
Results in Engineering, Год журнала: 2024, Номер unknown, С. 103001 - 103001
Опубликована: Сен. 1, 2024
Язык: Английский
Results in Engineering, Год журнала: 2024, Номер unknown, С. 103001 - 103001
Опубликована: Сен. 1, 2024
Язык: Английский
Results in Engineering, Год журнала: 2025, Номер unknown, С. 103985 - 103985
Опубликована: Янв. 1, 2025
Язык: Английский
Процитировано
3Results in Engineering, Год журнала: 2025, Номер 25, С. 104197 - 104197
Опубликована: Янв. 30, 2025
Язык: Английский
Процитировано
1Опубликована: Янв. 1, 2025
Язык: Английский
Процитировано
0Mineral Processing and Extractive Metallurgy Transactions of the Institutions of Mining and Metallurgy, Год журнала: 2025, Номер unknown
Опубликована: Фев. 6, 2025
This research study proposed a novel approach utilising AI models to predict the metallurgical performance of complex sulfide ore flotation. Five machine learning and artificial intelligence were employed in this study, that is, Random Forest (RF), Artificial Neural Networks (ANN), Adaptive Neuro Fuzzy Interference System (ANFIS), Mamdani Logic (MFL) Hybrid (HyFIS). Sixty-two flotation tests conducted on samples containing galena, chalcopyrite sphalerite as main valuable minerals, pyrite gangue mineral. Different variables used inputs studies including physiochemical operational parameters. The recovery lead copper their corresponding grades bulk concentrate primary dependent (outputs). input included dosages sodium cyanide (pyrite's depressant), isopropyl xanthate (collector), zinc sulfate (sphalerite's depressant) Methyl isobutyl carbinol (MIBC, frother); air flow rate; time; speed impeller cell, which is indicative energy input. For purpose model development, datasets divided into two subsets. first subset was primarily for training phase, it comprised 80% total data. second subset, consisting 20% data, testing. models’ assessed using indicators: R-squared (R 2 ) proportion explained variation RMSE average prediction error. demonstrated superior predicting grade lead, with R² 0.9895 1.069 respectively, whereas testing step respective values 0.9128 2.859.
Язык: Английский
Процитировано
0PLoS ONE, Год журнала: 2025, Номер 20(2), С. e0317193 - e0317193
Опубликована: Фев. 24, 2025
This study aims at the limitations of traditional methods in evaluation stroke sequelae and rehabilitation effect monitoring, especially for accurate identification tracking brain injury areas. To overcome these challenges, we introduce an advanced neuroimaging technology based on deep learning, SWI-BITR-UNet model. model, introduced as novel Machine Learning (ML) combines SWIN Transformer’s local receptive field shift mechanism, effective feature fusion strategy U-Net architecture, aiming to improve accuracy lesion region segmentation multimodal MRI scans. Through application a 3-D CNN encoder decoder, well integration CBAM attention module jump connection, model can finely capture refine features, achieve level comparable that manual by experts. introduces 3D encoder-decoder architecture specifically designed enhance processing capabilities medical imaging data. The development utilizes ADAM optimization algorithm facilitate training process. Bra2020 dataset is utilized assess proposed learning neural network. By employing skip connections, effectively integrates high-resolution features from with up-sampling thereby increasing model’s sensitivity spatial characteristics. both testing phases, SWI-BITR-Unet trained using reliable datasets evaluated through comprehensive array statistical metrics, including Recall (Rec), Precision (Pre), F1 test score, Kappa Coefficient (KC), mean Intersection over Union (mIoU), Receiver Operating Characteristic-Area Under Curve (ROC-AUC). Furthermore, various machine models, such Random Forest (RF), Support Vector (SVM), Extreme Gradient Boosting (XGBoost), Categorical (CatBoost), Adaptive (AdaBoost), K-Nearest Neighbor (KNN), have been employed analyze tumor progression brain, performance characterized Hausdorff distance. In From ML was more than other models. Subsequently, regarding DICE coefficient values, maps (annotation distributions) generated models indicated models’s capability autonomously delineate areas core (TC) enhancing (ET). Moreover, efficacy demonstrated superiority existing research field. computational efficiency ability handle long-distance dependencies make it particularly suitable applications clinical Settings. results showed SNA-BITR-UNet not only identify monitor subtle changes area, but also provided new efficient tool process, providing scientific basis developing personalized plans.
Язык: Английский
Процитировано
0International Journal of Energy and Water Resources, Год журнала: 2025, Номер unknown
Опубликована: Апрель 10, 2025
Язык: Английский
Процитировано
0Journal of Water Process Engineering, Год журнала: 2025, Номер 74, С. 107876 - 107876
Опубликована: Май 1, 2025
Язык: Английский
Процитировано
0International Journal of Hydrogen Energy, Год журнала: 2025, Номер 138, С. 331 - 343
Опубликована: Май 17, 2025
Язык: Английский
Процитировано
0Results in Engineering, Год журнала: 2024, Номер unknown, С. 103001 - 103001
Опубликована: Сен. 1, 2024
Язык: Английский
Процитировано
1