EUVIMEDEUVIMED entdecken
Crossref

A Hybrid Machine Learning–Bayesian Framework for Correcting Measurement Error in Health Data

Romuald Daniel Boy Ngbogbele

Journal of Artificial Intelligence and Digital Health · 2026

DOI: 10.67238/jaid.2026.v1.12 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Artificial Intelligence and Digital Health, 2026. Verfasst von Romuald Daniel Boy Ngbogbele.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The global transition to renewable energy has elevated solar power as a key driver of sustainability, yet its intermittent nature and integration challenges demand advanced solutions to optimize efficiency and reliability. This research investigates the role of artificial intelligence (AI) in revolutionizing solar energy management, focusing on machine learning and optimization techniques to enhance system performance, the experiment was calibrated in MATLAB environment. We evaluate algorithms including Artificial Neural Networks (ANNs), Support Vector Regression (SVR), Linear Regression (LR), and Genetic Algorithms (GAs), applied to solar power forecasting and parameter optimization. Our methodology employs SVR with an RBF kernel and grid search, achieving precise predictions of solar power output with reduced forecasting errors, while GAs optimizes system parameters to a fitness value of 23.20 kWh, even under constraints like a 90° panel tilt. Comparative analysis reveals SVR and GA outperform ANNs and LR, demonstrating their adaptability to weather fluctuations. This study highlights AI’s transformative impact on solar energy efficiency and sustainability, offering valuable implications for researchers and industry stakeholders.

Zitieren

APA

Ngbogbele, R. D. B. (2026). A Hybrid Machine Learning–Bayesian Framework for Correcting Measurement Error in Health Data. Journal of Artificial Intelligence and Digital Health. https://doi.org/10.67238/jaid.2026.v1.12

Vancouver

Ngbogbele RDB. A Hybrid Machine Learning–Bayesian Framework for Correcting Measurement Error in Health Data. Journal of Artificial Intelligence and Digital Health. 2026. doi:10.67238/jaid.2026.v1.12

BibTeX
@article{Ngbogbele2026,
  author = {Ngbogbele, Romuald Daniel Boy},
  title = {A Hybrid Machine Learning–Bayesian Framework for Correcting Measurement Error in Health Data},
  journal = {Journal of Artificial Intelligence and Digital Health},
  year = {2026},
  doi = {10.67238/jaid.2026.v1.12}
}
Kostenlos starten →