Performance analysis of the water quality index model for predicting water state using machine learning techniques

Process Safety and Environmental Protection, Год журнала: 2022, Номер 169, С. 808 - 828

Опубликована: Ноя. 28, 2022

Existing water quality index (WQI) models assess using a range of classification schemes. Consequently, different methods provide number interpretations for the same properties that contribute to considerable amount uncertainty in correct quality. The aims this study were evaluate performance model order classify coastal correctly completely new scheme. Cork Harbour data was used study, which collected by Ireland's environmental protection agency (EPA). In present four machine-learning classifier algorithms, including support vector machines (SVM), Naïve Bayes (NB), random forest (RF), k-nearest neighbour (KNN), and gradient boosting (XGBoost), utilized identify best predicting classes widely seven WQI models, whereas three are recently proposed authors. KNN (100% 0% wrong) XGBoost (99.9% 0.1% algorithms outperformed accurately models. validation results indicate outperformed, accuracy (1.0), precision (0.99), sensitivity specificity F1 (0.99) score, predict Moreover, compared higher prediction accuracy, precision, sensitivity, specificity, score found weighted quadratic mean (WQM) unweighted root square (RMS) respectively, each class. findings showed WQM RMS could be effective reliable assessing terms classification. Therefore, helpful providing accurate information researchers, policymakers, research personnel monitoring more effectively.

Язык: Английский

---

Interpretable machine learning for predicting the strength of 3D printed fiber-reinforced concrete (3DP-FRC)

Journal of Building Engineering, Год журнала: 2023, Номер 72, С. 106648 - 106648

Опубликована: Апрель 25, 2023

Язык: Английский

---

Explainable machine learning (XML) framework for seismic assessment of structures using Extreme Gradient Boosting (XGBoost)

Engineering Structures, Год журнала: 2025, Номер 327, С. 119621 - 119621

Опубликована: Янв. 9, 2025

Язык: Английский

---

Predicting Penetration Depth in Ultra-High-Performance Concrete Targets under Ballistic Impact: An Interpretable Machine Learning Approach Augmented by Deep Generative Adversarial Network

Results in Engineering, Год журнала: 2025, Номер unknown, С. 103909 - 103909

Опубликована: Янв. 1, 2025

Язык: Английский

---

Modified Genetic Algorithm for Feature Selection and Hyper Parameter Optimization: Case of XGBoost in Spam Prediction

IEEE Access, Год журнала: 2022, Номер 10, С. 84365 - 84383

Опубликована: Янв. 1, 2022

Recently, spam on online social networks has attracted attention in the research and business world. Twitter become preferred medium to spread content. Many efforts attempted encounter spam. brought extra challenges represented by feature space size, imbalanced data distributions. Usually, related works focus part of these main or produce black-box models. In this paper, we propose a modified genetic algorithm for simultaneous dimensionality reduction hyper parameter optimization over datasets. The initialized an eXtreme Gradient Boosting classifier reduced features tweets dataset; generate prediction model. model is validated using 50 times repeated 10-fold stratified cross-validation, analyzed nonparametric statistical tests. resulted attains average 82.32% 92.67% terms geometric mean accuracy respectively, utilizing less than 10% total space. empirical results show that outperforms Chi² PCA selection methods. addition, many machine learning algorithms, including BERT-based deep model, prediction. Furthermore, proposed approach applied SMS modeling compared works.

Язык: Английский

---

Snow avalanche susceptibility mapping using novel tree-based machine learning algorithms (XGBoost, NGBoost, and LightGBM) with eXplainable Artificial Intelligence (XAI) approach

Stochastic Environmental Research and Risk Assessment, Год журнала: 2023, Номер 37(6), С. 2243 - 2270

Опубликована: Март 13, 2023

Язык: Английский

---

Soft computing for determining base resistance of super-long piles in soft soil: A coupled SPBO-XGBoost approach

Computers and Geotechnics, Год журнала: 2023, Номер 162, С. 105707 - 105707

Опубликована: Авг. 2, 2023

Язык: Английский

---

Rapid Landslide Extraction from High-Resolution Remote Sensing Images Using SHAP-OPT-XGBoost

Remote Sensing, Год журнала: 2023, Номер 15(15), С. 3901 - 3901

Опубликована: Авг. 7, 2023

Landslides, the second largest geological hazard after earthquakes, result in significant loss of life and property. Extracting landslide information quickly accurately is basis disaster prevention. Fengjie County, Chongqing, China, a typical landslide-prone area Three Gorges Reservoir Area. In this study, we newly integrate Shapley Additive Explanation (SHAP) Optuna (OPT) hyperparameter tuning into four basic machine learning algorithms: Gradient Boosting Decision Tree (GBDT), Extreme (XGBoost), Light Machine (LightGBM), (AdaBoost). We construct new models (SHAP-OPT-GBDT, SHAP-OPT-XGBoost, SHAP-OPT-LightGBM, SHAP-OPT-AdaBoost) apply to extraction for first time. Firstly, high-resolution remote sensing images were preprocessed, non-landslide samples constructed, an initial feature set with 48 features was built. Secondly, SHAP used select contributions, important selected. Finally, Optuna, Bayesian optimization technique, utilized automatically models’ best hyperparameters. The experimental results show that accuracy (ACC) these SHAP-OPT above 92% training time less than 1.3 s using mediocre computational hardware. Furthermore, SHAP-OPT-XGBoost achieved highest (96.26%). Landslide distribution County from 2013 2020 can be extracted by quickly.

Язык: Английский

---

Prediction of compressive strength and tensile strain of engineered cementitious composite using machine learning

International Journal of Mechanics and Materials in Design, Год журнала: 2024, Номер 20(4), С. 671 - 716

Опубликована: Янв. 12, 2024

Язык: Английский

---

Interactive effects of hyperparameter optimization techniques and data characteristics on the performance of machine learning algorithms for building energy metamodeling

Case Studies in Thermal Engineering, Год журнала: 2024, Номер 55, С. 104124 - 104124

Опубликована: Фев. 12, 2024

Metamodeling is a promising technique for alleviating the computational burden of building energy simulation. Although various machine learning (ML) algorithms have been applied, interactive effects multiple factors on ML algorithm performance remain unclear. In this study, six popular algorithms, including ridge regression, random forest, extreme gradient boosting (XGBoost), support vector regression (SVR), k-nearest neighbor (KNN) and multi-layer perceptron (MLP), were analyzed benchmark metamodeling problem in simulation under impacts four factors: input dimension, sample size, degree input-output sensitivity hyperparameter optimization (HPO) technique. The results indicated that XGBoost had high model precision strong robustness, while KNN SVR performed poorly two metrics. Increasing size could mitigate impact other three precision, especially MLP. findings will assist designers, engineers researchers selecting suitable HPO techniques based dataset's characteristics facilitate application design optimization, analysis decision-making processes.

Язык: Английский

---