Cloud data transmission based on security and improved routing through hybrid machine learning techniques

A shared environment and the computer paradigm are combined in cloud computing (CC), enabling multiple users to access services and resources. This ecosystem is not only globally accessible via the Internet, but it can also be shared at all levels. All levels of resources, platforms, and infrastructure can be traded with a variety of clients. This research propose novel method in cloud data transmission with security and enhance routing by hybrid machine learning techniques. Here, the cryptographic-based cloud architecture and routing for data analysis is carried out using hybrid of support auto-encoder gradient neural networks. The experimental analysis in terms of data transmission ratio, specificity, training accuracy, validation accuracy, security analysis. Proposed technique attained data transmission ratio of 65%, specificity of 78%, training accuracy of 93%, validation accuracy of 83%, and security analysis of 65%.

Automated summary

Cloud computing combines a shared environment and the computer paradigm, allowing multiple users to access services and resources. This ecosystem can be globally accessible via the Internet and shared at all levels. This research proposes a novel method in cloud data transmission using hybrid machine learning techniques for security and enhanced routing. The experimental analysis shows that the proposed technique achieves a data transmission ratio of 65%, specificity of 78%, training accuracy of 93%, validation accuracy of 83%, and security analysis of 65%.