A Fuzzy Neural Network Approach for Nanomaterials Analysis in Nanoelectronics Under Fuzzy Credibility Information

• Published in: International journal of computational intelligence systems Vol. 18; no. 1; pp. 1 - 23
• Main Authors: Ullah, Ihsan, Abdullah, Saleem, Nawaz, Marya, Ahmadzai, Hameed Gul
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 07.08.2025; Springer Nature B.V; Springer
• Subjects: Artificial Intelligence; Computational Intelligence; Control; Credibility; Decision making; Decision making model; Engineering; Fuzzy credibility neural network; Fuzzy logic; Graphene; Hamacher aggregation operator; Mathematical Logic and Foundations; Mechatronics; Nanoelectronics; Nanomaterial; Nanomaterials; Neural networks; Operators (mathematics); Parameter sensitivity; Robotics; Sensitivity analysis; Decision making model; Fuzzy credibility neural network; Nanomaterial; Hamacher aggregation operator
• ISSN: 1875-6883; 1875-6891; 1875-6883
• DOI: 10.1007/s44196-025-00938-w

Nanomaterials are a key component of nanoelectronics and selecting the most suitable nanomaterial for nanoelectronics remains a significant challenge for companies. The classical decision making process is often difficult and uncertain when identifying the ideal nanomaterial. To address this, we develop a novel decision making model based on a fuzzy credibility neural network with Hamacher aggregation operators. We apply the proposed model to select the most suitable nanomaterial for nanoelectronics. For this purpose, we collect information matrices from three experts regarding various nanomaterials. To analyze these matrices, we use entropy to calculate the weights of each criterion. After determining the weights, we apply fuzzy credibility Hamacher weighted aggregation operators to combine the input signals and their corresponding weights in order to compute the hidden layer information for the nanomaterials. To ensure accurate and reliable results, we apply the fuzzy credibility Hamacher weighted aggregation operator once again to the hidden layer information, aggregating it with the appropriate weights to generate the output layer information. Next, we use a score function based on fuzzy credibility numbers to calculate the score values of the output information. After this, we apply three activation functions to compute the final output of the proposed model. Based on the results, graphene is identified as the best nanomaterial for nanoelectronics. Furthermore, we perform a sensitivity analysis of the proposed model by varying the Hamacher parameter. To confirm the effectiveness and accuracy of the proposed approach, we finally validate the results using three well-known MCDM methods.