Hybrid machine learning techniques for knowledge extraction in communication networks and advanced decision based complex q-Rung orthopair fuzzy frameworks

用于通信网络知识提取的混合机器学习技术及基于高级决策的复杂q阶正交对模糊框架

阅读:2

Abstract

Hybrid machine learning techniques for knowledge extraction in communication networks combine the strengths of multiple learning algorithms to analyze complex, high-dimensional, and dynamic network data effectively. Some advanced approaches are discussed to improve the intelligence and efficiency of modern communication networks, making them more resilient and capable of meeting the growing demands of data-driven applications. This article articulates the efficiency and feasibility of a complex q-rung orthopair fuzzy set (Cq-ROFS), which is an extended version of an intuitionistic and q-rung orthopair fuzzy model. The Cq-ROFS has extensive information about any object in the form of amplitude and phase terms. Besides the theoretical concepts of Cq-ROFS, we modified the family of weighted average and weighted geometric operators using fundamental operations of Sugeno-Weber t-norms and t-conorms. An optimization technique of the WASPAS method is adopted to integrate the ranking of alternatives based on multi-criteria decision-making (MCDM) problems. To show the validation and compatibility of diagnosed approaches, we also discussed an experimental case study to assess some advanced communication techniques using developed mathematical approaches and a decision analysis system. The sensitivity analysis and comparative study with existing mathematical methodologies are employed to demonstrate the flexibility and superiority of the discussed approaches.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。