Enhancing Predictive Accuracy of Renewable Energy Systems and Sustainable Architectural Design Using PSO Algorithm

International Journal of Computational and Experimental Science and Engineering, Год журнала: 2025, Номер 11(1)

Опубликована: Янв. 12, 2025

This paper formulates and examines the approach of integrating PSO into tune DNNs for boosting predictive capability in renewable energy systems green building designs. The method was then employed to select Key features such as; Solar Irradiance, Ambient Temperature, Panel Efficiency Energy Output. PSO-based feature selection resulted significant enhancements across a set four metrics, there an improvement accuracy from previous 0.82 0.87, precision 0.78 0.83, as well recall 0.76 0.81, F1-Score 0.77 current score 0.82. Moreover, RMSE values reduced 0.27 0.23, AUC enriched 0.74 0.85. Thus, results study support PSO’s role improving selection, which, return, improves models management. presented emphasizes possibility use enhanced optimization algorithms enhancing best performing, less resource-intensive, environmentally friendly solutions architecture.

Язык: Английский

BreastHybridNet: A Hybrid Deep Learning Framework for Breast Cancer Diagnosis Using Mammogram Images

International Journal of Computational and Experimental Science and Engineering, Год журнала: 2025, Номер 11(1)

Опубликована: Янв. 25, 2025

As a common malignancy in females, breast cancer represents one of the most serious threats to female's life, which is also closely associated with Sustainable Development Goal 3 (SDG 3) United Nations for keeping healthy lives and promoting well-being all people. Breast accounts highest number mortality early diagnosis key reducing disease-specific general. Current methods struggle accurately localize important regions, model sequential dependencies, or combine different features despite considerable improvements artificial intelligence deep learning domains. They prevent diagnostic frameworks from being reliable scalable, especially low-resourced healthcare settings. This study proposes novel hybrid framework, BreastHybridNet, using mammogram images tackle these mutual challenges. The proposed framework combines pre-trained CNN backbone feature extraction, spatial attention mechanism automatically highlight image area, contains signature patterns carrying information, BiLSTM layer obtain dependencies features, fusion strategy process complementarily. Experimental results show that accuracy 98.30%, outperforms state-of-the-art LMHistNet, BreastMultiNet, DOTNet 2.0 extent quantitatively. BreastHybridNet works towards feasibility interpretability scalability on existing systems while contributing worldwide efforts alleviate cancer-related cost-efficient lenses. highlights need AI-enabled solutions contribute accessing technologies screening.

Язык: Английский

Exploring Quantum-Inspired Algorithms for High-Performance Computing in Structural Analysis

International Journal of Computational and Experimental Science and Engineering, Год журнала: 2025, Номер 11(1)

Опубликована: Фев. 15, 2025

Structural analysis in high-performance computing (HPC) faces challenges related to computational complexity, energy efficiency, and solution accuracy. This research explores Quantum-Inspired Algorithms (QIAs) as an innovative approach enhance efficiency accuracy large-scale structural simulations. The proposed methodology integrates a Evolutionary Algorithm (QIEA) with Hybrid Neural Network (HQINN) for improved performance prediction. study evaluates QIAs on three benchmark problems: Bridge Load Distribution Analysis – Achieves speed-up of 45% compared classical solvers while maintaining error rate <0.5%. Variational Monte Carlo (QIVMC) method is applied solve complex eigenvalue problems, achieving 8× acceleration solving stiffness matrices traditional iterative solvers. Experimental validation cluster using 1,024 cores demonstrates 55% improvement processing speed 37% reduction consumption. Results confirm that significantly outperform numerical methods analysis, paving the way their adoption next-generation engineering Future work will focus hybrid quantum-classical frameworks real-world applications civil, aerospace, automotive engineering.

Язык: Английский