Enhanced growth optimizer algorithm with dynamic fitness-distance balance method for solution of security-constrained optimal power flow problem in the presence of stochastic wind and solar energy

Applied Energy, Год журнала: 2024, Номер 368, С. 123499 - 123499

Опубликована: Май 25, 2024

Язык: Английский

---

Alpha evolution: An efficient evolutionary algorithm with evolution path adaptation and matrix generation

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 137, С. 109202 - 109202

Опубликована: Авг. 30, 2024

Язык: Английский

---

Advanced Optimized Deep-Learning Model for Precise Evaluation of Subsurface Carbon Dioxide Trapping Efficiency

Energy & Fuels, Год журнала: 2025, Номер unknown

Опубликована: Фев. 16, 2025

As global warming intensifies, geological carbon storage (GCS) in saline aquifers could play a vital role mitigating CO2 emissions. trapping occurs mainly through solubility and residual trapping, requiring an accurate prediction using (STI) (RTI) indices. Machine learning shows promise for estimating aquifers, but current models often lack effective feature selection, parameter optimization, advanced deep techniques, limiting their performance. This study develops predictive RTI STI CNN, LSTM, hybrid algorithms by combining them with growth optimization (GO) cuckoo (COA). An extensive data set of 6,811 points was analyzed, selection the nondominated sorting genetic algorithm random forest analysis. Model performance based on independent testing data, Shapley additive explanation (SHAP) analysis identified key features. For RTI, gas saturation (RGS), injection rate (IR), permeability (Perm), elapsed time (Te), porosity (Por), salinity (Sal) were most influential. Conversely, RGS, thickness (Th), Te, Perm, Sal, Por critical STI. The results confirm that DL outperformed standard models, metaheuristic enhancing accuracy generalization. CNN-COA model achieved lowest root-mean-square error (RMSE) (0.0011 training; 0.0035 testing) (0.0005 0.0028 predictions. SHAP revealed RGS Perm as least influential features predictions Th features, respectively, is innovative its integration methods selection. leads to improved GCS performance, robustness, adaptability diverse conditions.

Язык: Английский

---

A hybridization of growth optimizer and improved arithmetic optimization algorithm and its application to discrete structural optimization

Computers & Structures, Год журнала: 2024, Номер 303, С. 107496 - 107496

Опубликована: Авг. 1, 2024

Язык: Английский

---

Predictive modeling for early detection of biliary atresia in infants with cholestasis: Insights from a machine learning study

Computers in Biology and Medicine, Год журнала: 2024, Номер 174, С. 108439 - 108439

Опубликована: Апрель 16, 2024

Язык: Английский

---

Bone scintigraphy based on deep learning model and modified growth optimizer

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Окт. 27, 2024

Bone scintigraphy is recognized as an efficient diagnostic method for whole-body screening bone metastases. At the moment, scan image analysis primarily dependent on manual reading by nuclear medicine doctors. However, needs substantial experience and both stressful time-consuming. To address aforementioned issues, this work proposed a machine-learning technique that uses phases to detect scintigraphy. The first phase in model feature extraction it was conducted based integrating Mobile Vision Transformer (MobileViT) our framework capture highly complex representations from raw medical imagery using two primary components including ViT lightweight CNN featuring limited number of parameters. In addition, second named selection, Arithmetic Optimization Algorithm (AOA) being used improve Growth Optimizer (GO). We evaluate performance FS model, GOAOA set 18 UCI datasets. Additionally, applicability real-world application evaluated 2800 images (1400 normal 1400 abnormal). results statistical revealed algorithm outperforms other algorithms employed study.

Язык: Английский

---

Automated legal consulting in construction procurement using metaheuristically optimized large language models

Automation in Construction, Год журнала: 2024, Номер 170, С. 105891 - 105891

Опубликована: Дек. 5, 2024

Язык: Английский

---

Optimizing k-coverage in energy-saving wireless sensor networks based on the Elite Global Growth Optimizer

Expert Systems with Applications, Год журнала: 2024, Номер 256, С. 124878 - 124878

Опубликована: Июль 31, 2024

Язык: Английский

---

Hybrid Machine-Learning Model for Accurate Prediction of Filtration Volume in Water-Based Drilling Fluids

Applied Sciences, Год журнала: 2024, Номер 14(19), С. 9035 - 9035

Опубликована: Окт. 7, 2024

Accurately predicting the filtration volume (FV) in drilling fluid (DF) is crucial for avoiding problems such as a stuck pipe and minimizing DF impacts on formations during drilling. Traditional FV measurement relies human-centric experimental evaluation, which time-consuming. Recently, machine learning (ML) proved itself promising approach prediction. However, existing ML methods require time-consuming input variables, hindering semi-real-time monitoring of FV. Therefore, employing radial basis function neural network (RBFNN) multilayer extreme (MELM) algorithms integrated with growth optimizer (GO), predictive hybrid (HML) models are developed to reliably predict using only two easy-to-measure variables: density (FD) Marsh funnel viscosity (MFV). A 1260-record dataset from seventeen wells drilled oil gas fields (Iran) was used evaluate models. Results showed superior performance RBFNN-GO model, achieving root-mean-square error (RMSE) 0.6396 mL. Overfitting index (OFI), score, dependency, Shapley additive explanations (SHAP) analysis confirmed prediction model. In addition, low RMSE (0.3227 mL) RBFNN-NGO model unseen data different well within studied strong generalizability this rapid novel method.

Язык: Английский

---

Rabbit algorithm for global optimization

Applied Mathematical Modelling, Год журнала: 2024, Номер unknown, С. 115860 - 115860

Опубликована: Дек. 1, 2024

Язык: Английский

---