Assessment of artificial neural networks in different sectors by employing the notion of bipolar fuzzy Schweizer-Sklar power aggregation operators

Abstract

In recent scenarios, we cannot ignore the importance of artificial intelligence in many fields like medical diagnosis, computer science, economics and agriculture, etc. In 1960, Schweizer and Sklar developed the concept of Schweizer-Sklar (SS) t-norm and t-conorm by incorporating a parameter which is more flexible and helpful in handling complex and unclear data. If we put parameter then the information of the Hamacher and Lukasiewicz t-norms is simply derived. The primary goal of this study is to develop the fundamental Schweizer-Sklar operational laws for bipolar fuzzy numbers. Additionally, we have defined the notion of bipolar fuzzy Schweizer-Sklar power average and bipolar fuzzy Schweizer-Sklar power geometric aggregation operators. Moreover, we have elaborated on the basic characteristics of these developed notions. We have initiated the algorithm to demonstrate the actual use of this work in artificial neural networking. We have also compared our work with some prevailing theories.

Keywords

• Artificial neural Network
• Bipolar Fuzzy Set
• Schweizer-Sklar Power Aggregation Operators