A New Extended Topsis Method for E-Waste Recycling Partner Selection Under Complex Pythagorean Fuzzy Rough Dombi Aggregation Operator

The utilization of electrical and electronic equipment (EEEs) in waste recycling has become paramount for various countries. The waste electrical and electronic equipment (WEEE) recyclers own a crucial position in the environmental growth of a country as they help to minimize carbon emissions during the recycling of WEEE in the most eco-friendly way. Therefore, selecting and evaluating suitable WEEE recycling partners has become an important part of the decision-making (DM) system. The primary aim of this research is to establish a new method based on the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) and a new artificial intelligence (AI) approach of feed-forward CPyFR neural network for determining WEEE recycling partners with uncertain weight information. For this, a new concept of complex Pythagorean fuzzy rough sets (CPyFRSs) is first defined to handle uncertainty in decision-making (DM) problems. A generalized distance measure is defined for calculating the weights of experts and criteria. The Dombi operators with operational parameters, have excellent flexibility. Since these Dombi operation parameters are very flexible, some Dombi Aggregation Operators (AOps) are provided to establish an optimal DM approach. Additionally, the developed methodology is applied to a real-world scenario to address the selection of e-waste recycling partners. Finally, to demonstrate the efficiency and consistency of the proposed model, a brief comparison of the proposed method with several existing methods is included.