Security of Cloud Computing Using Adaptive Neural Fuzzy Inference System

Abstract

Cloud computing can enable organizations to do more by breaking the physical bonds between an IT foundation. The raised security dangers in cloud computing must be overpowered to profit the new processing perspective that offers an imaginative arrangement of activity for relationship to IT. The purpose of the study was to reduce security’s obstacles and risks by using protection methods and approaches to ensure maximum data protection, which allows for the user to select the original security level. An adaptive neural control fuzzy system is used to resolve the unsecure and risky tasks of cloud computing. Sugeno control methods have been applied for these data protection issues in which the uncertainty because of randomness can be resolved. ANFIS identified the input parameters according to the current scenario, fuzzified the data, and integrated them into knowledge rule base. Different membership functions were used for training the data. In this article, we present a point-by-point examination of the cloud security issue. We assessed the issue from the cloud building point of view. In context of this examination, we deduce an unmistakable detail of the cloud security issue and key highlights that ought to be confirmed by any proposed security strategy. The examination and results show that the parameters dependent on ANFIS are very much intended to distinguish the oddities in cloud condition with least bogus negative rate and high discovery precision. The performance of Sugeno membership function usually gives better results and ensures the computational efficiency and accuracy of data.