An Intelligent Algorithm for Evaluating Martial Arts Teaching Skills Based on Complex Picture Fuzzy Dombi Aggregation Operator

Martial arts teaching skills involve the systematic instruction of physical techniques, mental discipline, and tactical strategies to develop a student’s proficiency in self-defense and personal growth. It is relevant when there is a specific analysis of the diverse features involving the technique, versatility, and interaction features. In Multi-Attribute Decision-Making (MADM), conventional approaches cannot provide a framework to capture the uncertainties and vague judgments inevitably associated with global experts’ evaluations of such a broad spectrum of skills. These limitations are seen when the evaluations do not consider the dynamism, uncertainty, or subjective nature inherent in the evaluation process, thus having less reliable or less complete decision outcomes. To handle these challenges, the concept of Complex Picture Fuzzy Sets (C-PFS) is utilized, and new advanced Dombi aggregation operators (AO), including Complex Picture Fuzzy Dombi Weighted Averaging (C-PFDWA) and Complex Picture Fuzzy Dombi Weighted Geometric (C-PFDWG) operators are developed. These operators can be effectively utilized to overcome real-life evaluation issues in martial arts skills assessment, serving as intelligent algorithms that facilitate more accurate decision-making processes. To allow the collection of the judgments of different experts over the membership, abstention, and non-membership degrees, offering a comprehensive and detailed picture of an instructor's performance even in cases where there is uncertainty. This comprehensive approach ensures a more reliable and customized assessment, enhancing instructional quality and better student outcomes as instructors receive more targeted feedback on improvement areas. In addition, this study includes detailed simulations and complete results of selected parameters, which demonstrate the practical applicability and robustness of the proposed operators, thus providing strong justification for the research and validating the efficacy of the developed framework.