@ARTICLE{Rehman_Ubaid_ur_AI-driven_2026,
 author={Rehman, Ubaid ur and Mahmood, Tahir and Waqas, Hafiz Muhammad and Rehman Virk, Abaid ur},
 volume={vol. 36},
 number={No 1},
 journal={Archives of Control Sciences},
 pages={55-84},
 howpublished={online},
 year={2026},
 publisher={Committee of Automatic Control and Robotics PAS},
 abstract={As cyberattacks become more advanced, advanced AI-based big data visualization is now needed for effective threat detection. Yet, choosing the best visualization tools is some multicriteria decision-making (MCDM) task that involves considering many criteria containing both positive and negative aspects. WhileMCDMmethods that address the selection and classification of AI-driven big data visualization tools focus on the positive aspects of the evaluation criteria and ignore the negative aspects of the criteria, resulting in incomplete evaluations. Further, although Einstein operators have shown strong results in uncertain and imprecise situations and MCDM approaches, they have not yet been used in bipolar fuzzy frameworks, which leaves a major gap in decision-making methods. To overcome these problems, this article interprets a bipolar fuzzy MCDM methodology based on Einstein prioritized operators to systematically evaluate and classify AI-driven big data visualization tools for cybersecurity threat detection. For this method, Einstein prioritized operators within a bipolar fuzzy framework devised in this article, which can aggregate both positive and negative aspects of the criteria.Acomprehensive case study is shown to assess and classify the prominent AI-driven big data visualization tools for cybersecurity threat detection, considering critical criteria with dual aspects. The proposed methodology is meticulously compared with the prevailing MCDM methods to validate its dominance in handling uncertainty and the bipolarity of the criteria. This article helps security professionals choose the right AI-powered visualization tools which, in turn improve the cybersecurity of their organizations and make it easier to detect threats.},
 type={Article},
 title={AI-driven big data visualization for cybersecurity using bipolar fuzzy Einstein prioritized operators},
 URL={http://ochroma.man.poznan.pl/Content/138657/PDF/acs-art03.pdf},
 doi={10.24425/acs.2026.158421},
 keywords={optimization models, control problem, efficient solution},
}