Modeling of extended osprey optimization algorithm with Bayesian neural network: An application on Fintech to predict financial crisis

AIMS Mathematics, Год журнала: 2024, Номер 9(7), С. 17555 - 17577

Опубликована: Янв. 1, 2024

<abstract> <p>Accurately predicting and anticipating financial crises becomes of paramount importance in the rapidly evolving landscape technology (Fintech). There is an increasing reliance on predictive modeling advanced analytics techniques to predict possible alleviate effects Fintech innovations reshaping traditional paradigms. Financial experts academics are focusing more risk prevention control tools based state-of-the-art such as machine learning (ML), big data, neural networks (NN). Researchers aim prioritize identify most informative variables for accurate prediction models by leveraging abilities deep feature selection (FS) techniques. This combination allows extraction relationships nuanced patterns from complex datasets, empowering discern subtle signals indicative potential crises. study developed extended osprey optimization algorithm with a Bayesian NN crisis (EOOABNN-PFC) technique. The EOOABNN-PFC technique uses metaheuristics model presence crisis. In preprocessing, min-max scalar scale input data into valid format. Besides, applies EOOA-based subset approach elect optimal subset, performed using BNN classifier. Lastly, parameter carried out multi-verse optimizer (MVO). simulation process identified that reaches superior accuracy outcomes 95.00% 95.87% compared other existing approaches under German Credit Australian datasets.</p> </abstract>

Язык: Английский

---

CFD simulation and measurement and control analysis of the ambient temperature field of agricultural greenhouses

Applied Mathematics and Nonlinear Sciences, Год журнала: 2025, Номер 10(1)

Опубликована: Янв. 1, 2025

Abstract This study addresses the issue of microclimate prediction in greenhouse environmental control southeastern Yunnan region by proposing a deep learning-enhanced CFD modeling method, DeepCFD-OptNet model. Traditional models have certain limitations when handling complex changes, making it difficult to effectively capture multidimensional variations dynamic environments. To address this, employs Convolutional Neural Networks (CNN) extract spatial features from data and uses Temporal (TCN) model time-series changes. Additionally, Particle Swarm Optimization (PSO) is integrated optimize strategies. Experimental results show that demonstrates high accuracy predicting temperature humidity, significantly reducing Root Mean Square Error (RMSE) compared traditional models, better simulates predicts changes within greenhouse. The further confirms learning techniques optimization algorithms enhance performance simulations. research provides new technological approach for development smart agriculture region, contributing improved crop yields, optimized resource efficiency, reduced energy consumption, promotion sustainable agricultural production through smarter management.

Язык: Английский

---

改进的蜣螂优化算法及其在无波前自适应系统波前校正中的应用

ACTA PHOTONICA SINICA, Год журнала: 2025, Номер 54(3), С. 0306001 - 0306001

Опубликована: Янв. 1, 2025

---

A new financial risk prediction model based on deep learning and quasi-oppositional coot algorithm

Alexandria Engineering Journal, Год журнала: 2024, Номер 108, С. 60 - 69

Опубликована: Июль 23, 2024

Язык: Английский

---

A new prediction model based on deep learning for pig house environment

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

Опубликована: Дек. 28, 2024

Язык: Английский

---