Differences in Colorectal Polyp Profile at Screening Colonoscopy Using Traditional Regression and Machine Learning Approaches

    … Vector Machines (SVM), Random Forest (RF), XG-Boost, and AdaBoost. Based on information-maximization and results showing highest information gain performance among the above ML algorithms, the best performing models were selected, and risk factor ensembled analysis was done. SAS v9.4 and …

    south-carolina Repository record for Identifying Racial Differences in Colorectal Polyp Profile at Screening Colonoscopy Using Traditional Regression and Machine Learning Approaches (opens in a new tab)