RNN with Adaptive Split Algorithm for the Analysis of Security on Cloud Computing

  • Dr. K. Loheswaran, Dr. D. Murali, D. Kalaiabirami

Abstract

One of the most recent trends in IT division is cloud computing (CC). It is an appropriated processing condition which has committed registering assets gotten to whenever from anyplace. In the present time, user keeps a high measure of information on cloud and even share a great deal of information, and thus, it is important to utilize safety efforts so that there is no risk to any of the client's information. To furnish an abnormal state of security with the fast headway of Internet, numerous devices and systems are being utilized. In this study, a Hybrid Adaptive algorithm is developed for the security on Cc. The proposed adaptive machine learning algorithm is the combination of Recurrent Neural Network (RNN) with adaptive split algorithm (ASA). RNN is one of the Artificial Intelligence (AI) techniques, which is utilized to classification purpose. The proposed hybrid adaptive algorithm is utilized to classify the data before the encryption process. Based on the process, the accuracy of the data is achieved and it requires less memory space only. After the data storage allocation, the design of end to end security framework is carried out. The main objective is to secure the data and eliminate the insider threats. The objective of the paper is to increase security by using adaptive split algorithm (ASA) for the transfer of data on cloud servers. The proposed hybrid adaptive method is implemented in JAVA platform and compared with the traditional methods, such as Artificial Neural Network (ANN), Support Vector Machines (SVM),respectively. Moreover, the statistical measures are evaluated Accuracy, Recall, Precision, F-measure, for the proposed and existing methods.

Published
2020-02-15
How to Cite
D. Kalaiabirami, D. K. L. D. D. M. (2020). RNN with Adaptive Split Algorithm for the Analysis of Security on Cloud Computing. International Journal of Advanced Science and Technology, 29(3), 3191- 3204. Retrieved from https://sersc.org/journals/index.php/IJAST/article/view/4554
Section
Articles