Ahmmad Jabbar, Al-Dayel Osamah AbdulAziz, Khan Meraj Ali, Mahmood Tahir
Department of Mathematics and Statistics, International Islamic University Islamabad, Islamabad, 46000, Pakistan.
Ad Diriyah Hospital, Third Health Cluster, Riyadh, Saudi Arabia.
Sci Rep. 2025 May 26;15(1):18335. doi: 10.1038/s41598-025-02362-8.
The selection of AI-assistive technologies for disability support systems involves a complex decision-making problem due to the presence of uncertain evaluation criteria. The traditional methods of decision-making often do not succeed in addressing the challenges leading to potential inefficiencies in resource allocation. Aggregation operators are the fundamental tool to manage overall information into a single value. This characteristic of aggregation operators helps in ranking processes and decision-making scenarios. To overcome the issues of uncertainty and keep in mind the advantages of AOs, in this article, we have proposed the notion of fuzzy rough Maclaurin symmetric mean (FRMSM) aggregation theory. The MSM AOs reduce the sensitivity in huge amounts of data due to symmetric formulation. As a result, more accurate and authentic results can be obtained. As the MABAC approach uses border approximation area, so this characteristic reduces the bias and improves the accuracy. Therefore, we have proposed the MABAC approach based on FRMSMS AOs. For the application of the proposed work, we have delivered an algorithm and initiated an illustrative example. We have utilized the proposed work for the optimization of AI-assisted technologies in disability support systems. Thus, it shows its potential for dealing with the problems arising from the selection process of inherent challenges and will offer a reliable tool to the stakeholders in the health and assistive technology design sectors. Additionally, we have proposed a comparative analysis of the initiated approach and discussed that the introduced approach is more reliable and trustable as compared to existing notions.
由于存在不确定的评估标准，为残疾支持系统选择人工智能辅助技术涉及一个复杂的决策问题。传统的决策方法往往无法成功应对这些挑战，从而导致资源分配可能出现低效。聚合算子是将整体信息整合为单个值的基本工具。聚合算子的这一特性有助于进行排序过程和决策场景。为了克服不确定性问题并牢记聚合算子的优势，在本文中，我们提出了模糊粗糙麦克劳林对称均值（FRMSM）聚合理论的概念。由于其对称的形式，MSM聚合算子降低了对大量数据的敏感性。因此，可以获得更准确和可靠的结果。由于MABAC方法使用边界近似区域，所以这一特性减少了偏差并提高了准确性。因此，我们提出了基于FRMSMS聚合算子的MABAC方法。为了应用所提出的工作，我们给出了一个算法并给出了一个示例。我们已将所提出的工作用于优化残疾支持系统中的人工智能辅助技术。因此，它显示出应对固有挑战选择过程中出现的问题的潜力，并将为健康和辅助技术设计领域的利益相关者提供一个可靠的工具。此外，我们对所提出的方法进行了比较分析，并讨论了与现有概念相比，所引入的方法更可靠、更值得信赖。
