EUVIMEDOpdag EUVIMED
Crossref

Ethical AI Frameworks for Bias Detection and Fairness Optimization in Machine Learning Systems

Myeong Dahalbahadur

International Journal of Electrical, Electronics and Computer Systems · 2025-10-30 · 14 (2) · 230-238

DOI: 10.65521/ijeecs.v14i2.2720 ↗

At a glance

Journal article in International Journal of Electrical, Electronics and Computer Systems, published online on 2025-10-30. Written by Myeong Dahalbahadur.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

The widespread adoption of artificial intelligence and machine learning systems in domains such as healthcare, finance, criminal justice, hiring, education, and autonomous decision-making has significantly increased concerns regarding algorithmic bias, discrimination, and fairness. Machine learning models trained on historical and socially biased datasets often inherit and amplify existing inequalities, leading to unfair predictions and ethically problematic outcomes. These challenges have created an urgent need for ethical AI frameworks capable of detecting, mitigating, and optimizing fairness within intelligent decision-making systems. This research proposes an ethical AI framework for bias detection and fairness optimization in machine learning systems. The proposed framework integrates fairness-aware preprocessing, bias-sensitive feature analysis, interpretable machine learning mechanisms, fairness-constrained optimization, and post-processing calibration strategies into a unified ethical AI architecture. The framework supports the identification of demographic disparities, mitigation of algorithmic discrimination, and optimization of fairness metrics while maintaining predictive performance. The proposed system incorporates fairness metrics such as demographic parity, equal opportunity, equalized odds, and disparate impact analysis to evaluate ethical compliance in machine learning models. Explainable artificial intelligence (XAI) mechanisms are also integrated to improve transparency, accountability, and interpretability of automated decisions. Experimental evaluation demonstrates that the proposed framework significantly reduces algorithmic bias and improves fairness consistency across demographic groups while preserving high classification accuracy.

Cite

APA

Dahalbahadur, M. (2025). Ethical AI Frameworks for Bias Detection and Fairness Optimization in Machine Learning Systems. International Journal of Electrical, Electronics and Computer Systems, 14(2), 230-238. https://doi.org/10.65521/ijeecs.v14i2.2720

Vancouver

Dahalbahadur M. Ethical AI Frameworks for Bias Detection and Fairness Optimization in Machine Learning Systems. International Journal of Electrical, Electronics and Computer Systems. 2025;14(2):230-238. doi:10.65521/ijeecs.v14i2.2720

BibTeX
@article{Dahalbahadur2025,
  author = {Dahalbahadur, Myeong},
  title = {Ethical AI Frameworks for Bias Detection and Fairness Optimization in Machine Learning Systems},
  journal = {International Journal of Electrical, Electronics and Computer Systems},
  year = {2025},
  volume = {14},
  number = {2},
  pages = {230--238},
  doi = {10.65521/ijeecs.v14i2.2720}
}
Start for free →